Juan-Manuel Torres-Moreno

Juan-José Guzmán-Landa, Juan-Manuel Torres-Moreno, Miguel Figueroa-Saavedra et al.

The aim of this article is to introduce two Context-Free Grammars (CFG) for Nawatl Corpora expansion. Nawatl is an Amerindian language (it is a National Language of Mexico) of the $π$-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 non contextual embeddings. For this objective, we introduce two new Nawatl CFGs and use them in generative mode. Using these grammars, it is possible to expand Nawatl corpus significantly and subsequently to use it to learn embeddings and to evaluate their relevance in a sentences semantic similarity task. 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.

Juan-José Guzmán-Landa, Juan-Manuel Torres-Moreno, Miguel Figueroa-Saavedra et al.

Mexico is a country with a large number of indigenous languages, among which the most widely spoken is Nawatl, with more than two million people currently speaking it (mainly in North and Central America). Despite its rich cultural heritage, which dates back to the 15th century, Nawatl is a language with few computer resources. The problem is compounded when it comes to its dialectal varieties, with approximately 30 varieties recognised, not counting the different spellings in the written forms of the language. In this research work, we addressed the problem of classifying Nawatl varieties using Machine Learning and Neural Networks.

Juan-José Guzman-Landa, Juan-Manuel Torres-Moreno, Graham Ranger et al.

In this article, we seek to answer the following question: could data duplication be useful in Natural Language Processing (NLP) for languages with limited computational resources? In this type of languages (or $π$-languages), corpora available for training Large Language Models are virtually non-existent. In particular, we will study the impact of corpora expansion in Nawatl, an agglutinative and polysynthetic $π$-language spoken by over 2 million people, with a large number of dialectal varieties. The aim is to expand the new $π$-yalli corpus, which contains a limited number of Nawatl texts, by duplicating it in a controlled way. In our experiments, we will use the incremental duplication technique. The aim is to learn embeddings that are well-suited to NLP tasks. Thus, static embeddings were trained and evaluated in a sentence-level semantic similarity task. Our results show a moderate improvement in performance when using incremental duplication compared to the results obtained using only the corpus without expansion. Furthermore, to our knowledge, this technique has not yet been used in the literature.

Juan-José Guzmán-Landa, Jesús Vázquez-Osorio, Juan-Manuel Torres-Moreno et al.

In this paper, we describe a symbolic model for the automatic orthographic unification of Nawatl text documents. Our model is based on algorithms that we have previously used to analyze sentences in Nawatl, and on the corpus called $π$-yalli, consisting of texts in several Nawatl orthographies. Our automatic unification algorithm implements linguistic rules in symbolic regular expressions. We also present a manual evaluation protocol that we have proposed and implemented to assess the quality of the unified sentences generated by our algorithm, by testing in a sentence semantic task. We have obtained encouraging results from the evaluators for most of the desired features of our artificially unified sentences

Juan-José Guzmán-Landa, Juan-Manuel Torres-Moreno, Miguel Figueroa-Saavedra et al.

In this article we introduce a context-free grammar (CFG) for the Nawatl language. Nawatl (or Nahuatl) is an Amerindian language of the $π$-language type, i.e. a language with few digital resources, in which the corpora available for machine learning are virtually non-existent. The objective here is to generate a significant number of grammatically correct artificial sentences, in order to increase the corpora available for language model training. We want to show that a grammar enables us significantly to expand a corpus in Nawatl which we call $π$-\textsc{yalli}. The corpus, thus enriched, enables us to train algorithms such as FastText and to evaluate them on sentence-level semantic tasks. Preliminary results show that by using the grammar, comparative improvements are achieved over some LLMs. However, it is observed that to achieve more significant improvement, grammars that model the Nawatl language even more effectively are required.

Juan-Manuel Torres-Moreno, Juan-José Guzmán-Landa, Graham Ranger et al.

The NAHU$^2$ project is a Franco-Mexican collaboration aimed at building the $π$-YALLI corpus adapted to machine learning, which will subsequently be used to develop computer resources for the Nahuatl language. Nahuatl is a language with few computational resources, even though it is a living language spoken by around 2 million people. We have decided to build $π$-YALLI, a corpus that will enable to carry out research on Nahuatl in order to develop Language Models (LM), whether dynamic or not, which will make it possible to in turn enable the development of Natural Language Processing (NLP) tools such as: a) a grapheme unifier, b) a word segmenter, c) a POS grammatical analyser, d) a content-based Automatic Text Summarization; and possibly, e) a translator translator (probabilistic or learning-based).

