Juan-Manuel Torres-Moreno
Also published as: Juan-Manuel Torres, Juan-Manuel Torres Moreno, Juan Manuel Torres Moreno
2026
Nawatl Context-Free Grammars for Natural Language Processing
Juan Jose Guzman Landa | Juan-Manuel Torres-Moreno | Graham Ranger | Miguel Figueroa-Saavedra | Ligia Quintana Torres | Carlos-Emiliano Gonzalez-Gallardo | Luis Gil Moreno Jimenez | Martha Lorena Avendaño Garrido
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Juan Jose Guzman Landa | Juan-Manuel Torres-Moreno | Graham Ranger | Miguel Figueroa-Saavedra | Ligia Quintana Torres | Carlos-Emiliano Gonzalez-Gallardo | Luis Gil Moreno Jimenez | Martha Lorena Avendaño Garrido
Proceedings of the Fifteenth Language Resources and Evaluation Conference
The aim of this article is to introduce Context-Free Grammars (CFG) for the Nawatl language. Nawatl is an Amerindian language of the đ-language type, i.e. a language with few digital resources. For this reason the corpora available for the learning of Large Language Models (LLMs) are virtually non-existent, posing a significant challenge. The goal is to produce a substantial number of syntactically valid artificial Nawatl sentences and thereby to expand the corpora for the purpose of learning embeddings (static models or probably LLMs). For this objective, we introduce two new Nawatl CFGs and use them in generative mode. Thanks to these grammars, it is possible to expand Nawatl corpus significantly and subsequently to use it to learn embeddings (such as FastText) and to evaluate their relevance in semantic similarity tasks. The results show an improvement compared to the results obtained using only the original corpus without artificial expansion, and also demonstrate that economic embeddings often perform better than some LLMs.
Corpora duplication for NLP in low-resource languages: A case study of Nahuatl
Juan Jose Guzman Landa | Juan-Manuel Torres-Moreno | Luis Moreno Jimenez | Elvys Linhares Pontes | Miguel Figueroa-Saavedra | Graham Ranger | Martha Lorena Avendaño Garrido
Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
Juan Jose Guzman Landa | Juan-Manuel Torres-Moreno | Luis Moreno Jimenez | Elvys Linhares Pontes | Miguel Figueroa-Saavedra | Graham Ranger | Martha Lorena Avendaño Garrido
Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
In this paper, we aim to answer the following question: could corpus duplication be useful in Natural Language Processing (NLP) for low-resource languages? In these languages (or pi-languages), corpora available for training Large Language Models are virtually non-existent. Specifically, we study the impact of corpus expansion in Nahuatl, an agglutinative and polysynthetic Amerindian pi-language characterised by extensive dialectal variation. Our goal is to increase the size of Nahuatl corpora, which currently consist of a limited number of tokens, through controlled duplication techniques. Our experimental setup employs incremental duplication alongside appropriate corpus balancing, with the objective of training embeddings optimised for downstream NLP tasks. Consequently, static embeddings were trained and evaluated on a sentence-level semantic similarity task. Our results show a significant improvement in performance when incremental duplication is applied, compared to results obtained without corpus expansion. To our knowledge, this technique has not yet been explored in this field.
2025
Ï-YALLI : un nouveau corpus pour des modĂšles de langue nahuatl / Yankuik nawatlahtolkorpus pampa tlahtolmachiotl
Juan-José Guzmån-Landa | Juan-Manuel Torres-Moreno | Martha Lorena Avendaño Garrido | Miguel Figueroa-Saavedra | Ligia Quintana-Torres | Graham Ranger | Carlos-Emiliano Gonzålez-Gallardo | Elvys Linhares-Pontes | Patricia Velåzquez-Morales | Luis-Gil Moreno-Jiménez
Actes des 32Úme Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux
Juan-José Guzmån-Landa | Juan-Manuel Torres-Moreno | Martha Lorena Avendaño Garrido | Miguel Figueroa-Saavedra | Ligia Quintana-Torres | Graham Ranger | Carlos-Emiliano Gonzålez-Gallardo | Elvys Linhares-Pontes | Patricia Velåzquez-Morales | Luis-Gil Moreno-Jiménez
Actes des 32Úme Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux
Ï-YALLI : a new corpus for Nahuatl Language Models The Nahuatl is a language with few computational resources, despite the fact that it is a living language spoken by around two million people. We built Ï-YALLI, a corpus that enables research and development of dynamic and static Language Models (LM). We measured the perplexity of Ï-YALLI, evaluating state-of-the-art LM performance on a manually annotated semantic similarity corpus relative to annotator agreement. The results show the difficulty of working with this Ï-language, but at the same time open up interesting perspectives for the study of other NLP tasks on Nahuatl.
