Search

In recent years, biomedical event extraction has been dominated by complicated pipeline and joint methods, which need to be simplified. In addition, existing work has not effectively utilized trigger word information explicitly. Hence, we propose MLSL, a method based on multi-layer sequence labeling for joint biomedical event extraction. MLSL does not introduce prior knowledge and complex structures. Moreover, it explicitly incorporates the information of candidate trigger words into the sequence labeling to learn the interaction relationships between trigger words and argument roles. Based on this, MLSL can learn well with just a simple workflow. Extensive experimentation demonstrates the superiority of MLSL in terms of extraction performance compared to other state-of-the-art methods., Comment: 13 pages, 3 figures, accepted by NLPCC2024

An extension $B\subset A$ of finite dimensional algebras is bounded if the $B$-$B$-bimodule $A/B$ is $B$-tensor nilpotent, its projective dimension is finite and $\mathrm{Tor}_i^B(A/B, (A/B)^{\otimes_B j})=0$ for all $i, j\geq 1$. We show that for a bounded extension $B\subset A$, the algebras $A$ and $B$ are singularly equivalent of Morita type with level. Additionally, under mild conditions, their stable categories of Gorenstein projective modules and Gorenstein defect categories are equivalent, respectively. Some homological conjectures are also investigated for bounded extensions, including Auslander-Reiten conjecture, finististic dimension conjecture, Fg condition, Han's conjecture, and Keller's conjecture. Applications to trivial extensions and triangular matrix algebras are given. In course of proof, we give some handy criteria for a functor between module categories to induce triangle functors between stable categories of Gorenstein projective modules and Gorenstein defect categories, which generalise some known criteria, and hence might be of independent interest., Comment: Comments are welcome. Many typos corrected

Large Language Models (LLMs) have played an important role in many fields due to their powerful capabilities.However, their massive number of parameters leads to high deployment requirements and incurs significant inference costs, which impedes their practical applications. Training smaller models is an effective way to address this problem. Therefore, we introduce OpenBA-V2, a 3.4B model derived from multi-stage compression and continual pre-training from the original 15B OpenBA model. OpenBA-V2 utilizes more data, more flexible training objectives, and techniques such as layer pruning, neural pruning, and vocabulary pruning to achieve a compression rate of 77.3\% with minimal performance loss. OpenBA-V2 demonstrates competitive performance compared to other open-source models of similar size, achieving results close to or on par with the 15B OpenBA model in downstream tasks such as common sense reasoning and Named Entity Recognition (NER). OpenBA-V2 illustrates that LLMs can be compressed into smaller ones with minimal performance loss by employing advanced training objectives and data strategies, which may help deploy LLMs in resource-limited scenarios.

As a generalization of the classical killing-contractible-complexes lemma, we present algebraic Morse theory via homological perturbation lemma, in a form more general than existing presentations in the literature. Two-sided Anick resolutions due to E.~Sk\"{o}ldberg are generalised to algebras given by quivers with relations and a minimality criterion is provided as well. Two applications of algebraic Morse theory are presented. It is shown that the Chinese algebra of rank $n\geq 1$ is homologically smooth and of global dimension $\frac{n(n+1)}{2}$, and the minimal two-sided projective resolution of a Koszul algebra is constructed.

Generalising a previous work of Jiang and Sheng, a cohomology theory for differential Lie algebras of arbitrary weight is introduced. The underlying $L_\infty[1]$-structure on the cochain complex is also determined via a generalised version of higher derived brackets. The equivalence between $L_\infty[1]$-structures for absolute and relative differential Lie algebras are established. Formal deformations and abelian extensions are interpreted by using lower degree cohomology groups. Also we introduce the homotopy differential Lie algebras. In a forthcoming paper, we will show that the operad of homotopy (relative) differential Lie algebras is the minimal model of the operad of (relative) differential Lie algebras.

Biomedical event extraction is an information extraction task to obtain events from biomedical text, whose targets include the type, the trigger, and the respective arguments involved in an event. Traditional biomedical event extraction usually adopts a pipelined approach, which contains trigger identification, argument role recognition, and finally event construction either using specific rules or by machine learning. In this paper, we propose an n-ary relation extraction method based on the BERT pre-training model to construct Binding events, in order to capture the semantic information about an event's context and its participants. The experimental results show that our method achieves promising results on the GE11 and GE13 corpora of the BioNLP shared task with F1 scores of 63.14% and 59.40%, respectively. It demonstrates that by significantly improving theperformance of Binding events, the overall performance of the pipelined event extraction approach or even exceeds those of current joint learning methods.

