Search

To communicate is to move. There is no way around that. Ifwe pick up comprehensive handbooks or introductory textsin movement science (Hong and Bartlett (2008)) we seethat there is very rich knowledge and tractable mathematicalmodels about different aspects of movements. Yet, we findno chapter on communicative movements. While the fieldof speech motor control is a developed area on its own(Parrell and Lammert (2019)), there is no movement scienceof communication proper, which would include whole-body-,hand-gestural-, signed-, and inter-bodily actions.

We examine the relation between event segmentation in language and cognition in the domain of motion events, focusing on Turkish, a verb-framed language that segments motion paths in separate linguistic units (verb clauses). We compare motion events that have a path change to those that did not have a path change. In the linguistic task, participants were more likely to use multiple verb phrases when describing events that had a path change compared to those that did not have a path change. In the non-linguistic Dwell Time task, participants viewed self-paced slideshows of still images sampled from the motion event videos in the linguistic task. Dwell times for slides corresponding to path changes were not significantly longer than those for temporally similar slides in the events without a path change. These findings suggest that event units in language may not have strong and stable influences on event segmentation in cognition.

Daily experiences are conceptualized as events involving multiple participants and their relations (i.e., thematic roles). When describing events, speakers often do not include all event participants involved. Here, we explore how underlying conceptual requirements and language-specific encoding options influence the content of event descriptions in speech and gesture in two typologically different languages (English, Turkish). Focusing on conceptually peripheral instruments whose status is highly debated, we manipulated the conceptual status of event participants by including events that ‘require' or ‘allow' otherwise syntactically optional instruments. Results showed that the require-allow distinction did not manifest uniformly in Turkish and English in speech, gesture, or when both modalities were considered. However, mention of highly optional event participants (e.g., allowed instruments) was affected by language-specific syntactic encoding options. We conclude that, under more naturalistic elicitation conditions, planning descriptions of instrument events is more heavily affected by language-specific encoding than conceptual prominence of the roles.

Whereas principles of communicative efficiency and legal doctrine dictate that laws be comprehensible to the common world, empirical evidence suggests legal documents are largely incomprehensible to lawyers and laypeople alike. Here, a corpus analysis (n=59million words) first replicated and extended prior work revealing laws to contain strikingly higher rates of complex syntactic structures relative to six baseline genres of English.Next, two pre-registered text generation experiments (n=280) tested two leading hypotheses regarding how these complex structures enter into legal documents in the first place. In line with the \textit{magic spell hypothesis}, we found people tasked with writing official laws wrote in a more convoluted manner than when tasked with writing unofficial legal texts of equivalent conceptual complexity. Contrary to the \textit{copy-and-edit hypothesis}, we did not find evidence that people editing a legal document wrote in a more convoluted manner than when writing the same document from scratch.From a cognitive perspective, these results suggest law to be a rare exception to the general tendency in human language towards communicative efficiency. In particular, these findings indicate law's complexity to be derived from its performativity, whereby low-frequency structures may be inserted to signal law's authoritative, world-state-altering nature, at the cost of increased processing demands on readers. From a law and policy perspective, these results suggest that the tension between the ubiquity and impenetrability of the law is not an inherent one, and that laws can be simplified without a loss or distortion of communicative content.

Speakers are often over-informative, referring to the color and shape of a referent even when all objects in a scene are unique. Interestingly, this helps listeners locate the target. If speakers are indeed sensitive to listeners' online processing demands, they should be more over-informative when addressing someone whose processing is especially slow. Here we show that English-speaking adults produce more redundant color adjectives when speaking to children than adults (Exp 1); that although Spanish-speakers produce fewer redundant color adjectives than English-speakers overall, they too do so more often for children (Exp 2); that these results are independent of experience with young children (Exp 3), and that children themselves (ages 4-10) are more over-informative when speaking to younger children than adults (Exps 4 and 5). Collectively, these results suggest that sensitivity to listeners' online processing demands is robust, emerges early in development, and may be especially tailored to young learners.

Spatial demonstratives are deictic expressions used to point to a referent with language. In the standard view, they encode a spatial proximal\distal contrast between “near” (this) and “far” (that) from the speaker. Several studies have shown that such contrast maps on a perceptual contrast between peripersonal and extrapersonal space. Still, other factors beyond spatial distance influence demonstrative choice. Here we investigate whether the proximal/distal contrast maps also onto a more general contrast between being in physical control/not in control of a target referent. Participants were presented with two circles (red and blue) on a screen. They had to move them with the mouse to find the target circle (the one with two gaps). One circle followed the mouse trajectory (controllable), while the other moved randomly in the center of the screen (not controllable). Unknown to the participants, the gaps only appeared if the stimuli crossed a distance threshold. Importantly, participants had to use stimulus controllability to solve the task. They were instructed to answer by indicating the target to the experimenter using this/that and red/blue (in Italian questo/quello and rosso/blu). Results show that participants used the proximal demonstrative more frequently to refer to the target stimulus when in control. These findings suggest that, similarly to spatial distance, physical control influences demonstrative choice.

