Search

In this paper, we describe the process that we used to create a new corpus of children’s emotional speech. We used a Wizard of Oz (WoZ) setting to induce different emotional reactions in children during speech-based interactions with two robots. We recorded the speech spoken in Mexican Spanish by 174 children (both sexes) between 6 and 11 years of age. The recordings were manually segmented and transcribed. The segments were then labeled with two types of emotional-related paralinguistic information: emotion and attitude. The corpus contained 2093 min of audio recordings (34.88 h) divided into 19,793 speech segments. The Interactive Emotional Children’s Speech Corpus (IESC-Child) can be a valuable resource for researchers studying affective reactions in speech communication during child-computer interactions in Spanish and for creating models to recognize acoustic paralinguistic information. IESC-Child is available to the research community upon request.

Depression is a severe mental health problem. Due to its relevance, the development of computational tools for its detection has attracted increasing attention in recent years. In this context, several research works have addressed the problem using word-based approaches (e.g., a bag of words). This type of representation has shown to be useful, indicating that words act as linguistic markers of depression. However, we believe that in addition to words, their contexts contain implicitly valuable information that could be inferred and exploited to enhance the detection of signs of depression. Specifically, we explore the use of user’s characteristics and the expressed sentiments in the messages as context insights. The main idea is that the words’ discriminative value depends on the characteristics of the person who is writing and on the polarity of the messages where they occur. Hence, this paper introduces a new approach based on specializing the framework of classification to profiles of users (e.g., males or women) and considering the sentiments expressed in the messages through a new text representation that captures their polarity (e.g., positive or negative). The proposed approach was evaluated on benchmark datasets from social media; the results achieved are encouraging, since they outperform those of state-of-the-art corresponding to computationally more expensive methods.

The increasing propagation of abusive language in social media is a major concern for supplier companies and governments because of its negative social impact. A large number of methods have been developed for its automatic identification, ranging from dictionary-based methods to sophisticated deep learning approaches. A common problem in all these methods is to distinguish the offensive use of swear words from their everyday and humorous usage. To tackle this particular issue we propose an attention-based neural network architecture that captures the word n-grams importance according to their context. The obtained results in four standard collections from Twitter and Facebook are encouraging, they outperform the \(F_1\) scores from state-of-the-art methods and allow identifying a set of inherently offensive swear words, and others in which its interpretation depends on its context.

E-communication represents a major threat to users who are exposed to a number of risks and potential attacks. Detecting these risks with as much anticipation as possible is crucial for prevention. However, much research so far has focused on forensic tools that can be applied only when an attack has been performed. This paper proposes a novel and effective methodology for the early detection of threats in written social media. The goal is to recognize a potential attack before it is consummated, and using a minimum amount of information. The proposed approach considers the use of profile-based representations (PBRs) for this goal. PBRs have multiple benefits, including non-sparsity, low dimensionality, and a proved discriminative power. Moreover, representations for partial documents can be derived naturally with PBRs, which makes them suitable for the addressed problem. Results include empirical evidence on the usefulness of PBRs in the early recognition setting for two tasks in which anticipation is critical: sexual predator detection and aggressive text identification. These results reveal, on the one hand, that PBRs achieve state of the art performance when using full-length documents (i.e., the classical task), and, on the other hand, that the proposed methodology outperforms previous work on early recognition of sexual predators by a considerable margin, while obtaining state of the art performance in aggressive text identification. To the best of our knowledge, these are the best results reported on early recognition for the approached problems. We foresee this work will pave the way for the development of novel methodologies for the problem and will motivate further research from the intelligent systems and text mining communities.