Luis-Gil Moreno-Jiménez, Juan-Manuel Torres-Moreno, Roseli S. Wedemann

In recent years, researchers in the area of Computational Creativity have studied the human creative process proposing different approaches to reproduce it with a formal procedure. In this paper, we introduce a model for the generation of literary rhymes in Spanish, combining structures of language and neural network models %(\textit{Word2vec}).%, into a structure for semantic assimilation. The results obtained with a manual evaluation of the texts generated by our algorithm are encouraging.

Rodrigo Cuéllar-Hidalgo, Julio de Jesús Guerrero-Zambrano, Dominic Forest et al.

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@ICON'21 Workshop on Multilingual Gender Biased and Communal Language Identification.

Juan-Manuel Torres-Moreno, Luis-Gil Moreno-Jiménez

In this work we present a new small data-set in Computational Creativity (CC) field, the Spanish Literary Sentences for emotions detection corpus (LISSS). We address this corpus of literary sentences in order to evaluate or design algorithms of emotions classification and detection. We have constitute this corpus by manually classifying the sentences in a set of emotions: Love, Fear, Happiness, Anger and Sadness/Pain. We also present some baseline classification algorithms applied on our corpus. The LISSS corpus will be available to the community as a free resource to evaluate or create CC-like algorithms.

Iria da Cunha, Juan-Manuel Torres-Moreno

Multilingual discourse parsing is a very prominent research topic. The first stage for discourse parsing is discourse segmentation. The study reported in this article addresses a review of two on-line available discourse segmenters (for English and Portuguese). We evaluate the possibility of developing similar discourse segmenters for Spanish, French and African languages.

Carlos-Emiliano González-Gallardo, Eric SanJuan, Juan-Manuel Torres-Moreno

Standard informativeness measures used to evaluate Automatic Text Summarization mostly rely on n-gram overlapping between the automatic summary and the reference summaries. These measures differ from the metric they use (cosine, ROUGE, Kullback-Leibler, Logarithm Similarity, etc.) and the bag of terms they consider (single words, word n-grams, entities, nuggets, etc.). Recent word embedding approaches offer a continuous alternative to discrete approaches based on the presence/absence of a text unit. Informativeness measures have been extended to Focus Information Retrieval evaluation involving a user's information need represented by short queries. In particular for the task of CLEF-INEX Tweet Contextualization, tweet contents have been considered as queries. In this paper we define the concept of Interestingness as a generalization of Informativeness, whereby the information need is diverse and formalized as an unknown set of implicit queries. We then study the ability of state of the art Informativeness measures to cope with this generalization. Lately we show that with this new framework, standard word embeddings outperforms discrete measures only on uni-grams, however bi-grams seems to be a key point of interestingness evaluation. Lastly we prove that the CLEF-INEX Tweet Contextualization 2012 Logarithm Similarity measure provides best results.

Elvys Linhares Pontes, Stéphane Huet, Juan-Manuel Torres-Moreno et al.

Multi-Sentence Compression (MSC) aims to generate a short sentence with the key information from a cluster of similar sentences. MSC enables summarization and question-answering systems to generate outputs combining fully formed sentences from one or several documents. This paper describes an Integer Linear Programming method for MSC using a vertex-labeled graph to select different keywords, with the goal of generating 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 datasets in three languages: French, Portuguese and Spanish. We led both automatic and manual evaluations to determine the informativeness and the grammaticality of compressions for each dataset. In additional tests, which take advantage of the fact that the length of compressions can be modulated, we still improve ROUGE scores with shorter output sentences.

Rémy Saksik, Alejandro Molina-Villegas, Andréa Carneiro Linhares et al.

In this article, we describe some discursive segmentation methods as well as a preliminary evaluation of the segmentation quality. Although our experiment were carried for documents in French, we have developed three discursive segmentation models solely based on resources simultaneously available in several languages: marker lists and a statistic POS labeling. We have also carried out automatic evaluations of these systems against the Annodis corpus, which is a manually annotated reference. The results obtained are very encouraging.

Carlos-Emiliano González-Gallardo, Romain Deveaud, Eric SanJuan et al.

The automatic summarization of multimedia sources is an important task that facilitates the understanding of an individual by condensing the source while maintaining relevant information. In this paper we focus on audio summarization based on audio features and the probability of distribution divergence. Our method, based on an extractive summarization approach, aims to select the most relevant segments until a time threshold is reached. It takes into account the segment's length, position and informativeness value. Informativeness of each segment is obtained by mapping a set of audio features issued from its Mel-frequency Cepstral Coefficients and their corresponding Jensen-Shannon divergence score. Results over a multi-evaluator scheme shows that our approach provides understandable and informative summaries.