2021
A Preliminary Study for Literary Rhyme Generation based on Neuronal Representation, Semantics and Shallow Parsing
Luis-Gil Moreno-Jimenez | Juan-Manuel Torres-Moreno | Roseli Wedemann
Proceedings of the 13th Brazilian Symposium in Information and Human Language Technology
Luis-Gil Moreno-Jimenez | Juan-Manuel Torres-Moreno | Roseli Wedemann
Proceedings of the 13th Brazilian Symposium in Information and Human Language Technology
LUC at ComMA-2021 Shared Task: Multilingual Gender Biased and Communal Language Identification without Using Linguistic Features
Rodrigo CuĂ©llar-Hidalgo | Julio de JesĂșs Guerrero-Zambrano | Dominic Forest | Gerardo Reyes-Salgado | Juan-Manuel Torres-Moreno
Proceedings of the 18th International Conference on Natural Language Processing: Shared Task on Multilingual Gender Biased and Communal Language Identification
Rodrigo CuĂ©llar-Hidalgo | Julio de JesĂșs Guerrero-Zambrano | Dominic Forest | Gerardo Reyes-Salgado | Juan-Manuel Torres-Moreno
Proceedings of the 18th International Conference on Natural Language Processing: Shared Task on Multilingual Gender Biased and Communal Language Identification
This work aims to evaluate the ability that both probabilistic and state-of-the-art vector space modeling (VSM) methods provide to well known machine learning algorithms to identify social network documents to be classified as aggressive, gender biased or communally charged. To this end, an exploratory stage was performed first in order to find relevant settings to test, i.e. by using training and development samples, we trained multiple algorithms using multiple vector space modeling and probabilistic methods and discarded the less informative configurations. These systems were submitted to the competition of the ComMA@ICONâ21 Workshop on Multilingual Gender Biased and Communal Language Identification.
2020
Enhancing Job Searches in Mexico City with Language Technologies
Gerardo Sierra MartĂnez | Gemma Bel-Enguix | Helena GĂłmez-Adorno | Juan Manuel Torres Moreno | Tonatiuh HernĂĄndez-GarcĂa | Julio V Guadarrama-Olvera | JesĂșs-GermĂĄn Ortiz-Barajas | Ăngela MarĂa Rojas | Tomas Damerau | Soledad AragĂłn MartĂnez
Proceedings of the 1st Workshop on Language Technologies for Government and Public Administration (LT4Gov)
Gerardo Sierra MartĂnez | Gemma Bel-Enguix | Helena GĂłmez-Adorno | Juan Manuel Torres Moreno | Tonatiuh HernĂĄndez-GarcĂa | Julio V Guadarrama-Olvera | JesĂșs-GermĂĄn Ortiz-Barajas | Ăngela MarĂa Rojas | Tomas Damerau | Soledad AragĂłn MartĂnez
Proceedings of the 1st Workshop on Language Technologies for Government and Public Administration (LT4Gov)
In this paper, we show the enhancing of the Demanded Skills Diagnosis (DiCoDe: DiagnĂłstico de Competencias Demandadas), a system developed by Mexico Cityâs Ministry of Labor and Employment Promotion (STyFE: SecretarĂa de Trabajo y Fomento del Empleo de la Ciudad de MĂ©xico) that seeks to reduce information asymmetries between job seekers and employers. The project uses webscraping techniques to retrieve job vacancies posted on private job portals on a daily basis and with the purpose of informing training and individual case management policies as well as labor market monitoring. For this purpose, a collaboration project between STyFE and the Language Engineering Group (GIL: Grupo de IngenierĂa LingĂŒĂstica) was established in order to enhance DiCoDe by applying NLP models and semantic analysis. By this collaboration, DiCoDeâs job vacancies systemâs macro-structure and its geographic referencing at the city hall (municipality) level were improved. More specifically, dictionaries were created to identify demanded competencies, skills and abilities (CSA) and algorithms were developed for dynamic classifying of vacancies and identifying terms for searches on free text, in order to improve the results and processing time of queries.