The concept of polarity is pervasive in natural language. It relates syntax, semantics and pragmatics narrowly (Giannakidou, in: Maienborn, von Heusinger, Portner (eds.), Semantics: an international handbook of natural language meaning, De Gruyter Mouton, Berlin, 2011; Israel in The grammar of polarity: pragmatics, sensitivity, and the logic of scales, Cambridge studies in linguistics, Cambridge University Press, Cambridge, 2014), it refers to items of many syntactic categories such as nouns, verbs and adverbs. Neutral polarity items appear in affirmative and negative sentences, negative polarity items cannot appear in affirmative sentences, and positive polarity items cannot appear in negative sentences. A way of reasoning in Natural Language is through Natural Logic (van Benthem in Essays in logical semantics, vol. 29 of Studies in linguistics and philosophy, Reidel, Dordrecht, 1986; Language in action: categories, lambdas, and dynamic logic, vol. 130 of Studies in logic, Elsevier, Amsterdam, 1991). This logic is based on the concept of polarity in order to make the meaning of a sentence weaker o stronger without changing its truth value. There exist many proposals to compute polarity in the Natural Logic context, the most widely known are the ones by: van Benthem (1986, 1991), Sanchez-Valencia (Studies on natural logic and categorial grammar, Ph.D. thesis, Universiteit van Amsterdam, 1991), Dowty (Proceedings of the 4th conference on semantics and theoretical linguistics, Cornel University, CLC Publications, Rochester, 1994), and van Eijck (in: ten Cate, Zeevat (eds.), 6th international Tbilisi symposium on logic, language, and computation, Batumi, Georgia, Springer, 2007). If Natural Logic is going to be used, as an inferential mechanism between text fragments, in Natural Language Processing applications such as text summarization, question answering, and information extraction, it is a priority to know what the existing relationship among the aforementioned algorithms is; for example, to implement the most general. We show in this paper the equivalence among the analyzed algorithms, filling a gap in Natural Logic research, particularly in computing polarity, and the soundness of their algorithms.

[EN] Several methods have been proposed for determining plagiarism between pairs of sentences, passages or even full documents. However, the majority of these methods fail to reliably detect paraphrase plagiarism due to the high complexity of the task, even for human beings. Paraphrase plagiarism identi cation consists in automatically recognizing document fragments that contain re-used text, which is intentionally hidden by means of some rewording practices such as semantic equivalences, discursive changes, and morphological or lexical substitutions. Our main hypothesis establishes that the original author's writing style ngerprint prevails in the plagiarized text even when paraphrases occur. Thus, in this paper we propose a novel text representation scheme that gathers both content and style characteristics of texts, represented by means of character-level features. As an additional contribution, we describe the methodology followed for the construction of an appropriate corpus for the task of paraphrase plagiarism identi cation, which represents a new valuable resource to the NLP community for future research work in this field., This work is the result of the collaboration in the framework of the CONACYT Thematic Networks program (RedTTL Language Technologies Network) and the WIQ-EI IRSES project (Grant No. 269180) within the FP7 Marie Curie action. The first author was supported by CONACYT (Scholarship 258345/224483). The second, third, and sixth authors were partially supported by CONACyT (Project Grants 258588 and 2410). The work of the fourth author was partially supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the Grant ALMAMATER (PrometeoII/2014/030).

Deception (the action of deliberately cause someone to believe something that is not true) can have many different repercussions in daily life. However, deception detection is an inherently complex task for humans. Due to this, not only there is uncertainty on which features should be used as cues for automatic deception detection, but labeled data is scarce. In this paper, we explore typical features that can be extracted from videos for affective computing and study their performance for deception detection in videos. Additionally, we perform a study of different multimodal fusion methods meant to improve the results obtained by using the different sets of extracted features separately, including a novel set of methods based on boosting. For this study, high level features are extracted with open automatic tools for the visual, acoustical and textual modalities, respectively. Experiments are conducted using a real-life court trial dataset for deception detection, as well as a novel Mexican deception detection dataset using Spanish as the spoken language.

Depression is a mental disorder with strong social and economic implications. Due to its relevance, recently several researches have explored the analysis of social media content to identify and track depressed users. Most approaches follow a supervised learning strategy supported on the availability of labeled training data. Unfortunately, acquiring such data is very complex and costly. To handle this problem, in this paper we propose a crosslingual approach based on the idea that data already labeled in a specific language can be leveraged to classify depression in other languages. The proposed method is based on a word-level alignment process. Particularly, we propose two representations for the alignment; one of them takes advantage of the psycholinguistic resource LIWC and the other uses bilingual word embeddings. For evaluating the proposed approach, we faced the detection of depression by employing English and Spanish tweets as the source and target data respectively. The results outperformed solutions based on automatic translation of texts, confirming the usefulness of the proposed approach.