In spoken languages, new information is often expressed with a longer duration than given information. We investigated whether signers use duration to mark information status. Fifty deaf Chinese Sign Language (CSL) signers retold a cartoon clip, and we examined how they tracked references. The results showed that CSL signers mostly used nominals, classifiers and constructed actions, but rarely used any pointing or zero anaphora. When focusing on nominals, newly introduced references had a longer duration than the maintained and re-introduced ones, while the durations of maintained and re-introduced nominals did not differ. Additionally, there was a gradient decrease in sign duration over the first three mentions followed by an increase for the fourth and fifth mentions. Furthermore, between two nominal mentions, the more non-nominal referring there were, the shorter the duration of the current nominal mention. Thus, CSL signers vary the duration of nominals to indicate the degree of accessibility.

Telicity is an important semantic feature pointing to event construal: telic verb phrases denote bounded events with an inherent endpoint while atelic verb phrases denote unbounded events without such an endpoint. Languages encode telicity in different ways. Unlike English, Mandarin lacks an overt count-mass distinction and allows bare noun objects to form verb phrases. Would this cross-linguistic difference influence event perception? Experiment 1 elicited descriptions of bounded vs. unbounded events from English and Mandarin native speakers. A clear cross-linguistic difference was found: English speakers mostly used telic predicates for bounded events and atelic predicates for unbounded events while Mandarin speakers gave atelic predicates with bare noun objects for both event types. Experiment 2 explored how English and Mandarin speakers tracked the temporal structure of bounded vs. unbounded events. The two language groups performed similarly. The way people describe events may not affect the way they track event temporal profiles.

We study referential communication about concepts at different levels of abstraction in an interactive concept-level reference game. To better understand processes of abstraction, we investigate superordinate referring expressions (animal). Previous work identified two main factors that influence speakers' choice of referring expressions for concepts: the immediate context and the basic-level effect, i.e. a preference for basic-level terms such as dog. Here we introduce a new concept-level reference game that allows us to study differences in the basic-level effect between comprehension and production and to elicit superordinate referring expressions experimentally. We find that superordinate referring expressions become relevant for groups of objects. Further, we reproduce the basic-level effect in production but not in comprehension. In conclusion, even though basic-level terms are most readily accessible, speakers tailor their expressions to the context, allowing the listener to identify the target concept.

Toddlers can only say one or two words at a time. What do they choose to talk about? We report preliminary results (N=167; mean; 19.5 months) from a pre-registered online experiment on productive language. Toddlers saw six movies. A curtain opened on an introductory scene, the parent closed their eyes, and a new event happened. The curtain closed and the child was asked what happened. On two trials the unseen event was new to the parent (Novel event); on two trials, one of two animals ate the only food in the scene (Agent ambiguous); on two trials, the only animal ate one of the two foods (Patient ambiguous). We predicted that toddlers would selectively generate informative utterances (i.e., referring to the novel event, the agent, and the patient, respectively). Toddlers' productive language was indeed sensitive to what listeners' know; however, unlike adults, they selectively referred to information in common ground.

In this paper we investigate whether subject doubling in French is affected by the Uniform Information Density (UID) principle, which states that speakers prefer language encoding that minimizes fluctuations in information density. We show that, other factors being controlled, speakers are more likely to double the NP subject when it has a high surprisal, thus providing further empirical evidence to the UID principle which predicts a surprisal-redundancy trade-off as a property of natural languages. We argue for the importance of employing GPT-2 to investigate complex linguistic phenomena such as subject doubling, as it enables the estimation of subject surprisal by considering a rather large conversational context, a task made possible by powerful language models that incorporate linguistic knowledge through pre-training on extensive datasets.

This study investigates whether homophone competitors are activated during typewriting and to which extent such activation is modulated by syntactic category. In two experiments, we compared the typewriting of homophone pairs in high vs. low conflict sentences (i.e., both homophones vs. only one homophone in the sentence, respectively) in a sentence dictation task (Experiment 1) and in a question-answering task (Experiment 2). The homophone pairs either belonged to the same or different syntactic categories. In Experiment 1, we found a homophone interference effect in accuracy, independent of conflict and syntactic category. In Experiment 2, this effect was replicated, but in addition, participants were slower to type homophones in a high vs. a low conflict context. Our results show a robust, lexically-situated homophone interference effect, regardless of conflict and syntactic category, but when deeper processing of the sentence is involved, conflict starts to play a role.