2018
Cyberbullying Detection Task: the EBSI-LIA-UNAM System (ELU) at COLINGâ18 TRAC-1
Ignacio Arroyo-FernĂĄndez | Dominic Forest | Juan-Manuel Torres-Moreno | Mauricio Carrasco-Ruiz | Thomas Legeleux | Karen Joannette
Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018)
Ignacio Arroyo-FernĂĄndez | Dominic Forest | Juan-Manuel Torres-Moreno | Mauricio Carrasco-Ruiz | Thomas Legeleux | Karen Joannette
Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018)
The phenomenon of cyberbullying has growing in worrying proportions with the development of social networks. Forums and chat rooms are spaces where serious damage can now be done to others, while the tools for avoiding on-line spills are still limited. This study aims to assess the ability that both classical and state-of-the-art vector space modeling methods provide to well known learning machines to identify aggression levels in social network cyberbullying (i.e. social network posts manually labeled as Overtly Aggressive, Covertly Aggressive and Non-aggressive). To this end, an exploratory stage was performed first in order to find relevant settings to test, i.e. by using training and development samples, we trained multiple learning machines using multiple vector space modeling methods and discarded the less informative configurations. Finally, we selected the two best settings and their voting combination to form three competing systems. These systems were submitted to the competition of the TRACK-1 task of the Workshop on Trolling, Aggression and Cyberbullying. Our voting combination system resulted second place in predicting Aggression levels on a test set of untagged social network posts.
Multi-Sentence Compression with Word Vertex-Labeled Graphs and Integer Linear Programming
Elvys Linhares Pontes | Stéphane Huet | Thiago Gouveia da Silva | Andréa Carneiro Linhares | Juan-Manuel Torres-Moreno
Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)
Elvys Linhares Pontes | Stéphane Huet | Thiago Gouveia da Silva | Andréa Carneiro Linhares | Juan-Manuel Torres-Moreno
Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)
Multi-Sentence Compression (MSC) aims to generate a short sentence with key information from a cluster of closely related sentences. MSC enables summarization and question-answering systems to generate outputs combining fully formed sentences from one or several documents. This paper describes a new Integer Linear Programming method for MSC using a vertex-labeled graph to select different keywords, and novel 3-gram scores to generate more informative sentences while maintaining their grammaticality. Our system is of good quality and outperforms the state-of-the-art for evaluations led on news dataset. We led both automatic and manual evaluations to determine the informativeness and the grammaticality of compressions for each dataset. Additional tests, which take advantage of the fact that the length of compressions can be modulated, still improve ROUGE scores with shorter output sentences.
A New Annotated Portuguese/Spanish Corpus for the Multi-Sentence Compression Task
Elvys Linhares Pontes | Juan-Manuel Torres-Moreno | Stéphane Huet | Andréa Carneiro Linhares
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)
Elvys Linhares Pontes | Juan-Manuel Torres-Moreno | Stéphane Huet | Andréa Carneiro Linhares
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)
DEFT2018 : recherche dâinformation et analyse de sentiments dans des tweets concernant les transports en Ăle de France (DEFT2018 : Information Retrieval and Sentiment Analysis in Tweets about Public Transportation in Ăle de France Region )
Patrick Paroubek | Cyril Grouin | Patrice Bellot | Vincent Claveau | Iris Eshkol-Taravella | Amel Fraisse | Agata Jackiewicz | Jihen Karoui | Laura Monceaux | Juan-Manuel Torres-Moreno
Actes de la Conférence TALN. Volume 2 - Démonstrations, articles des Rencontres Jeunes Chercheurs, ateliers DeFT
Patrick Paroubek | Cyril Grouin | Patrice Bellot | Vincent Claveau | Iris Eshkol-Taravella | Amel Fraisse | Agata Jackiewicz | Jihen Karoui | Laura Monceaux | Juan-Manuel Torres-Moreno
Actes de la Conférence TALN. Volume 2 - Démonstrations, articles des Rencontres Jeunes Chercheurs, ateliers DeFT
Cet article prĂ©sente lâĂ©dition 2018 de la campagne dâĂ©valuation DEFT (DĂ©fi Fouille de Textes). A partir dâun corpus de tweets, quatre tĂąches ont Ă©tĂ© proposĂ©es : identifier les tweets sur la thĂ©matique des transports, puis parmi ces derniers, identifier la polaritĂ© (nĂ©gatif, neutre, positif, mixte), identifier les marqueurs de sentiment et la cible, et enfin, annoter complĂštement chaque tweet en source et cible des sentiments exprimĂ©s. Douze Ă©quipes ont participĂ©, majoritairement sur les deux premiĂšres tĂąches. Sur lâidentification de la thĂ©matique des transports, la micro F-mesure varie de 0,827 Ă 0,908. Sur lâidentification de la polaritĂ© globale, la micro F-mesure varie de 0,381 Ă 0,823.