Luis-Gil Moreno-Jiménez, Juan-Manuel Torres-Moreno, Roseli S. Wedemann

In this work we present a state of the art in the area of Computational Creativity (CC). In particular, we address the automatic generation of literary sentences in Spanish. We propose three models of text generation based mainly on statistical algorithms and shallow parsing analysis. We also present some rather encouraging preliminary results.

Ana Lilia Laureano-Cruces, Laura Hernández-Domínguez, Martha Mora-Torres et al.

In this paper, we present a visual emulator of the emotions seen in characters in stories. This system is based on a simplified view of the cognitive structure of emotions proposed by Ortony, Clore and Collins (OCC Model). The goal of this paper is to provide a visual platform that allows us to observe changes in the characters' different emotions, and the intricate interrelationships between: 1) each character's emotions, 2) their affective relationships and actions, 3) The events that take place in the development of a plot, and 4) the objects of desire that make up the emotional map of any story. This tool was tested on stories with a contrasting variety of emotional and affective environments: Othello, Twilight, and Harry Potter, behaving sensibly and in keeping with the atmosphere in which the characters were immersed.

Jean Valère Cossu, Juan-Manuel Torres-Moreno, Eric SanJuan et al.

The amount of user generated contents from various social medias allows analyst to handle a wide view of conversations on several topics related to their business. Nevertheless keeping up-to-date with this amount of information is not humanly feasible. Automatic Summarization then provides an interesting mean to digest the dynamics and the mass volume of contents. In this paper, we address the issue of tweets summarization which remains scarcely explored. We propose to automatically generated summaries of Micro-Blogs conversations dealing with public figures E-Reputation. These summaries are generated using key-word queries or sample tweet and offer a focused view of the whole Micro-Blog network. Since state-of-the-art is lacking on this point we conduct and evaluate our experiments over the multilingual CLEF RepLab Topic-Detection dataset according to an experimental evaluation process.

Andrés Torres-Rivera, Juan-Manuel Torres-Moreno

Semantic neologisms (SN) are defined as words that acquire a new word meaning while maintaining their form. Given the nature of this kind of neologisms, the task of identifying these new word meanings is currently performed manually by specialists at observatories of neology. To detect SN in a semi-automatic way, we developed a system that implements a combination of the following strategies: topic modeling, keyword extraction, and word sense disambiguation. The role of topic modeling is to detect the themes that are treated in the input text. Themes within a text give clues about the particular meaning of the words that are used, for example: viral has one meaning in the context of computer science (CS) and another when talking about health. To extract keywords, we used TextRank with POS tag filtering. With this method, we can obtain relevant words that are already part of the Spanish lexicon. We use a deep learning model to determine if a given keyword could have a new meaning. Embeddings that are different from all the known meanings (or topics) indicate that a word might be a valid SN candidate. In this study, we examine the following word embedding models: Word2Vec, Sense2Vec, and FastText. The models were trained with equivalent parameters using Wikipedia in Spanish as corpora. Then we used a list of words and their concordances (obtained from our database of neologisms) to show the different embeddings that each model yields. Finally, we present a comparison of these outcomes with the concordances of each word to show how we can determine if a word could be a valid candidate for SN.

Alexandre Nadjem, Juan-Manuel Torres-Moreno, Marc El-Bèze et al.

Nobody knows what one's do in the future and everyone will have had a different answer to the question : how do you see yourself in five years after your current job/diploma? In this paper we introduce concepts, large categories of fields of studies or job domains in order to represent the vision of the future of the user's trajectory. Then, we show how they can influence the prediction when proposing him a set of next steps to take.

Alfonso Medina-Urrea, Juan-Manuel Torres-Moreno

This paper presents RIMAX, a new system for detecting semantic rhymes, using a Comprehensive Mexican Spanish Dictionary (DEM) and its Rhyming Dictionary (REM). We use the Vector Space Model to calculate the similarity of the definition of a query with the definitions corresponding to the assonant and consonant rhymes of the query. The preliminary results using a manual evaluation are very encouraging.