Deception detection -identifying when someone is trying to cause someone else to believe something that is not true- is a hard task for humans. The task is even harder for automatic approaches, that must deal with additional problems like the lack of enough labeled data. In this context, transfer learning in the form of cross-domain classification is a task that aims to leverage labeled data from certain domains for which labeled data is available to others for which data is scarce. This paper presents a study on the suitability of linguistic features for cross-domain deception detection on multimodal data. Specifically, we aim to learn models for deception detection across different domains of written texts (one modality) and apply the new knowledge to unrelated topics transcribed from spoken statements (another modality). Experimental results reveal that by using LIWC and POS n-grams we reach a in-modality accuracy of 69.42%, as well as an AUC ROC of 0.7153. When doing transfer learning, we achieve an accuracy of 63.64% and get an AUC ROC of 0.6351.

Recognizing Textual Entailment (RTE) is a Natural Language Processing task. It is very important in tasks as Semantic Search and Text Summarization. There are many approaches to RTE, for example, methods based on machine learning, linear programming, probabilistic calculus, optimization, and logic. Unfortunately, no one of them can explain why the entailment is carried on. We can make reasonings, with Natural Logic, from the syntactic part of a natural language expression, and very little semantic information. This paper presents an Automatic Theorem Prover for Natural Logic that allows to know precisely the relationships needed in order to reach the entailment in a class of natural language expressions.

[EN] Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the relatedness of two given texts: a semantically-informed similarity measure and a semantically-informed edit distance. Both measures are able to extract semantic information from either an external resource or a distributed representation of words, resulting in informative features for training a supervised classifier for detecting paraphrase plagiarism. Obtained results indicate that the proposed metrics are consistently good in detecting different types of paraphrase plagiarism. In addition, results are very competitive against state-of-the art methods having the advantage of representing a much more simple but equally effective solution., This work was partially supported by CONACYT under scholarship 401887, project grants 257383, 258588 and 2016-01-2410 and under the Thematic Networks program (Language Technologies Thematic Network project 281795). The work of the fourth author was partially supported by the SomEMBED TIN2015-71147-C2-1-P MINECO research project and by the Generalitat Valenciana under the grant ALMAMATER (Prometeo II/2014/030).

There is a considerable number of people with some disability they may go from partial limb disability to total incapacity. For these people, technology is an opportunity to bring them back some capabilities. In this work, we present a framework where we envisage a system that can be used by a disabled person who can not move but still possesses eye movements. Therefore, by using electroencephalographic (EEG) signals, we recognize and classify eye movements, which are then translated to control commands. Based on the latter, we developed an application to illustrate how such commands could be used to control a drone that could be used to deliver messages or carry out any other activity that involves the drone having to fly from a start point to a final destination. The results obtained in this study indicate that ocular movements are recognized with an accuracy of 86%, which suggests the feasibility of our approach.

The Author Profiling (AP) task aims to reveal as much as possible information from a given author's document (e.g., age, gender, etc.). AP is crucial for several applications, ranging from customized advertising to computer forensics, psychology, and entertainment. Nonetheless, the AP task is far from being solved, particularly in social media domains, where the nature of documents hinder the applicability of state-of-the-art text mining tools (e.g., because of spelling-grammar errors, huge vocabularies, and the presence of many out-of-vocabulary terms). Currently, most of the work in AP for social media has been devoted to the development of descriptive features, which are used under standard representations, such as the Bag-of-Words (BoW). Nevertheless, BoW-like representations have some well known shortcomings, namely: (i) the sparsity and high dimensionality of the representation, and (ii) the failure to capture relationships, other than mere occurrence, among terms. This paper focuses on the study of alternative document representations that can deal with such issues. We propose a representation for documents that capture discriminative and subprofile-specific information of terms. Under the proposed representation, terms are represented in a vector space that captures discriminative information. Then, term representations are aggregated to represent the content of a document. In this manner, documents are represented in a low-dimensional (and discriminative) space which is non-sparse. We evaluate the effectiveness of the proposed representation on several corpora from the social media domain. The proposed representation is compared to the standard BoW representation and a wide variety of state-of-the-art AP approaches. Experimental results reveal that the proposed representation outperforms most of the reference methodologies. Furthermore, we show that the proposed representation is in agreement with previous studies on handcrafted attributes for AP.