What drives lexical alignment in the context of language emergence? We test the theory that limited context promotes alignment, because individuals cannot make use of iconic mappings between shared meanings and forms. Using a novel referential communication paradigm where participants use pre-recorded gesture videos to communicate, we test different context conditions. We find, unexpectedly, no alignment differences between dyads with shared context and dyads with limited context, even though the former have fewer communicative errors. Importantly, we do observe differences when it comes to the iconic strategies used: less shared context promotes the use of (shared) visual iconicity.

Dependency length minimization is a universally observed quantitative property of natural languages. However, the extent of dependency length minimization, and the cognitive mechanisms through which the language processor achieves this minimization remain unclear. This research offers mechanistic insights by postulating that moving a short preverbal constituent next to the main verb explains preverbal constituent ordering decisions better than global minimization of dependency length in SOV languages. This approach constitutes a least-effort strategy because it's just one operation but simultaneously reduces the length of all preverbal dependencies linked to the main verb. We corroborate this strategy using large-scale corpus evidence across all seven SOV languages that are prominently represented in the Universal Dependency Treebank. These findings align with the concept of bounded rationality, where decision-making is influenced by `quick-yet-economical' heuristics rather than exhaustive searches for optimal solutions. Overall, this work sheds light on the role of bounded rationality in linguistic decision-making and language evolution.

Understanding referring expression generation has long been of interest to psycholinguistics, pragmatics, and sociolinguistics. Experimental data in the former two has shown that referring expression generation is modulated by both pragmatic and cognitive considerations, and the latter suggests that referring expressions have social meaning beyond their literal referential utility. This project integrates these three accounts by extending Burnett (2017)'s socially-enriched implementation of the Rational Speech Act (RSA) framework to account for variation in referring expressions used to denote transgender women in two politically opposed media corpora. Our findings highlight the utility of the RSA framework in explaining socially-modulated variation while also accounting for pragmatic and cognitive considerations. Finally, this paper contributes to growing literatures that address the relationship between (alt-)right ideologies about gender and language by highlighting the use of bioessentialist language such as 'biological male' in the propagation of anti-trans rhetoric in the United States.

In our cross-cultural corpus study of 332 comics, we asked whether animacy preference plays a role in comics. Are animates or inanimates more or less grammatically marked compared to each other, similarly to differential marking modulated by animacy in grammars of many languages? Following Opfer (2002), we considered the animacy preference as the expectation that only animates move in a goal-directed way. We focused on two visual morphological markings that indicate motion in comics and differ in their goal-directedness: the goal-directed motion lines (trailing a moving entity) and the non-goal-directed circumfixing lines (surrounding an entity). We found that inanimates are more marked by motion lines than animates in our data, while there is no difference between the two groups with circumfixing lines. This indicates that inanimates need to be marked by motion lines in order to signal their goal-directed movement, which is otherwise unexpected. We call this the principle of “Mark the unexpected!”.

Conversation requires a substantial amount of coordination between dialogue participants, from managing turn taking to negotiating mutual understanding. Part of this coordination effort surfaces as the reuse of linguistic behaviour across speakers, a process often referred to as alignment. While the presence of linguistic alignment is well documented in the literature, several questions remain open, including the extent to which patterns of reuse across speakers have an impact on the emergence of labelling conventions for novel referents. In this study, we put forward a methodology for automatically detecting shared lemmatised constructions---expressions with a common lexical core used by both speakers within a dialogue---and apply it to a referential communication corpus where participants aim to identify novel objects for which no established labels exist. Our analyses uncover the usage patterns of shared constructions in interaction and reveal that features such as their frequency and the amount of different constructions used for a referent are associated with the degree of object labelling convergence the participants exhibit after social interaction.More generally, the present study shows that automatically detected shared constructions offer a useful level of analysis to investigate the dynamics of reference negotiation in dialogue.

Many challenging problems in linguistic analysis concern structures that have a hybrid character---they show evidence of belonging to two, independently motivated types. Proposals often assign them to one or the other class, requiring complication of the theory to handle their exceptionality. We suggest that there is no satisfactory answer to such conundrums under standard, type-based representational theories, for those theories are founded on discrete topologies. As an alternative, we propose “Metric Grammars”--grammatical systems founded on connected topologies. A metric grammar, a recurrent map that has a neural network at its core, changes its grammatical system slightly with each instance of language experience. Focusing on a grammaticalization episode from the history of English---the development of “sort of" and “kind of" from Noun-Preposition structures into adverbs---we provide evidence that metric grammars exhibit statistical anticipation of categorical change, a phenomenon that is difficult to account for with discrete-topology models.