Aspect Sentiment Understanding (ASU) in interactive scenarios (e.g., Question-Answering and Dialogue) has attracted ever-more interest in recent years and achieved important progresses. However, existing studies on interactive ASU largely ignore the coreference issue for opinion targets (i.e., aspects), while this phenomenon is ubiquitous in interactive scenarios especially dialogues, limiting the ASU performance. Recently, large language models (LLMs) shows the powerful ability to integrate various NLP tasks with the chat paradigm. In this way, this paper proposes a new Chat-based Aspect Sentiment Understanding (ChatASU) task, aiming to explore LLMs' ability in understanding aspect sentiments in dialogue scenarios. Particularly, this ChatASU task introduces a sub-task, i.e., Aspect Chain Reasoning (ACR) task, to address the aspect coreference issue. On this basis, we propose a Trusted Self-reflexion Approach (TSA) with ChatGLM as backbone to ChatASU. Specifically, this TSA treats the ACR task as an auxiliary task to boost the performance of the primary ASU task, and further integrates trusted learning into reflexion mechanisms to alleviate the LLMs-intrinsic factual hallucination problem in TSA. Furthermore, a high-quality ChatASU dataset is annotated to evaluate TSA, and extensive experiments show that our proposed TSA can significantly outperform several state-of-the-art baselines, justifying the effectiveness of TSA to ChatASU and the importance of considering the coreference and hallucination issues in ChatASU.

Multimodal Conversational Emotion (MCE) detection, generally spanning across the acoustic, vision and language modalities, has attracted increasing interest in the multimedia community. Previous studies predominantly focus on learning contextual information in conversations with only a few considering the topic information in single language modality, while always neglecting the acoustic and vision topic information. On this basis, we propose a model-agnostic Topic-enriched Diffusion (TopicDiff) approach for capturing multimodal topic information in MCE tasks. Particularly, we integrate the diffusion model into neural topic model to alleviate the diversity deficiency problem of neural topic model in capturing topic information. Detailed evaluations demonstrate the significant improvements of TopicDiff over the state-of-the-art MCE baselines, justifying the importance of multimodal topic information to MCE and the effectiveness of TopicDiff in capturing such information. Furthermore, we observe an interesting finding that the topic information in acoustic and vision is more discriminative and robust compared to the language.

Weakly-supervised Phrase Grounding (WPG) is an emerging task of inferring the fine-grained phrase-region matching, while merely leveraging the coarse-grained sentence-image pairs for training. However, existing studies on WPG largely ignore the implicit phrase-region matching relations, which are crucial for evaluating the capability of models in understanding the deep multimodal semantics. To this end, this paper proposes an Implicit-Enhanced Causal Inference (IECI) approach to address the challenges of modeling the implicit relations and highlighting them beyond the explicit. Specifically, this approach leverages both the intervention and counterfactual techniques to tackle the above two challenges respectively. Furthermore, a high-quality implicit-enhanced dataset is annotated to evaluate IECI and detailed evaluations show the great advantages of IECI over the state-of-the-art baselines. Particularly, we observe an interesting finding that IECI outperforms the advanced multimodal LLMs by a large margin on this implicit-enhanced dataset, which may facilitate more research to evaluate the multimodal LLMs in this direction.

It is well known that for Auslander algebras, the category of all (finitely generated) projective modules is an abelian category and this property of abelianness characterizes Auslander algebras by Tachikawa theorem in 1974. Let $n$ be a positive integer. In this paper, by using torsion theoretic methods, we show that $ n $-Auslander algebras can be characterized by the abelianness of the category of modules with projective dimension less than $ n $ and a certain additional property, extending the classical Auslander-Tachikawa theorem. By Auslander-Iyama correspondence a categorical characterization of the class of Artin algebras having $ n $-cluster tilting modules is obtained. Since higher Auslander algebras are a special case of higher Auslander-Gorenstein algebras, the results are given in the general setting as extending previous results of Kong. Moreover, as an application of some results, we give categorical descriptions for the semisimplicity and selfinjectivity of an Artin algebra. Higher Auslander-Gorenstein Algebras are also studied from the viewpoint of cotorsion pairs and, as application, we show that they satisfy in two nice equivalences.