An important task in plagiarism detection is determining and measuring similar text portions between a given pair of documents. One of the main difficulties of this task resides on the fact that reused text is commonly modified with the aim of covering or camouflaging the plagiarism. Another difficulty is that not all similar text fragments are examples of plagiarism, since thematic coincidences also tend to produce portions of similar text. In order to tackle these problems, we propose a novel method for detecting likely portions of reused text. This method is able to detect common actions performed by plagiarists such as word deletion, insertion and transposition, allowing to obtain plausible portions of reused text. We also propose representing the identified reused text by means of a set of features that denote its degree of plagiarism, relevance and fragmentation. This new representation aims to facilitate the recognition of plagiarism by considering diverse characteristics of the reused text during the classification phase. Experimental results employing a supervised classification strategy showed that the proposed method is able to outperform traditionally used approaches. 2012 Elsevier Ltd. All rights reserved., This work was done under partial support of CONACyT project Grants: 134186, and Scholarships: 258345/224483. This work is the result of the collaboration in the framework of the WIQEI IRSES project (Grant No. 269180) within the FP 7 Marie Curie. The work of the last author was in the framework of the VLC/CAMPUS Microcluster on Multimodal Interaction in Intelligent Systems.

The vast amount of electronic documents available on the Internet demands for automatic tools that help people finding, organizing and easily accessing to all this information. Although current text classification methods have alleviated some of the above problems, such strategies depend on having a large and reliable set of labeled data. In order to overcome such limitation, this work proposes an alternative approach for semi-supervised text classification, which is based on a new strategy for diminishing the sensitivity to the noise contained on labeled data by means of automatic text summarization. Experimental results showed that our proposed approach outperforms traditional semi-supervised text classification techniques; additionally, our results also indicate that our approach is suitable for learning from only one labeled example per category.

During the last decades the Web has become the greatest repository of digital information. In order to organize all this information, several text categorization methods have been developed, achieving accurate results in most cases and in very different domains. Due to the recent usage of Internet as communication media, short texts such as news, tweets, blogs, and product reviews are more common every day. In this context, there are two main challenges; on the one hand, the length of these documents is short, and therefore, the word frequencies are not informative enough, making text categorization even more difficult than usual. On the other hand, topics are changing constantly at a fast rate, causing the lack of adequate amounts of training data. In order to deal with these two problems we consider a text classification method that is supported on the idea that similar documents may belong to the same category. Mainly, we propose a neighborhood consensus classification method that classifies documents by considering their own information as well as information about the category assigned to other similar documents from the same target collection. In particular, the short texts we used in our evaluation are news titles with an average of 8 words. Experimental results are encouraging; they indicate that leveraging information from similar documents helped to improve classification accuracy and that the proposed method is especially useful when labeled training resources are limited.

In this paper we report the results obtained from experiments with a database of emotional speech in English in order to find the most important acoustic features to estimate Emotion Primitives which determine the emotional content on speech. We are interested in exploiting the potential benefits of continuous emotion models, so in this paper we demonstrate the feasibility of applying this approach to annotation of emotional speech and we explore ways to take advantage of this kind of annotation to improve the automatic classification of basic emotions.

Most current methods for automatic text categorization are based on supervised learning techniques and, therefore, they face the problem of requiring a great number of training instances to construct an accurate classifier. In order to tackle this problem, this paper proposes a new semi-supervised method for text categorization, which considers the automatic extraction of unlabeled examples from the Web and the application of an enriched self-training approach for the construction of the classifier. This method, even though language independent, is more pertinent for scenarios where large sets of labeled resources do not exist. That, for instance, could be the case of several application domains in different non-English languages such as Spanish. The experimental evaluation of the method was carried out in three different tasks and in two different languages. The achieved results demonstrate the applicability and usefulness of the proposed method.

Depression is a disease that affects a considerable portion of the world population. Severe cases of depression interfere with the common live of patients, for those patients a strict monitoring is necessary in order to control the progress of the disease and to prevent undesired side effects. A way to keep track of patients with depression is by means of online monitoring via human-computer-interaction. The AVEC'14 challenge aims at developing technology towards the online monitoring of depression patients. This paper describes an approach to depression recognition from audiovisual information in the context of the AVEC'14 challenge. The proposed method relies on an effective voice segmentation procedure, followed by segment-level feature extraction and aggregation. Finally, a meta-model is trained to fuse mono-modal information. The main novel features of our proposal are that (1) we use affective dimensions for building depression recognition models; (2) we extract visual information from voice and silence segments separately; (3) we consolidate features and use a meta-model for fusion. The proposed methodology is evaluated, experimental results reveal the method is competitive.