The present study focuses on a type of seemingly arbitrary alternation in modern Russian. Specifically, we investigate the phenomenon of Complementizer Omission, i.e. the alternation between the presence and absence of complementizer with regard to the factors that potentially exert an influence on the alternation in Russian. The choice of alternating pairs is statistically modeled with mixed-effects logistic regression. We find that the complementizer is more likely to be absent in Russian when the matrix subject is a first-or-second-person pronoun, the matrix predicate has a high frequency and the onset of the complement clause is non-ambiguous and non-informational. The findings align well with the Grammaticalization theory, according to which the distribution of complementizer is partially driven by certain types of combinations of matrix subjects and verbs that have become grammaticalized as epistemic markers. Moreover, we argue that the results provide weak support for ambiguity avoidance at the general syntactic level and that the Uniform Information Density account more fully explains the alternation than the Availability account. As in Jaeger and Norcliffe (2009), we propose that more cross-linguistic research should be done on syntactic alternations as "even similar constructions may be processed differently in different languages".

Humans are surrounded by dynamic, continuous streams of stimuli, yet the human mind segments these stimuli and organizes them into discrete event units. Theories of language production assume that segmenting and construing an event provides a starting point for speaking about the event (Levelt, 1989; Konopka & Brown-Schmidt, 2018). However, the precise units of event representation and their mapping to language remain elusive. In this work, we examine event unit formation in linguistic and conceptual event representations. Given cross-linguistic differences in motion event encoding (satellite vs. verb-framed languages), we investigate the extent to which such differences in forming linguistic motion event units affect how speakers of different languages form cognitive event units in non-linguistic tasks. We test English (satellite-framed) and Turkish (verb-framed) speakers on verbal and non-verbal motion event tasks. Our results show that speakers do not rely on the same event unit representations when verbalizing motion vs. identifying motion event units in non-verbal tasks. Therefore, we suggest that conceptual and linguistic event representations are related but distinct levels of event structure.

Because information theory equates information with event occurrence probabilities, when applying its methods, language researchers typically take the information provided by words to be their relative frequencies in a corpus. This implicitly assumes words occur uniformly across contexts, however empirically, word distributions are bursty: the likelihood of most words appearing in most contexts is small, whereas the likelihood of a word recurring in context is much higher. In an elicitation study we examined whether speakers are sensitive to the dynamic word occurrence probabilities this implies. Consistent with proposals that prenominal adjectives increase noun predictability, participants produced numerous seemingly redundant adjectives prior to unambiguous nouns at first mention. However, despite receiving no feedback, they produced significantly fewer adjectives before subsequent mentions of the same nouns, indicating they had re-evaluated their probabilities. These results support the idea that prenominal adjectives facilitate efficient communication, and that speakers' representations of lexical probabilities are dynamic.

Previous work has shown that isolated non-canonical sentences with Object-before-Subject (OSV) order are initially harder to process than their canonical counterparts with Subject-before-Object (SOV) order. Although this difficulty diminishes with appropriate discourse context, the underlying cognitive factors responsible for alleviating processing challenges in OSV sentences remain a question. In this work, we test the hypothesis that dependency length minimization is a significant predictor of non-canonical (OSV) syntactic choices, especially when controlling for information status such as givenness and surprisal measures. We extract sentences from the Hindi-Urdu Treebank corpus (HUTB) that contain clearly-defined subjects and objects, systematically permute the preverbal constituents of those sentences, and deploy a classifier to distinguish between original corpus sentences and artificially generated alternatives. The classifier leverages various discourse-based and cognitive features, including dependency length, surprisal, and information status, to inform its predictions. Our results suggest that, although there exists a preference for minimizing dependency length in non-canonical corpus sentences amidst the generated variants, this factor does not significantly contribute in identifying corpus sentences above and beyond surprisal and givenness measures. Notably, discourse predictability emerges as the primary determinant of constituent-order preferences. These findings are further supported by human evaluations involving 44 native Hindi speakers. Overall, this work sheds light on the role of expectation adaptation in word-ordering decisions. We conclude by situating our results within the theories of discourse production and information locality.

Online mental health support plays a crucial role in addressing the mental health issues faced by modern individuals. However, delivering high-quality online mental health support presents a significant challenge. In response to this challenge, we introduce MentalBlend, a framework that leverages psychological counseling theories, including Cognitive-Behavioral Therapy, Dialectical Behavior Therapy, Person-Centered Therapy, and Reality Therapy, to guide large language models (LLMs) in offering professional online mental health support to individuals seeking assistance. Experimental evidence validates that the collaboration between LLMs and the MentalBlend framework results in the generation of responses that align with professional standards for online mental health support. Overall, our research aims to contribute to advancing the capabilities of LLMs in understanding the emotional backgrounds of help-seekers and delivering professional mental health support effectively.