Predicting the Semantic Textual Similarity with Siamese CNN and LSTM
Elvys Linhares Pontes | Stéphane Huet | Andréa Carneiro Linhares | Juan-Manuel Torres-Moreno
Actes de la Conférence TALN. Volume 1 - Articles longs, articles courts de TALN
Elvys Linhares Pontes | Stéphane Huet | Andréa Carneiro Linhares | Juan-Manuel Torres-Moreno
Actes de la Conférence TALN. Volume 1 - Articles longs, articles courts de TALN
Semantic Textual Similarity (STS) is the basis of many applications in Natural Language Processing (NLP). Our system combines convolution and recurrent neural networks to measure the semantic similarity of sentences. It uses a convolution network to take account of the local context of words and an LSTM to consider the global context of sentences. This combination of networks helps to preserve the relevant information of sentences and improves the calculation of the similarity between sentences. Our model has achieved good results and is competitive with the best state-of-the-art systems.
2014
Classification and Optimization Algorithms: the LIA/ADOC participation at DEFTâ14 (Algorithmes de classification et dâoptimisation : participation du LIA/ADOC Ă DEFTâ14) [in French]
Luis Adriån Cabrera-Diego | Stéphane Huet | Bassam Jabaian | Alejandro Molina | Juan-Manuel Torres-Moreno | Marc El-BÚze | Barthélémy Durette
TALN-RECITAL 2014 Workshop DEFT 2014 : DĂfi Fouille de Textes (DEFT 2014 Workshop: Text Mining Challenge)
Luis Adriån Cabrera-Diego | Stéphane Huet | Bassam Jabaian | Alejandro Molina | Juan-Manuel Torres-Moreno | Marc El-BÚze | Barthélémy Durette
TALN-RECITAL 2014 Workshop DEFT 2014 : DĂfi Fouille de Textes (DEFT 2014 Workshop: Text Mining Challenge)
2013
Search and usage of named conceptual entities in a categorisazion task (Recherche et utilisation dâentitĂ©s nommĂ©es conceptuelles dans une tĂąche de catĂ©gorisation) [in French]
Jean-ValĂšre Cossu | Juan-Manuel Torres-Moreno | Marc El-BĂšze
Proceedings of TALN 2013 (Volume 2: Short Papers)
Jean-ValĂšre Cossu | Juan-Manuel Torres-Moreno | Marc El-BĂšze
Proceedings of TALN 2013 (Volume 2: Short Papers)
SegCV : Eficient parsing of rĂ©sumĂ©s with analysis and correction of errors (SegCV : traitement efficace de CV avec analyse et correction dâerreurs) [in French]
Luis AdriĂĄn Cabrera-Diego | Juan-Manuel Torres-Moreno | Marc El-BĂšze
Proceedings of TALN 2013 (Volume 2: Short Papers)
Luis AdriĂĄn Cabrera-Diego | Juan-Manuel Torres-Moreno | Marc El-BĂšze
Proceedings of TALN 2013 (Volume 2: Short Papers)
2011
On the Development of the RST Spanish Treebank
Iria da Cunha | Juan-Manuel Torres-Moreno | Gerardo Sierra
Proceedings of the 5th Linguistic Annotation Workshop
Iria da Cunha | Juan-Manuel Torres-Moreno | Gerardo Sierra
Proceedings of the 5th Linguistic Annotation Workshop
The RST Spanish Treebank On-line Interface
Iria da Cunha | Juan-Manuel Torres-Moreno | Gerardo Sierra | Luis-AdriĂĄn Cabrera-Diego | Brenda-Gabriela Castro-RolĂłn | Juan-Miguel Rolland Bartilotti
Proceedings of the International Conference Recent Advances in Natural Language Processing 2011
Iria da Cunha | Juan-Manuel Torres-Moreno | Gerardo Sierra | Luis-AdriĂĄn Cabrera-Diego | Brenda-Gabriela Castro-RolĂłn | Juan-Miguel Rolland Bartilotti
Proceedings of the International Conference Recent Advances in Natural Language Processing 2011
Utilisation dâun score de qualitĂ© de traduction pour le rĂ©sumĂ© multi-document cross-lingue (Using translation quality scores for cross-language multi-document summarization)
Stéphane Huet | Florian Boudin | Juan-Manuel Torres-Moreno
Actes de la 18e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Stéphane Huet | Florian Boudin | Juan-Manuel Torres-Moreno
Actes de la 18e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Le rĂ©sumĂ© automatique cross-lingue consiste Ă gĂ©nĂ©rer un rĂ©sumĂ© rĂ©digĂ© dans une langue diffĂ©rente de celle utilisĂ©e dans les documents sources. Dans cet article, nous proposons une approche de rĂ©sumĂ© automatique multi-document, basĂ©e sur une reprĂ©sentation par graphe, qui prend en compte des scores de qualitĂ© de traduction lors du processus de sĂ©lection des phrases. Nous Ă©valuons notre mĂ©thode sur un sous-ensemble manuellement traduit des donnĂ©es utilisĂ©es lors de la campagne dâĂ©valuation internationale DUC 2004. Les rĂ©sultats expĂ©rimentaux indiquent que notre approche permet dâamĂ©liorer la lisibilitĂ© des rĂ©sumĂ©s gĂ©nĂ©rĂ©s, sans pour autant dĂ©grader leur informativitĂ©.