This paper is devoted to study the relationship between two important notions in ring theory, category theory, and representation theory of Artin algebras; namely, Gabriel topologies and higher Auslander(-Gorenstein) algebras. It is well-known that the class of all torsionless modules over a higher Auslander(-Gorenstein) algebra is a torsion-free class of a hereditary torsion theory that is cogenerated by its injective envelope and so by Gabriel-Maranda correspondence we can define a Gabriel topology on it. We show that higher Auslander(-Gorenstein) algebras can be characterized by this Gabriel topology. This characterization can be considered as a higher version of the Auslander-Buchsbaum-Serre theorem that is considered as one of the most important achievements of the use of homological algebra in the theory of commutative rings. Among some applications, the results also reveal a relation between the projective dimension of a module and the projective dimensions of the annihilator ideals of its objects over higher Auslander algebras., Comment: arXiv admin note: text overlap with arXiv:2402.17293

The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In this paper, we propose a novel two-branch hierarchical model for short-form video humor detection (SVHD), named Comment-aided Video-Language Alignment (CVLA) via data-augmented multi-modal contrastive pre-training. Notably, our CVLA not only operates on raw signals across various modal channels but also yields an appropriate multi-modal representation by aligning the video and language components within a consistent semantic space. The experimental results on two humor detection datasets, including DY11k and UR-FUNNY, demonstrate that CVLA dramatically outperforms state-of-the-art and several competitive baseline approaches. Our dataset, code and model release at https://github.com/yliu-cs/CVLA., Comment: Accepted by ICMR 2024

Large language models (LLMs) with billions of parameters have demonstrated outstanding performance on various natural language processing tasks. This report presents OpenBA, an open-sourced 15B bilingual asymmetric seq2seq model, to contribute an LLM variant to the Chinese-oriented open-source model community. We enhance OpenBA with effective and efficient techniques as well as adopt a three-stage training strategy to train the model from scratch. Our solution can also achieve very competitive performance with only 380B tokens, which is better than LLaMA-70B on the BELEBELE benchmark, BLOOM-176B on the MMLU benchmark, GLM-130B on the C-Eval (hard) benchmark. This report provides the main details to pre-train an analogous model, including pre-training data processing, Bilingual Flan data collection, the empirical observations that inspire our model architecture design, training objectives of different stages, and other enhancement techniques. Additionally, we also provide the fine-tuning details of OpenBA on four downstream tasks. We have refactored our code to follow the design principles of the Huggingface Transformers Library, making it more convenient for developers to use, and released checkpoints of different training stages at https://huggingface.co/openBA. More details of our project are available at https://github.com/OpenNLG/openBA.git.

Extracting sentiment elements using pre-trained generative models has recently led to large improvements in aspect-based sentiment analysis benchmarks. However, these models always need large-scale computing resources, and they also ignore explicit modeling of structure between sentiment elements. To address these challenges, we propose an opinion tree parsing model, aiming to parse all the sentiment elements from an opinion tree, which is much faster, and can explicitly reveal a more comprehensive and complete aspect-level sentiment structure. In particular, we first introduce a novel context-free opinion grammar to normalize the opinion tree structure. We then employ a neural chart-based opinion tree parser to fully explore the correlations among sentiment elements and parse them into an opinion tree structure. Extensive experiments show the superiority of our proposed model and the capacity of the opinion tree parser with the proposed context-free opinion grammar. More importantly, the results also prove that our model is much faster than previous models.

Quite much recent studies has been attracted to the operated algebra since it unifies various notions such as the differential algebra and the Rota-Baxter algebra. An $\Omega$-operated algebra is a an (associative) algebra equipped with a set $\Omega$ of linear operators which might satisfy certain operator identities such as the Leibniz rule. A free $\Omega$-operated algebra $B$ can be generated on an algebra $A$ similar to a free algebra generated on a set. If $A$ has a Gr\"{o}bner-Shirshov basis $G$ and if the linear operators $\Omega$ satisfy a set $\Phi$ of operator identities, it is natural to ask when the union $G\cup \Phi$ is a Gr\"{o}bner-Shirshov basis of $B$. A previous work answers this question affirmatively under a mild condition, and thereby obtains a canonical linear basis of $B$. In this paper, we answer this question in the general case of multiple linear operators. As applications we get operated Gr\"{o}bner-Shirshov bases for free differential Rota-Baxter algebras and free integro-differential algebras over algebras as well as their linear bases. One of the key technical difficulties is to introduce new monomial orders for the case of two operators, which might be of independent interest., Comment: 27 pages