When we communicate with others, we often repeat aspects of each other's communicative behavior such as sentence structures and words. Such behavioral alignment has been mostly studied for speech or text. Yet, language use is mostly multimodal, flexibly using speech and gestures to convey messages. Here, we explore the use of alignment in speech (words) and co-speech gestures (iconic gestures) in a referential communication task aimed at finding labels for novel objects in interaction. In particular, we investigate how people flexibly use lexical and gestural alignment to create shared labels for novel objects and whether alignment in speech and gesture are related over time. The present study shows that interlocutors establish shared labels multimodally, and alignment in words and iconic gestures are used throughout the interaction. We also show that the amount of lexical alignment positively associates with the amount of gestural alignment over time, suggesting a close relationship between alignment in the vocal and manual modalities.

Speech production in aphasia is often described as “effortful”, though the consequences of consistent, high degrees of cognitive effort have not been explored. Using recent work on mental effort as a theoretical framework, the present study examined how effort-related fatigue produces decrements in performance in picture naming among participants with post-stroke aphasia. We analyzed three data sets from prior studies where participants completed a large picture naming test. Decreasing naming accuracy across trials was statistically significant in two of the three samples. There were also significant effects of practice (better performance on a second test administration), word frequency (better performance for more frequent words), and word length (better performance for shorter words). These results are the first concrete demonstration of fatigue affecting performance on a language task in post-stroke aphasia. They open a new avenue for research on mental effort/fatigue with potential implications for aphasia assessment, treatment, and management.

A speaker's use of language is one of the most important indicators in detecting deception. To date, however, little research has focused on grammatical cues used in deceitful statements. One such cue is evidentiality which is the grammatical encoding for the source of information; i.e., whether the speaker has direct or indirect access to what they assert. This study investigates whether and how evidentiality coding in Turkish, an evidential language, interacts with producing deceitful and truthful narratives. Deceptive retellings were notably longer and syntactically more complex compared to truthful counterparts. Our hypothesis of increased past forms in deception was confirmed, alongside a heightened use of direct evidential inflection (–DI) in deceptive conditions. This exploration sheds light on the nuanced relationship between grammatical evidentiality and deceptive language use.

Gricean maxims prescribe cooperative speakers to make their utterances maximally informative so that listeners have the highest chance of understanding the utterances. At the same time, speakers are expected to save effort and not produce descriptions that are more explicit than necessary. In this work, we first ask how predictability of the described events affects the choice of anaphoric referring expressions. We show that speakers prefer phonologically overt descriptions, such as definite NPs, when they refer to agents that behave in an unexpected way. We further test how the interpretation of referring expressions changes depending on the listening conditions and prior expectations about the plausibility of an event. Our work shows that the speaker's extra effort in choosing a more phonologically overt referring expression is justified by listeners' behavior: they report having heard an utterance which is more plausible than the originally spoken utterance and which contains additional phonological material.

Semanticists have debated the extent to which modality and causation are related in natural language. This paper aims to promote a theory in which overt causatives share core components of meaning with deontic modals. We report a sentence recall experiment that suggests that priming can be used to target the high-level semantic representations shared between two syntactically distinct linguistic expressions. Our results show that it's possible to prime the production of the deontic modal 'had to' (e.g., ``George 'had to' go to the store"), with causative 'made' (e.g., ``Jane 'made' George go to the store''), suggesting that the two expressions share a component of their meaning. Our results contribute to the methodological development in experimental semantics by establishing the utility of the priming effect to target meaning.

Languages differ in how they form questions that are equivalent to English questions such as who does John think Maria loves? in that the correct answer is who John thinks Maria loves, and not who Maria actually loves. Linguists disagree about how Polish makes such inquiries, and to date, no research has investigated how native Polish-speaking adults judge, process or produce these inquiries. In this paper, we investigated the nature of Polish questions via a corpus study, a grammaticality judgment study, and a spoken production study. Taken together, the results of these studies suggest that Polish has several syntactically distinct options for making these sorts of inquiries. Although, at first blush, this seems inconsistent with linguistic theories that argue against syntactic optionality, closer examination reveals that discourse context strongly affects which option is preferred. These findings highlight the importance of considering context, and the pitfall of studying sentences presented in isolation when evaluating linguistic or psycholinguistic claims.