Sequential Pattern Mining is a widely addressed problem in data mining, with applications such as analyzing Web usage, examining purchase behavior, and text mining, among others. Nevertheless, with the dramatic increase in data volume, the current approaches prove inefficient when dealing with large input datasets, a large number of different symbols and low minimum supports. In this paper, we propose a new sequential pattern mining algorithm, which follows a pattern-growth scheme to discover sequential patterns. Unlike most pattern growth algorithms, our approach does not build a data structure to represent the input dataset, but instead accesses the required sequences through pseudo-projection databases, achieving better runtime and reducing memory requirements. Our algorithm traverses the search space in a depth-first fashion and only preserves in memory a pattern node linkage and the pseudo-projections required for the branch being explored at the time. Experimental results show that our new approach, the Node Linkage Depth-First Traversal algorithm (NLDFT), has better performance and scalability in comparison with state of the art algorithms.

This paper proposes a novel representation for Authorship Attribution (AA), based on Concise Semantic Analysis (CSA), which has been successfully used in Text Categorization (TC). Our approach for AA, called Document Author Representation (DAR), builds document vectors in a space of authors, calculating the relationship between textual features and authors. In order to evaluate our approach, we compare the proposed representation with conventional approaches and previous works using the c50 corpus. We found that DAR can be very useful in AA tasks, because it provides good performance on imbalanced data, getting comparable or better accuracy results.

Emotions are complex human phenomena. Numberless researchers have attempted a variety of approaches to model these phenomena and to find the optimal set of emotion descriptors. In this paper, we search for the most appropriate acoustic features to estimate the emotional content in speech based on a continuous multi-dimensional model of emotions. We analyze a set of 6,920 features using the feature selection method known as Linear Forward Selection. We studied the importance of the features dividing them into groups and working with two databases, one in English and one in German to analyze the multi-lingual importance of features and to know if these features are important regardless of the language.

The traditional approach for spoken document retrieval (SDR) uses an automatic speech recognizer (ASR) in combination with a word-based information retrieval method. This approach has only showed limited accuracy, partially because ASR systems tend to produce transcriptions of spontaneous speech with significant word error rate. In order to overcome such limitation we propose a method which uses word and phonetic-code representations in collaboration. The idea of this combination is to reduce the impact of transcription errors in the processing of some (presumably complex) queries by representing words with similar pronunciations through the same phonetic code. Experimental results on the CLEF-CLSR-2007 corpus are encouraging; the proposed hybrid method improved the mean average precision and the number of retrieved relevant documents from the traditional word-based approach by 3% and 7% respectively.

The acquisition of naturalistic speech data and the richness of its annotation are very important to face the challenges of automatic emotion recognition from speech. This paper describes the creation of a database of emotional speech in the Spanish spoken in Mexico. It was recorded from children between 7 and 13 years old while playing a sorting card game with an adult examiner. The game is based on a neuropsychological test, modified to encourage dialogue and induce emotions in the player. The audio was segmented at speaker turn level and annotated with six emotional categories and three continuous emotion primitives by 11 human evaluators. Inter-evaluator agreement is presented for categorical and continuous annotation. Initial classification and regression experiments were performed using a set of 6,552 acoustic features.

Reinforcement Learning is commonly used for learning tasks in robotics, however, traditional algorithms can take very long training times. Reward shaping has been recently used to provide domain knowledge with extra rewards to converge faster. The reward shaping functions are normally defined in advance by the user and are static. This paper introduces a dynamic reward shaping approach, in which these extra rewards are not consistently given, can vary with time and may sometimes be contrary to what is needed for achieving a goal. In the experiments, a user provides verbal feedback while a robot is performing a task which is translated into additional rewards. It is shown that we can still guarantee convergence as long as most of the shaping rewards given per state are consistent with the goals and that even with fairly noisy interaction the system can still produce faster convergence times than traditional reinforcement learning techniques.

Crosslingual text classification consists of exploiting labeled documents in a source language to classify documents in a different target language. In addition to the evident translation problem, this task also faces some difficulties caused by the cultural discrepancies manifested in both languages by means of different topic distributions. Such discrepancies make the classifier unreliable for the categorization task. In order to tackle this problem we propose to improve the classification performance by using information embedded in the own target dataset. The central idea of the proposed approach is that similar documents must belong to the same category. Therefore, it classifies the documents by considering not only their own content but also information about the assigned category to other similar documents from the same target dataset. Experimental results using three different languages evidence the appropriateness of the proposed approach.