A differential algebra with weight is an abstraction of both the derivation (weight zero) and the forward and backward difference operators (weight $\pm 1$). In 2010 Loday established the Koszul duality for the operad of differential algebras of weight zero. He did not treat the case of nonzero weight, noting that new techniques are needed since the operad is no longer quadratic. This paper continues Loday's work and establishes the Koszul duality in the case of nonzero weight. In the process, the minimal model and the Koszul dual homotopy cooperad of the operad governing differential algebras with weight are determined. As a consequence, a notion of homotopy differential algebras with weight is obtained and the deformation complex as well as its $L_\infty$-algebra structure for differential algebras with weight are deduced., Comment: Final version. arXiv admin note: text overlap with arXiv:2203.02960

Given a recollement of three proper dg algebras over a noetherian commutative ring, e.g. three algebras which are finitely generated over the base ring, which extends one step downwards, it is shown that there is a short exact sequence of their singularity categories. This allows us to recover and generalise some known results on singularity categories of finite-dimensional algebras., Comment: Section 3 is new, and in Section 4 the base ring is changed from a field to a commutative noetherian ring and in Section 6 the base ring is changed from a field to an arbitrary commutative ring

It is well known that translations generated by an excellent document-level neural machine translation (NMT) model are consistent and coherent. However, existing sentence-level evaluation metrics like BLEU can hardly reflect the model's performance at the document level. To tackle this issue, we propose a Discourse Cohesion Evaluation Method (DCoEM) in this paper and contribute a new test suite that considers four cohesive manners (reference, conjunction, substitution, and lexical cohesion) to measure the cohesiveness of document translations. The evaluation results on recent document-level NMT systems show that our method is practical and essential in estimating translations at the document level.

Causal relation extraction of biomedical entities is one of the most complex tasks in biomedical text mining, which involves two kinds of information: entity relations and entity functions. One feasible approach is to take relation extraction and function detection as two independent sub-tasks. However, this separate learning method ignores the intrinsic correlation between them and leads to unsatisfactory performance. In this paper, we propose a joint learning model, which combines entity relation extraction and entity function detection to exploit their commonality and capture their inter-relationship, so as to improve the performance of biomedical causal relation extraction. Meanwhile, during the model training stage, different function types in the loss function are assigned different weights. Specifically, the penalty coefficient for negative function instances increases to effectively improve the precision of function detection. Experimental results on the BioCreative-V Track 4 corpus show that our joint learning model outperforms the separate models in BEL statement extraction, achieving the F1 scores of 58.4% and 37.3% on the test set in Stage 2 and Stage 1 evaluations, respectively. This demonstrates that our joint learning system reaches the state-of-the-art performance in Stage 2 compared with other systems., Comment: 15 pages, 3 figures

This paper is devoted to studying deformation, cohomology theory of Rota-Baxter pre-Lie algebras of arbitrary weights. First we give the notion of a new representation of a Rota-Baxter pre-Lie algebra of arbitrary weight and define the cohomology theory of a Rota-Baxter pre-Lie algebra of arbitrary weight. Then we study formal deformations by lower degree cohomology groups. Finally, we classify abelian extensions of Rota-Baxter pre-Lie algebras of arbitrary weight using the second cohomology group, and classify skeletal Rota-Baxter pre-Lie 2-algebra of arbitrary weight using the third cohomology group as applications., Comment: 28 pages. arXiv admin note: text overlap with arXiv:2204.00160, arXiv:2108.06744

A cohomology theory of weighted Rota-Baxter $3$-Lie algebras is introduced. Formal deformations, abelian extensions, skeletal weighted Rota-Baxter $3$-Lie 2-algebras and crossed modules of weighted Rota-Baxter 3-Lie algebras are interpreted by using lower degree cohomology groups., Comment: Title changed to "Deformations and cohomology theory of Rota-Baxter $3$-Lie algebras of arbitrary weights" J. Geom. Phys. to appear

Pre-trained masked language models have demonstrated remarkable ability as few-shot learners. In this paper, as an alternative, we propose a novel approach to few-shot learning with pre-trained token-replaced detection models like ELECTRA. In this approach, we reformulate a classification or a regression task as a token-replaced detection problem. Specifically, we first define a template and label description words for each task and put them into the input to form a natural language prompt. Then, we employ the pre-trained token-replaced detection model to predict which label description word is the most original (i.e., least replaced) among all label description words in the prompt. A systematic evaluation on 16 datasets demonstrates that our approach outperforms few-shot learners with pre-trained masked language models in both one-sentence and two-sentence learning tasks., Comment: Accepted to COLING 2022. The code is publicly available at https://github.com/cjfarmer/TRD_FSL