We investigated the emergence of dispersion in phonological systems using an established experimental paradigm in which pairs of participants play a non-linguistic communication game, taking turns to select discrete colors from a continuous underlying space and send them to each other to communicate animal silhouettes. Over time participants established sets of signals made up of combinatorial color units, analogous to the phonemes of natural language. This allowed us to investigate the role of interactive pressures on the emergence of organizational structure in phonological inventories, principally dispersion. We manipulated minimum signal length (as a means of investigating the role of coarticulation) and the presence of probabilistic noise. We also manipulated the nature of the underlying color space. There was an effect of colorspace but not of noise or minimum signal-length. However, dispersion occurred at above-chance levels in all conditions. Our results provide evidence for the role of communicative interaction in the emergence and cultural evolution of phonological structure.

The effect of syntactic priming exhibits three well-documented empirical properties: the lexical boost, the inverse frequency effect, and the asymmetrical decay. We aim to show how these three empirical phenomena can be reconciled in a general learning framework, the hierarchical Bayesian model (HBM). The model represents syntactic knowledge in a hierarchical structure of syntactic statistics, where a lower level represents the verb-specific biases of syntactic decisions, and a higher level represents the abstract bias as an aggregation of verb-specific biases. This knowledge is updated in response to experience by Bayesian inference. In simulations, we show that the HBM captures the above-mentioned properties of syntactic priming. The results indicate that some properties of priming which are usually explained by a residual activation account can also be explained by an implicit learning account. We also discuss the model's implications for the lexical basis of syntactic priming.

Variation in the use of syntactic alternations has long been an explanatory target of language production theories. In this work, we test the predictions of several semantic, pragmatic and psycholinguistic theories of language use for the English dative alternation. We first experimentally test the role of incremental constituent informativity in the dative alternation, and find that contrary to information structural and RSA models of production, informativity has little effect on production preferences. We then more rigorously focus on accessibility effects, demonstrating that a lossy-context automatic policy can recover a key pattern of accessibility. Ultimately, we conclude that audience design pressures likely do not influence incremental production, but simply may affect planning at a broader scope.

Classifiers play a fundamental role in shaping how objects are categorized in Mandarin Chinese. We conducted object naming experiments with different types of classifiers as prompts and analyzed the distribution of names via the taxonomic device, by which nouns are divided into three levels according to the level of specificity, i.e., basic (e.g. apple), superordinate (e.g. fruit) and subordinate (e.g. golden apple) levels. We observe that different classifiers induce distinct distributions of names across the three levels. Under the general classifier condition, participants use more general terms for home furnishing objects (e.g., ‘furniture') but not for animals, whereas the specific classifier condition consistently reveals a preference for basic level names (e.g., ‘table'), which are less general and represent the most inclusive category at which objects share common features and can be easily recognized. These findings contribute to our understanding of language production in Mandarin Chinese and highlight the importance of considering grammatical factors when examining referential expression choices.

This study explores whether Large Language Models (LLMs) can mimic human cognitive processes, particularly pragmatic reasoning in language processing. Focusing on how humans tend to offer semantically similar alternatives in response to negated statements, the research examines if LLMs, both base and fine-tuned, exhibit this behavior. The experiment involves a cloze task, where the models provide completions to negative sentences. Findings reveal that chat models closely resemble human behavior, while completion models align worse with human responses. This indicates that mere linguistic input statistics might be inadequate for LLMs to develop behaviours consistent with pragmatic reasoning. Instead, conversational fine-tuning appears to enable these models to adopt behaviors akin to human pragmatic reasoning. This research not only sheds light on LLMs' capabilities but also prompts further inquiry into language acquisition, especially the role of conversational interactions in developing pragmatic reasoning.

Our world knowledge is deeply embedded in language. The word “banana” immediately brings to mind the color “yellow”. Oftentimes, however, when we read about “banana”, we do not expect the color “yellow” to be explicitly mentioned as in “yellow banana”. Frequent omission of obvious information given our world knowledge is predicted by so-called informativity expectations, which capture our preferences for newsworthy and informative utterances. Here we present two studies investigating informativity expectations in a socially situated context of gender stereotypicality and testing whether expressions like “female nurses” are less preferred than expressions like “female directors”. While the results show a clear impact of informativity expectations, effects of gender stereotypes turn out to be difficult to overcome.