2010
A French Human Reference Corpus for Multi-Document Summarization and Sentence Compression
Claude de Loupy | Marie Guégan | Christelle Ayache | Somara Seng | Juan-Manuel Torres Moreno
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)
Claude de Loupy | Marie Guégan | Christelle Ayache | Somara Seng | Juan-Manuel Torres Moreno
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)
This paper presents two corpora produced within the RPM2 project: a multi-document summarization corpus and a sentence compression corpus. Both corpora are in French. The first one is the only one we know in this language. It contains 20 topics with 20 documents each. A first set of 10 documents per topic is summarized and then the second set is used to produce an update summarization (new information). 4 annotators were involved and produced a total of 160 abstracts. The second corpus contains all the sentences of the first one. 4 annotators were asked to compress the 8432 sentences. This is the biggest corpus of compressed sentences we know, whatever the language. The paper provides some figures in order to compare the different annotators: compression rates, number of tokens per sentence, percentage of tokens kept according to their POS, position of dropped tokens in the sentence compression phase, etc. These figures show important differences from an annotator to the other. Another point is the different strategies of compression used according to the length of the sentence.
NLGbAse: A Free Linguistic Resource for Natural Language Processing Systems
Eric Charton | Juan-Manuel Torres-Moreno
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)
Eric Charton | Juan-Manuel Torres-Moreno
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)
Availability of labeled language resources, such as annotated corpora and domain dependent labeled language resources is crucial for experiments in the field of Natural Language Processing. Most often, due to lack of resources, manual verification and annotation of electronic text material is a prerequisite for the development of NLP tools. In the context of under-resourced language, the lack of copora becomes a crucial problem because most of the research efforts are supported by organizations with limited funds. Using free, multilingual and highly structured corpora like Wikipedia to produce automatically labeled language resources can be an answer to those needs. This paper introduces NLGbAse, a multilingual linguistic resource built from the Wikipedia encyclopedic content. This system produces structured metadata which make possible the automatic annotation of corpora with syntactical and semantical labels. A metadata contains semantical and statistical informations related to an encyclopedic document. To validate our approach, we built and evaluated a Named Entity Recognition tool, trained with Wikipedia corpora annotated by our system.
Automatic Summarization Using Terminological and Semantic Resources
Jorge Vivaldi | Iria da Cunha | Juan-Manuel Torres-Moreno | Patricia VelĂĄzquez-Morales
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)
Jorge Vivaldi | Iria da Cunha | Juan-Manuel Torres-Moreno | Patricia VelĂĄzquez-Morales
Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)
This paper presents a new algorithm for automatic summarization of specialized texts combining terminological and semantic resources: a term extractor and an ontology. The term extractor provides the list of the terms that are present in the text together their corresponding termhood. The ontology is used to calculate the semantic similarity among the terms found in the main body and those present in the document title. The general idea is to obtain a relevance score for each sentence taking into account both the Âtermhood of the terms found in such sentence and the similarity among such terms and those terms present in the title of the document. The phrases with the highest score are chosen to take part of the final summary. We evaluate the algorithm with Rouge, comparing the resulting summaries with the summaries of other summarizers. The sentence selection algorithm was also tested as part of a standalone summarizer. In both cases it obtains quite good results although the perception is that there is a space for improvement.