Current text classification methods are mostly based on a supervised approach, which require a large number of examples to build models accurate. Unfortunately, in several tasks training sets are extremely small and their generation is very expensive. In order to tackle this problem in this paper we propose a new text classification method that takes advantage of the information embedded in the own test set. This method is supported on the idea that similar documents must belong to the same category. Particularly, it classifies the documents by considering not only their own content but also information about the assigned category to other similar documents from the same test set. Experimental results in four data sets of different sizes are encouraging. They indicate that the proposed method is appropriate to be used with small training sets, where it could significantly outperform the results from traditional approaches such as Naive Bayes and Support Vector Machines.

Most common feature selection techniques for document categorization are supervised and require lots of training data in order to accurately capture the descriptive and discriminative information from the defined categories. Considering that training sets are extremely small in many classification tasks, in this paper we explore the use of unsupervised extractive summarization as a feature selection technique for document categorization. Our experiments using training sets of different sizes indicate that text summarization is a competitive approach for feature selection, and show its appropriateness for situations having small training sets, where it could clearly outperform the traditional information gain technique.

Geographic Information Retrieval (GIR) is a specialized Information Retrieval (IR) branch that deals with information related to geographical locations. Traditional IR engines are perfectly able to retrieve the majority of the relevant documents for most geographical queries, but they have severe difficulties generating a pertinent ranking of the retrieved results, which leads to poor performance. A key reason for this ranking problem has been a lack of information. Therefore, previous GIR research has tried to fill this gap using robust geographical resources (i.e. a geographical ontology), while other research with the same aim has used relevant feedback techniques instead. This paper explores the use of Bag of Concepts (BoC; a representation where documents are considered as the union of the meanings of its terms) and Holographic Reduced Representation (HRR; a novel representation for textual structure) as re-ranking mechanisms for GIR. Our results reveal an improvement in mean average precision (MAP) when compared to the traditional vector space model, even if Pseudo Relevance Feedback is employed.

The full deployment of service robots in daily activities will require the robot to adapt to the needs of non-expert users, particularly, to learn how to perform new tasks from "natural" interactions. Reinforcement learning has been widely used in robotics, however, traditional algorithms require long training times, and may have problems with continuous spaces. Programming by demonstration has been used to instruct a robot, but is limited by the quality of the trace provided by the user. In this paper, we introduce a novel approach that can handle continuous spaces, can produce continuous actions and incorporates the user's intervention to quickly learn optimal policies of tasks defined by the user. It is shown how the continuous actions produce smooth trajectories and how the user's intervention allows the robot to learn significantly faster optimal policies. The proposed approach is tested in a simulated robot with very promising results.

Multi-document summarization systems must be able to draw the "best" information from a set of documents.In this paper we propose a novel extractive approach for multidocument summarization based on the detection of locally relevant sentences. Our main hypothesis is that by extracting relevant sentences from each document within a collection, instead of considering all documents at once, the final multi-document summary will be of higher quality. Performed experiments showed that the proposed method is able to outperform conventional baselines as well as traditional approaches by constructing summaries of high quality according to the ROUGE evaluation metrics.

As any other classification task, Word Sense Disambiguation requires a large number of training examples. These examples, which are easily obtained for most of the tasks, are particularly difficult to obtain for this case. Based on this fact, in this paper we investigate the possibility of using a Web-based approach for determining the correct sense of an ambiguous word based only in its surrounding context. In particular, we propose a semi-supervised method that is specially suited to work with just a few training examples. The method considers the automatic extraction of unlabeled examples from the Web and their iterative integration into the training data set. The experimental results, obtained over a subset of ten nouns from the SemEval lexical sample task, are encouraging. They showed that it is possible to improve the baseline accuracy of classifiers such as Naive Bayes and SVM using some unlabeled examples extracted from the Web.

This paper describes the results of the INAOE's answer va-lidation system evaluated at the Spanish track of the AVE 2007. The system is based on a supervised learning approach that considers two kinds of attributes. On the one hand, some attributes indicating the textual entailment between the given support text and the hypothesis constructed from the question and answer. On the other hand, some new features denoting certain answer restrictions as imposed by the question's type and format. The evaluation results were encouraging; they reached a F-measure of 53% (the best performance in the Spanish track), and outperformed the standard baseline by 15 percentage points.