This paper explores how speakers choose between two utterance alternatives with similar syntactic properties and distinct yet related meanings. We consider the interaction of two speaker pressures: to mention accessible lexical items early in the utterance and to mention informative content early in the utterance, the latter of which is explicitly predicted by an incremental Rational Speech Act (IRSA) model. In Exp. 1, we observed a significant effect of accessibility on utterance choice in an online spoken production task, which elicited descriptions of the relationship between two entities using a provided verb. We found that making entities more accessible via foregrounding led speakers to mention them earlier. In Exp. 2, an interactive production task, both informativity and foregrounding were manipulated. While IRSA predicts more informative content to be mentioned earlier in the sentence, we observed neither significant effects of informativity nor of accessibility. Consistent with recent work on Good-Enough theories of production, we conclude that even when two sentences are not entirely meaning-equivalent, production choices can be affected by lexical accessibility; the pressure to mention informative material early, however, should be investigated further

Action descriptions can include or omit various types of information. In this paper, we are interested in the inclusion of manner in verbs. We use the concept of descriptive verbs, first introduced by Snell-Hornby (1983), and hypothesise that the use of descriptive verbs is reliant on having enough context to determine if the descriptive verb is correct and preferred as opposed to a more general non-descriptive verb. We conduct two online experiments in which participants are asked to indicate their preference for a verb after seeing varying amounts of textual and visual context. Our results show that textual context does not contribute to verb choice. However, we find evidence that videos contain information which creates agreement between participants, suggesting there are objective reasons to choose a descriptive or non-descriptive verb.

Verbal descriptions of spatial configurations open a window to a specific aspect of visual cognition relevant to the interpretation of topological relations in the visual world. The present study reports an experimental investigation of the production of spatial prepositions by human participants while they verbally described visual stimuli within a stimuli battery commonly utilized in relevant research. The analysis of participants' eye movements revealed a relationship between the variety of spatial terms in the given language and native speakers' fixation patterns on the stimuli. A broader spectrum of spatial expressions, describing the same visual scene, is related to longer and more frequent fixations on the stimuli. The findings reflect cognitive processes, as indicated by oculomotor control variables, related to the verbal expression of spatial relationships.

While effects of animacy and attention have been studied quite extensively in adult speakers, less is known about their role in child language production. In the present study we fill this gap by testing German-speaking preschool children in two language production tasks using eye-tracking. We find that animacy does neither affect the production of transitive sentences nor the production of conjoined noun phrases. By contrast, we find significant effects of attentional orienting. Children were more likely to first fixate an entity when it had been preceded by a visual cue and was hence in their focus of attention. While this held true across tasks, attentional orienting only affected children's production of conjoined noun phrases but not the production of transitive sentences. Effects of attentional orienting therefore seem conditioned by language production affordances. In sum, our findings provide new evidence that animacy and attention play different roles in children's language production.

Working Memory (WM) is a necessary component for models of human cognition and human-inspired robot cognitive architectures. Different theories explain how the limited capacity of WM should be maintained, including theories of forgetting through decay and interference. Yet, it is unclear how WM models informed by these theories might be used to inform robot cognition, and how they might shape robots' ability to engage in natural, situated, language-based interactions. To resolve this tension, in this work we consider entity-level, feature-based WM systems that can be integrated into robot cognitive architectures to reflect both decay- and interference-based dynamics. We demonstrate how different parameterizations of these WM strategies have fundamentally different error modes in different interaction contexts. We formulate rules that inform the selection of decay and interference parameters to be used in contexts with different factors that are important for language-based interaction.

This paper provides an epistemological and methodological analysis of the practice of using neural language models to simulate brain language processing. Firstly, neural language models are introduced; a study case showing how neural language models are being applied in cognitive neuroscience for simulative purposes is then presented; after recalling the main epistemological features of the simulative method in artificial intelligence, it is finally examined how the simulative method is modified when using neural language models. In particular, it is argued that the epistemic opacity of neural language models requires that the brain itself be used to simulate the model and to test hypotheses about the model, in what is called here a co-simulation.

There is no consensus in the literature about the role of disfluencies as cues to deception. The current study used an interactive picture-description game to collect speech data of speakers and veracity assessments of listeners engaged in a socially meaningful interaction. The paradigm was implemented so that not only statement veracity (i.e., true or false) could be analysed, but also speaker intention (i.e., wanting or not wanting to be believed) and listener decision (i.e., believing or not believing the speaker). The goal was to test whether veracity, intention, and decision could be predicted based on disfluency patterns, using Multivariate Pattern Analysis. We observed that veracity and intention could not be predicted above chance on the basis of disfluency features, while listeners based their decision on these patterns. These results suggest that listeners wrongly interpret disfluencies as cues to deception.

Models of word recognition and production diverge on the question of how to represent complex words. Under the morpheme-based approach, each morpheme is represented asa separate unit, while under the word-based approach, morphemes are represented in lexical networks. The word-based approach is consistent with construction morphologyand recent research on the grammar network. However, while the network view of constructions has become popular in recent years, there is little computational and experimental research on this topic. In the current study, we used a computational network model (based on graph theory) and an experiment to investigate the Romance component of English morphology. Specifically, we provide evidence that complex words can be conceptualised as paths in a weighted directed network of morphemes.