This paper investigates Rota-Baxter associative algebras of of arbitrary weights, that is, associative algebras endowed with Rota-Baxter operators of arbitrary weights from an operadic viewpoint. Denote by $\RB$ the operad of Rota-Baxter associative algebras. A homotopy cooperad is explicitly constructed, which can be seen as the Koszul dual of $\RB$ as it is proven that the cobar construction of this homotopy cooperad is exactly the minimal model of $\RB$. This enables us to give the notion of homotopy Rota-Baxter associative algebras. The deformation complex of a Rota-Baxter associative algebra and the underlying $L_\infty$-algebra structure over it are exhibited as well., Comment: A completely new version of arXiv:2108.06744. Title changed. Seleta Math. to appear

We study a question which can be roughly stated as follows: Given a (unital or nonunital) algebra $A$ together with a Gr\"obner-Shirshov basis $G$, consider the free operated algebra $B$ over $A$, such that the operator satisfies some polynomial identities $\Phi$ which are Gr\"obner-Shirshov in the sense of Guo et al., when doesthe union $\Phi\cup G$ will be an operated Gr\"obner-Shirshov basis for $B$? We answer this question in the affirmative under a mild condition in our previous work with Wang. When this condition is satisfied, $\Phi\cup G$ is an operated Gr\"obner-Shirshov basis for $ B$ and as a consequence, we also get a linear basis of $B$. However, the condition could not be applied directly to differential type algebras introduced by Guo, Sit and Zhang, including usual differential algebras. This paper solves completely this problem for differential type algebras.Some new monomial orders are introduced which, together with some known ones, permit the application of the previous result to most of differential type algebras, thus providing new operated GS bases and linear bases for these differential type algebras.Versions are presented both for unital and nonunital algebras. However, a class of examples are also presented, for which the natural expectation in the question is wrong and these examples are dealt with by direct inspection., Comment: 27 pages, comments are welcome! arXiv admin note: text overlap with arXiv:1601.04254 by other authors

This paper studies formal deformations and homotopy theory of Rota-Baxter algebras of any weight. We define an $L_\infty$-algebra, which controls simultaneous deformations of associative products and Rota-Baxter operators. As a consequence, we develop a cohomology theory of Rota-Baxter algebras of any weight and justify it by interpreting lower degree cohomology groups as formal deformations and abelian extensions. The notion of homotopy Rota-Baxter algebras is introduced and it is shown that the operad governing homotopy Rota-Baxter algebras is a minimal model of the operad of Rota-Baxter algebras.

Continuing a work of Ph.~Monnier, we determine the Gerstenhaber algebra structure over the Poisson cohomology groups for a large class of Poisson structures with isolated singularities over the plane. It reveals that there exists a GAGA type phenomenon. We give an explicit description via generators and relations for the case of simple singularities.

This paper investigates algebraic objects equipped with an operator, such as operated monoids, operated algebras etc. Various free object functors in these operated contexts are explicitly constructed. For operated algebras whose operator satisfies a set $\Phi$ of relations (usually called operated polynomial identities (aka. OPIs)), Guo defined free objects, called free $\Phi$-algebras, via universal algebra. Free $\Phi$-algebras over algebras are studied in details. A mild sufficient condition is found such that $\Phi$ together with a Gr\"obner-Shirshov basis of an algebra $A$ form a Gr\"obner-Shirshov basis of the free $\Phi$-algebra over algebra $A$ in the sense of Guo et al.. Ample examples for which this condition holds are provided, such as all Rota-Baxter type OPIs, a class of differential type OPIs, averaging OPIs and Reynolds OPI., Comment: Slightly revised version of the published paper in Journal of Algebra

Various neural-based methods have been proposed so far for joint mention detection and coreference resolution. However, existing works on coreference resolution are mainly dependent on filtered mention representation, while other spans are largely neglected. In this paper, we aim at increasing the utilization rate of data and investigating whether those eliminated spans are totally useless, or to what extent they can improve the performance of coreference resolution. To achieve this, we propose a mention representation refining strategy where spans highly related to mentions are well leveraged using a pointer network for representation enhancing. Notably, we utilize an additional loss term in this work to encourage the diversity between entity clusters. Experimental results on the document-level CoNLL-2012 Shared Task English dataset show that eliminated spans are indeed much effective and our approach can achieve competitive results when compared with previous state-of-the-art in coreference resolution., Comment: Accepted by NLPCC 2021