Automatic call routing is one of the most important issues in the call center domain. It can be modeled ---once performed the speech recognition of utterances--- as a text classification task. Nevertheless, in this case, texts are extremely small (just a few words) and there are a great number of narrow call-type classes. In this paper, we propose a text classification method specially suited to work on this scenario. This method considers a new weighting scheme of terms and uses a multiple stage classification approach with the aim of balance the rate of rejected calls (directed to a human operator) and the classification accuracy. The proposed method was evaluated on a Spanish corpus consisting of 24,638 call utterances achieving outstanding results: 95.5% of classification accuracy with a rejection rate of just 8.2%.

Current storage and processing facilities have caused the emergence of many multimedia repositories and, consequently, they have also triggered the necessity of new approaches for information retrieval. In particular, spoken document retrieval is a very complex task since existing speech recognition systems tend to generate several transcription errors (such as word substitutions, insertions and deletions). In order to deal with these errors, this paper proposes an enriched document representation based on a phonetic codification of the automatic transcriptions. This representation aims to reduce the impact of the transcription errors by representing words with similar pronunciations through the same phonetic code. Experimental results on the CL-SR corpus from the CLEF 2007 (which includes 33 test topics and 8,104 English interviews) are encouraging; our method achieved a mean average precision of 0.0795, outperforming all except one of the evaluated systems at this forum.

As any other text categorization task, authorship attribution requires a large number of training examples. These examples, which are easily obtained for most of the tasks, are particularly difficult to obtain for this case. Based on this fact, in this paper we investigate the possibility of using Web-based text mining methods for the identification of the author of a given poem. In particular, we propose a semi-supervised method that is specially suited to work with justfew training examples in order to tackle the problem of the lack of data with the same writing style. The method considers the automatic extraction of the unlabeled examples from the Web and its iterative integration into the training data set. To the knowledge of the authors, a semi-supervised method which makes use of the Web as support lexical resource has not been previously employed in this task. The results obtained on poem categorization show that this method may improve the classification accuracy and it is appropriate to handle the attribution of short documents.

A problem of supervised approaches for text classification is that they commonly require high-quality training data to construct an accurate classifier. Unfortunately, in many real-world applications the training sets are extremely small and present imbalanced class distributions. In order to confront these problems, this paper proposes a novel approach for text classification that combines under-sampling with a semi-supervised learning method. In particular, the proposed semi-supervised method is specially suited to work with very few training examples and considers the automatic extraction of untagged data from the Web. Experimental results on a subset of Reuters-21578 text collection indicate that the proposed approach can be a practical solution for dealing with the class-imbalance problem, since it allows achieving very good results using very small training sets.

This paper describes a method for extracting hyponyms from free text. In particular it explores two main matters. On the one hand, the possibility of reaching favorable results using only lexical extraction patterns. On the other hand, the usefulness of measuring the instance's confidences based on the pattern's confidences, and vice versa. Experimental results are encouraging because they show that the proposed method can be a practical high-precision approach for extracting hyponyms for a given set of concepts.

One major problem in multilingual Question Answering (QA) is the combination of answers obtained from different languages into one single ranked list. This paper proposes a new method for tackling this problem. This method is founded on a graph-based ranking approach inspired in the popular Google's PageRank algorithm. Experimental results demonstrate that the proposed method outperforms other current techniques for answer fusion, and also evidence the advantages of multilingual QA over the traditional monolingual approach.

This paper describes a QA system centered in a full data-driven architecture. It applies machine learning and text mining techniques to identify the most probable answers to factoid and definition questions respectively. Its major quality is that it mainly relies on the use of lexical information and avoids applying any complex language processing resources such as named entity classifiers, parsers and ontologies. Experimental results on the Spanish Question Answering task at CLEF 2006 show that the proposed architecture can be a practical solution for monolingual question answering by reaching a precision as high as 51%.