Multilingual Summarization Evaluation without Human Models
Horacio Saggion | Juan-Manuel Torres-Moreno | Iria da Cunha | Eric SanJuan | Patricia VelĂĄzquez-Morales
Coling 2010: Posters
Horacio Saggion | Juan-Manuel Torres-Moreno | Iria da Cunha | Eric SanJuan | Patricia VelĂĄzquez-Morales
Coling 2010: Posters
Ăvaluation automatique de rĂ©sumĂ©s avec et sans rĂ©fĂ©rence
Juan-Manuel Torres-Moreno | Horacio Saggion | Iria da Cunha | Patricia VelĂĄzquez-Morales | Eric Sanjuan
Actes de la 17e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Juan-Manuel Torres-Moreno | Horacio Saggion | Iria da Cunha | Patricia VelĂĄzquez-Morales | Eric Sanjuan
Actes de la 17e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Nous Ă©tudions diffĂ©rentes mĂ©thodes dâĂ©valuation de rĂ©sumĂ© de documents basĂ©es sur le contenu. Nous nous intĂ©ressons en particulier Ă la corrĂ©lation entre les mesures dâĂ©valuation avec et sans rĂ©fĂ©rence humaine. Nous avons dĂ©veloppĂ© FRESA, un nouveau systĂšme dâĂ©valuation fondĂ© sur le contenu qui calcule les divergences entre les distributions de probabilitĂ©. Nous appliquons notre systĂšme de comparaison aux diverses mesures dâĂ©valuation bien connues en rĂ©sumĂ© de texte telles que la Couverture, Responsiveness, Pyramids et Rouge en Ă©tudiant leurs associations dans les tĂąches du rĂ©sumĂ© multi-document gĂ©nĂ©rique (francais/anglais), focalisĂ© (anglais) et rĂ©sumĂ© mono-document gĂ©nĂ©rique (français/espagnol).
2009
Proceedings of the 1st Workshop on Definition Extraction
Gerardo Sierra | Mara Pozzi | Juan-Manuel Torres
Proceedings of the 1st Workshop on Definition Extraction
Gerardo Sierra | Mara Pozzi | Juan-Manuel Torres
Proceedings of the 1st Workshop on Definition Extraction
Classification dâun contenu encyclopĂ©dique en vue dâun Ă©tiquetage par entitĂ©s nommĂ©es
Eric Charton | Juan-Manuel Torres-Moreno
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Eric Charton | Juan-Manuel Torres-Moreno
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
On utilise souvent des ressources lexicales externes pour amĂ©liorer les performances des systĂšmes dâĂ©tiquetage dâentitĂ©s nommĂ©es. Les contenus de ces ressources lexicales peuvent ĂȘtre variĂ©s : liste de noms propres, de lieux, de marques. On note cependant que la disponibilitĂ© de corpus encyclopĂ©diques exhaustifs et ouverts de grande taille tels que Worldnet ou Wikipedia, a fait Ă©merger de nombreuses propositions spĂ©cifiques dâexploitation de ces contenus par des systĂšmes dâĂ©tiquetage. Un problĂšme demeure nĂ©anmoins ouvert avec ces ressources : celui de lâadaptation de leur taxonomie interne, complexe et composĂ©e de dizaines de milliers catĂ©gories, aux exigences particuliĂšres de lâĂ©tiquetage des entitĂ©s nommĂ©es. Pour ces derniĂšres, au plus de quelques centaines de classes sĂ©mantiques sont requises. Dans cet article nous explorons cette difficultĂ© et proposons un systĂšme complet de transformation dâun arbre taxonomique encyclopĂ©dique en une systĂšme Ă classe sĂ©mantiques adaptĂ© Ă lâĂ©tiquetage dâentitĂ©s nommĂ©es.
Une approche exploratoire de compression automatique de phrases basée sur des critÚres thermodynamiques
Silvia FernĂĄndez Sabido | Juan-Manuel Torres-Moreno
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
Silvia FernĂĄndez Sabido | Juan-Manuel Torres-Moreno
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
Nous prĂ©sentons une approche exploratoire basĂ©e sur des notions thermodynamiques de la Physique statistique pour la compression de phrases. Nous dĂ©crivons le modĂšle magnĂ©tique des verres de spins, adaptĂ© Ă notre conception de la problĂ©matique. Des simulations MĂ©tropolis Monte-Carlo permettent dâintroduire des fluctuations thermiques pour piloter la compression. Des comparaisons intĂ©ressantes de notre mĂ©thode ont Ă©tĂ© rĂ©alisĂ©es sur un corpus en français.
Résumé automatique multi-document et indépendance de la langue : une premiÚre évaluation en français
Florian Boudin | Juan-Manuel Torres-Moreno
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
Florian Boudin | Juan-Manuel Torres-Moreno
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
Le rĂ©sumĂ© automatique de texte est une problĂ©matique difficile, fortement dĂ©pendante de la langue et qui peut nĂ©cessiter un ensemble de donnĂ©es dâapprentissage consĂ©quent. Lâapproche par extraction peut aider Ă surmonter ces difficultĂ©s. (Mihalcea, 2004) a dĂ©montrĂ© lâintĂ©rĂȘt des approches Ă base de graphes pour lâextraction de segments de texte importants. Dans cette Ă©tude, nous dĂ©crivons une approche indĂ©pendante de la langue pour la problĂ©matique du rĂ©sumĂ© automatique multi-documents. LâoriginalitĂ© de notre mĂ©thode repose sur lâutilisation dâune mesure de similaritĂ© permettant le rapprochement de segments morphologiquement proches. De plus, câest Ă notre connaissance la premiĂšre fois que lâĂ©valuation dâune approche de rĂ©sumĂ© automatique multi-document est conduite sur des textes en français.