In this paper we introduce a novel way of quantifying typing expertise according to the ability to type without visual guidance from the keyboard (i.e., in a blind typing task). We present results of two experiments showing that performance in blind typing allows dissociating two profiles of typists, touch and non-touch typists. In Experiment 1, analyzing more than 100 typists, we show that performance in blind typing correlates with faster typing speed of lexical and non-lexical material, but not with low-level motoric skills. In Experiment 2, we show that touch and non-touch typists present differences in both written and spoken language production, but not language perception. Our results demonstrate that the characterization of “everyday touch typists” not only discriminates typing skills but may also capture distinct cognitive abilities. Spanning the fields of sensorimotor and linguistic processing, this study stresses the importance of considering language processing to understand typing skills.

This study investigates whether fixation behaviour during scene viewing can offer insights into sequentialisation in verbal scene description production. We explored the correlation between visual and linguistic attention on naturalistic scenes using scene descriptions and eye movement measures. Results demonstrate an overlap in object prioritization during scene viewing and describing. Our additional analysis of scene descriptions reveals a tendency towards selecting and prioritizing category-specific objects.

A key task in natural language generation (NLG) is Referring Expression Generation (REG), in which a set of properties are selected to describe a target referent. Computational cognitive models of REG typically focus on REG-in-context, where the referring expressions are designed to take into account the conversational context into which they are to be generated. However, in practice, these methods only focus on linguistic context of the text into which they are to be inserted. We argue that to develop robust models of naturalistic human referring, REG will need to move beyond linguistic context, and account for cognitive and environmental context as well. That is, we propose that a cognitivist, interactionist, and situated approach to modeling REG is needed. In this paper, we present GAIA, a Givenness Hierarchy theoretic model of REG, and demonstrate the immediate qualitative benefits of this model over the traditional REG model which it extends.

Speakers and listeners show an informativity bias in the use and interpretation of color modifiers. For example, speakers use color more often when referring to objects that vary in color than to objects with a prototypical color. Likewise, listeners look away from objects with prototypical colors upon hearing that color mentioned. Here we test whether speakers and listeners account for another factor related to informativity: the strength of the association between lexical categories and color. Our results demonstrate that speakers and listeners' choices are indeed influenced by this factor; as such, it should be integrated into current pragmatic theories of informativity and computational models of color reference.

It has been proposed that Chinese classifiers facilitate efficient communication by reducing the noun uncertainty in context. Although recent evidence has undermined this proposal, it was obtained using the common method of equating noun occurrence probabilities with corpus frequencies. This method implicity assumes words occur uniformly across contexts, yet this is inconsistent with empirical findings showing word distributions to be bursty. We hypothesized that if language users are sensitive to burstiness, and if classifiers provide information about upcoming nouns, this information will be less important in reducing uncertainty about noun after their first mention. We show that classifier usage provides more information at earlier mentions of nouns and and less information at later mentions, and that the actual classifier distribution appears inconsistent with previous proposals. These results support the idea that classifiers facilitate efficient communication and indicate that language users representations of lexical probabilities in context are dynamic.

Drawing on the principles of associative learning theory and positing a statistical foundation for language acquisition, this paper investigates the independent contributions of the predictive validities of verbal and constructional cues in English native and non-native speakers' mental representations of the English as-predicative construction. This is examined through two experiments: a sentence completion task targeting constructional outcome retrieval (Experiment 1), and a gap-fill schema task with a focus on verb retrieval (Experiment 2). The results demonstrate that both cues are integrated in parallel when eliciting a constructional outcome (Experiment 1), but only construction cue validity plays a role in eliciting verbal outcomes (Experiment 2). Verb frequency and voice additionally contribute to the retrieval of verbal and constructional information in distinct manners. The present study raises discussions about distributional cue integration in forward versus backward retrieval of linguistic information, in addition to emphasizing the importance of considering cross-linguistic factors in future research.

In two experiments (N = 179), we studied the effect of contextual similarity and training mode on new vocabulary learning. Adult participants were trained on blocks of items that were semantically similar, phonologically similar, or unrelated to one another. Each participant was trained through passive exposure, active comprehension, or active production of the new vocabulary. Exp 1 trained items in clusters of 9, whereas Exp 2 trained the same number of items in clusters of 3. Exp 2 also assessed delayed retention 48-72 hours after training. Results showed a robust and negative impact of semantic similarity and production mode on vocabulary learning. A detrimental effect of phonological similarity was only observed in the delayed test. These results suggest that adding the challenge of resolving similarity-induced competition and articulating the word-form negatively impacts the quick acquisition of new vocabulary.