This work is a revised version of the paper “INAOE-UPV Joint Participation at CLEF 2005: Experiments in Monolingual Question Answering”, previously published in the CLEF 2005 working notes (www.clef-campaign.org/2005/working_notes/). This paper describes a full data-driven system for question answering. The system uses pattern matching and statistical techniques to identify the relevant passages as well as the candidate answers for factoid and definition questions. Since it does not consider any sophisticated linguistic analysis of questions and answers, it can be applied to different languages without requiring major adaptation changes. Experimental results on Spanish, Italian and French demonstrate that the proposed approach can be a convenient strategy for monolingual and multilingual question answering. CONACYT (Project Grant 43990); R2D2 (CICYTTIC2003-07158-C04-03); ICT EU-India (ALA/95/23/2003/077-054)

Traditional approaches for extractive summarization score/classify sentences based on features such as position in the text, word frequency and cue phrases These features tend to produce satisfactory summaries, but have the inconvenience of being domain dependent In this paper, we propose to tackle this problem representing the sentences by word sequences (n-grams), a widely used representation in text categorization The experiments demonstrated that this simple representation not only diminishes the domain and language dependency but also enhances the summarization performance.

Authorship attribution is the task of identifying the author of a given text. The main concern of this task is to define an appropriate characterization of documents that captures the writing style of authors. This paper proposes a new method for authorship attribution supported on the idea that a proper identification of authors must consider both stylistic and topic features of texts. This method characterizes documents by a set of word sequences that combine functional and content words. The experimental results on poem classification demonstrated that this method outperforms most current state-of-the-art approaches, and that it is appropriate to handle the attribution of short documents.

This paper describes the prototype developed in the Language Technologies Laboratory at INAOE for the Spanish monolingual QA evaluation task at CLEF 2005. The proposed approach copes with the QA task according to the type of question to solve (factoid or definition). In order to identify possible answers to factoid questions, the system applies a methodology centered in the use of lexical features. On the other hand, the system is supported by a pattern recognition method in order to identify answers to definition questions. The paper shows the methods applied at different stages of the system, with special emphasis on those used for answering factoid questions. Then the results achieved with this approach are discussed.

This paper describes a method for definition question answering based on the use of surface text patterns. The method is specially suited to answer questions about person’s positions and acronym’s descriptions. It considers two main steps. First, it applies a sequence-mining algorithm to discover a set of definition-related text patterns from the Web. Then, using these patterns, it extracts a collection of concept-description pairs from a target document database, and applies the sequence-mining algorithm to determine the most adequate answer to a given question. Experimental results on the Spanish CLEF 2005 data set indicate that this method can be a practical solution for answering this kind of definition questions, reaching a precision as high as 84%.

This paper presents a method for cross-language question answering. The method combines multiple query translations in order to improve the answering precision. The combination of translations is based on their pertinence to the target document collection rather than on their grammatical correctness. The pertinence is measured by the translation perplexity with respect to the collection language model. Experimental evaluation on question answering demonstrates that the proposed approach outperforms the results obtained by the best translation machine.

Spoken language identification consists in recognizing a language based on a sample of speech from an unknown speaker. The traditional approach for this task mainly considers the phonothactic information of languages. However, for marginalized languages –languages with few speakers or oral languages without a fixed writing standard–, this information is practically not at hand and consequently the usual approach is not applicable. In this paper, we present a method that only considers the acoustic features of the speech signal and does not use any kind of linguistic information. The experimental results on a pairwise discrimination task among nine languages demonstrated that our proposal is comparable to other similar methods. Nevertheless, its great advantage is the straightforward characterization of the acoustic signal.

Passage Retrieval (PR) is typically used as the first step in current Question Answering (QA) systems. Most methods are based on the vector space model allowing the finding of relevant passages for general user needs, but failing on selecting pertinent passages for specific user questions. This paper describes a simple PR method specially suited for the QA task. This method considers the structure of the question, favoring the passages that contain the longer n-gram structures from the question. Experimental results of this method on Spanish, French and Italian show that this approach can be useful for multilingual question answering systems.

The problem of the resolution of the lexical ambiguity seems to be stuck because of the knowledge acquisition bottleneck. Therefore, it is worthwhile to investigate the possibility of using the Web as a lexical resource. This paper explores two attempts of using Web counts collected through a search engine. The first approach calculates the hits of each possible synonym of the noun to disambiguate together with the nouns of the context. In the second approach the disambiguation of a noun uses a modifier adjective as supporting evidence. A better precision than the baseline was obtained using adjective-noun pairs, even if with a low recall. A comprehensive set of weighting formulae for combining Web counts was investigated in order to give a complete picture of what are the various possibilities, and what are the formulae that work best. The comparison across different search engines was also useful: Web counts, and consequently disambiguation results, were almost identical. Moreover, the Web seems to be more effective than the WordNet Domains lexical resource if integrated rather than stand-alone.