Profilage de candidatures assisté par Relevance Feedback
Rémy Kessler | Nicolas Béchet | Juan-Manuel Torres-Moreno | Mathieu Roche | Marc El-BÚze
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
Rémy Kessler | Nicolas Béchet | Juan-Manuel Torres-Moreno | Mathieu Roche | Marc El-BÚze
Actes de la 16Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
Le marchĂ© dâoffres dâemploi et des candidatures sur Internet connaĂźt une croissance exponentielle. Ceci implique des volumes dâinformation (majoritairement sous la forme de texte libre) quâil nâest plus possible de traiter manuellement. Une analyse et catĂ©gorisation assistĂ©es nous semble pertinente en rĂ©ponse Ă cette problĂ©matique. Nous proposons E-Gen, systĂšme qui a pour but lâanalyse et catĂ©gorisation assistĂ©s dâoffres dâemploi et des rĂ©ponses des candidats. Dans cet article nous prĂ©sentons plusieurs stratĂ©gies, reposant sur les modĂšles vectoriel et probabiliste, afin de rĂ©soudre la problĂ©matique du profilage des candidatures en fonction dâune offre prĂ©cise. Nous avons Ă©valuĂ© une palette de mesures de similaritĂ© afin dâeffectuer un classement pertinent des candidatures au moyen des courbes ROC. Lâutilisation dâune forme de relevance feedback a permis de surpasser nos rĂ©sultats sur ce problĂšme difficile et sujet Ă une grande subjectivitĂ©.
2008
A Scalable MMR Approach to Sentence Scoring for Multi-Document Update Summarization
Florian Boudin | Marc El-BĂšze | Juan-Manuel Torres-Moreno
Coling 2008: Companion volume: Posters
Florian Boudin | Marc El-BĂšze | Juan-Manuel Torres-Moreno
Coling 2008: Companion volume: Posters
Extraction automatique dâinformations Ă partir de micro-textes non structurĂ©s
Cédric Vidrequin | Juan-Manuel Torres-Moreno | Jean-Jacques Schneider | Marc El-BÚze
Actes de la 15Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Cédric Vidrequin | Juan-Manuel Torres-Moreno | Jean-Jacques Schneider | Marc El-BÚze
Actes de la 15Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Nous prĂ©sentons dans cet article une mĂ©thode dâextraction automatique dâinformations sur des textes de trĂšs petite taille, faiblement structurĂ©s. Nous travaillons sur des textes dont la rĂ©daction nâest pas normalisĂ©e, avec trĂšs peu de mots pour caractĂ©riser chaque information. Les textes ne contiennent pas ou trĂšs peu de phrases. Il sâagit le plus souvent de morceaux de phrases ou dâexpressions composĂ©es de quelques mots. Nous comparons plusieurs mĂ©thodes dâextraction, dont certaines sont entiĂšrement automatiques. Dâautres utilisent en partie une connaissance du domaine que nous voulons rĂ©duite au minimum, de façon Ă minimiser le travail manuel en amont. Enfin, nous prĂ©sentons nos rĂ©sultats qui dĂ©passent ce dont il est fait Ă©tat dans la littĂ©rature, avec une prĂ©cision Ă©quivalente et un rappel supĂ©rieur.
Enertex : un systĂšme basĂ© sur lâĂ©nergie textuelle
Silvia FernĂĄndez | Eric Sanjuan | Juan-Manuel Torres-Moreno
Actes de la 15Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Silvia FernĂĄndez | Eric Sanjuan | Juan-Manuel Torres-Moreno
Actes de la 15Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Dans cet article, nous prĂ©sentons des applications du systĂšme Enertex au Traitement Automatique de la Langue Naturelle. Enertex est basĂ© sur lâĂ©nergie textuelle, une approche par rĂ©seaux de neurones inspirĂ©e de la physique statistique des systĂšmes magnĂ©tiques. Nous avons appliquĂ© cette approche aux problĂšmes du rĂ©sumĂ© automatique multi-documents et de la dĂ©tection de frontiĂšres thĂ©matiques. Les rĂ©sultats, en trois langues : anglais, espagnol et français, sont trĂšs encourageants.
E-Gen : Profilage automatique de candidatures
Rémy Kessler | Juan-Manuel Torres-Moreno | Marc El-BÚze
Actes de la 15Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
Rémy Kessler | Juan-Manuel Torres-Moreno | Marc El-BÚze
Actes de la 15Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles courts
La croissance exponentielle de lâInternet a permis le dĂ©veloppement de sites dâoffres dâemploi en ligne. Le systĂšme E-Gen (Traitement automatique dâoffres dâemploi) a pour but de permettre lâanalyse et la catĂ©gorisation dâoffres dâemploi ainsi quâune analyse et classification des rĂ©ponses des candidats (Lettre de motivation et CV). Nous prĂ©sentons les travaux rĂ©alisĂ©s afin de rĂ©soudre la seconde partie : on utilise une reprĂ©sentation vectorielle de texte pour effectuer une classification des piĂšces jointes contenus dans le mail Ă lâaide de SVM. Par la suite, une Ă©valuation de la candidature est effectuĂ©e Ă lâaide de diffĂ©rents classifieurs (SVM et n-grammes de mots).
2007
Ănergie textuelle de mĂ©moires associatives
Silvia FernĂĄndez | Eric Sanjuan | Juan-Manuel Torres-Moreno
Actes de la 14Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Silvia FernĂĄndez | Eric Sanjuan | Juan-Manuel Torres-Moreno
Actes de la 14Úme conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
Dans cet article, nous prĂ©sentons une approche de rĂ©seaux de neurones inspirĂ©e de la physique statistique de systĂšmes magnĂ©tiques pour Ă©tudier des problĂšmes fondamentaux du Traitement Automatique de la Langue Naturelle. Lâalgorithme modĂ©lise un document comme un systĂšme de neurones oĂč lâon dĂ©duit lâĂ©nergie textuelle. Nous avons appliquĂ© cette approche aux problĂšmes de rĂ©sumĂ© automatique et de dĂ©tection de frontiĂšres thĂ©matiques. Les rĂ©sultats sont trĂšs encourageants.
Search
Fix author
Co-authors
- Marc El-BĂšze 7
- Stéphane Huet 5
- Elvys Linhares-Pontes 5
- Iria da Cunha 5
- Eric Sanjuan 4
- Gerardo Sierra 4
- Patricia Velazquez-Morales 4
- Florian Boudin 3
- Luis-AdriĂĄn Cabrera-Diego 3
- Miguel Figueroa-Saavedra 3
- Juan-José Guzmån-Landa 3
- Andréa Carneiro Linhares 3
- Martha Lorena Avendaño Garrido 3
- Luis-Gil Moreno-Jiménez 3
- Graham Ranger 3
- Eric Charton 2
- Silvia FernĂĄndez 2
- Dominic Forest 2
- Carlos-Emiliano Gonzalez-Gallardo 2
- Rémy Kessler 2
- Ligia Quintana-Torres 2
- Horacio Saggion 2
- Soledad AragĂłn MartĂnez 1
- Ignacio Arroyo-FernĂĄndez 1
- Christelle Ayache 1
- Gemma Bel-Enguix 1
- Patrice Bellot 1
- Nicolas Béchet 1
- Mauricio Carrasco-Ruiz 1
- Brenda-Gabriela Castro-RolĂłn 1
- Vincent Claveau 1
- Jean-ValĂšre Cossu 1
- Rodrigo Cuéllar-Hidalgo 1
- Tomas Damerau 1
- Barthélémy Durette 1
- Iris Eshkol 1
- Silvia FernĂĄndez Sabido 1
- Amel Fraisse 1
- Helena Gomez Adorno 1
- Thiago Gouveia da Silva 1
- Cyril Grouin 1
- Julio V Guadarrama-Olvera 1
- Julio de JesĂșs Guerrero-Zambrano 1
- Marie Guégan 1
- Tonatiuh HernĂĄndez-GarcĂa 1
- Bassam Jabaian 1
- Agata Jackiewicz 1
- Karen Joannette 1
- Jihen Karoui 1
- Thomas Legeleux 1
- Alejandro Molina 1
- Laura Monceaux 1
- Luis Moreno Jimenez 1
- Jesus-German Ortiz-Barajas 1
- Patrick Paroubek 1
- Maria Pozzi 1
- Gerardo Reyes-Salgado 1
- Mathieu Roche 1
- Ăngela MarĂa Rojas 1
- Juan-Miguel Rolland Bartilotti 1
- Jean-Jacques Schneider 1
- Somara Seng 1
- Cédric Vidrequin 1
- Jorge Vivaldi 1
- Roseli Wedemann 1
- Claude de Loupy 1