Marc El-Bèze, Juan-Manuel Torres-Moreno, Frédéric Béchet

We present a set of probabilistic models applied to binary classification as defined in the DEFT'05 challenge. The challenge consisted a mixture of two differents problems in Natural Language Processing : identification of author (a sequence of François Mitterrand's sentences might have been inserted into a speech of Jacques Chirac) and thematic break detection (the subjects addressed by the two authors are supposed to be different). Markov chains, Bayes models and an adaptative process have been used to identify the paternity of these sequences. A probabilistic model of the internal coherence of speeches which has been employed to identify thematic breaks. Adding this model has shown to improve the quality results. A comparison with different approaches demostrates the superiority of a strategy that combines learning, coherence and adaptation. Applied to the DEFT'05 data test the results in terms of precision (0.890), recall (0.955) and Fscore (0.925) measure are very promising.

Elvys Linhares Pontes, Stéphane Huet, Andréa Carneiro Linhares et al.

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.

Elvys Linhares Pontes, Stéphane Huet, Juan-Manuel Torres-Moreno

Cross-Language Text Summarization (CLTS) generates summaries in a language different from the language of the source documents. Recent methods use information from both languages to generate summaries with the most informative sentences. However, these methods have performance that can vary according to languages, which can reduce the quality of summaries. In this paper, we propose a compressive framework to generate cross-language summaries. In order to analyze performance and especially stability, we tested our system and extractive baselines on a dataset available in four languages (English, French, Portuguese, and Spanish) to generate English and French summaries. An automatic evaluation showed that our method outperformed extractive state-of-art CLTS methods with better and more stable ROUGE scores for all languages.

Carlos-Emiliano González-Gallardo, Malek Hajjem, Eric SanJuan et al.

In this paper we propose a new approach to evaluate the informativeness of transcriptions coming from Automatic Speech Recognition systems. This approach, based in the notion of informativeness, is focused on the framework of Automatic Text Summarization performed over these transcriptions. At a first glance we estimate the informative content of the various automatic transcriptions, then we explore the capacity of Automatic Text Summarization to overcome the informative loss. To do this we use an automatic summary evaluation protocol without reference (based on the informative content), which computes the divergence between probability distributions of different textual representations: manual and automatic transcriptions and their summaries. After a set of evaluations this analysis allowed us to judge both the quality of the transcriptions in terms of informativeness and to assess the ability of automatic text summarization to compensate the problems raised during the transcription phase.

Carlos-Emiliano González-Gallardo, Juan-Manuel Torres-Moreno

Sentence Boundary Detection (SBD) has been a major research topic since Automatic Speech Recognition transcripts have been used for further Natural Language Processing tasks like Part of Speech Tagging, Question Answering or Automatic Summarization. But what about evaluation? Do standard evaluation metrics like precision, recall, F-score or classification error; and more important, evaluating an automatic system against a unique reference is enough to conclude how well a SBD system is performing given the final application of the transcript? In this paper we propose Window-based Sentence Boundary Evaluation (WiSeBE), a semi-supervised metric for evaluating Sentence Boundary Detection systems based on multi-reference (dis)agreement. We evaluate and compare the performance of different SBD systems over a set of Youtube transcripts using WiSeBE and standard metrics. This double evaluation gives an understanding of how WiSeBE is a more reliable metric for the SBD task.

Carlos-Emiliano González-Gallardo, Juan-Manuel Torres-Moreno

In this work we tackle the problem of sentence boundary detection applied to French as a binary classification task ("sentence boundary" or "not sentence boundary"). We combine convolutional neural networks with subword-level information vectors, which are word embedding representations learned from Wikipedia that take advantage of the words morphology; so each word is represented as a bag of their character n-grams. We decide to use a big written dataset (French Gigaword) instead of standard size transcriptions to train and evaluate the proposed architectures with the intention of using the trained models in posterior real life ASR transcriptions. Three different architectures are tested showing similar results; general accuracy for all models overpasses 0.96. All three models have good F1 scores reaching values over 0.97 regarding the "not sentence boundary" class. However, the "sentence boundary" class reflects lower scores decreasing the F1 metric to 0.778 for one of the models. Using subword-level information vectors seem to be very effective leading to conclude that the morphology of words encoded in the embeddings representations behave like pixels in an image making feasible the use of convolutional neural network architectures.

Ignacio Arroyo-Fernández, Carlos-Francisco Méndez-Cruz, Gerardo Sierra et al.

Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an open question due to complexities of semantic interactions among words. In this paper, we present an embedding method, which is aimed at learning unsupervised sentence representations from unlabeled text. We propose an unsupervised method that models a sentence as a weighted series of word embeddings. The weights of the word embeddings are fitted by using Shannon's word entropies provided by the Term Frequency--Inverse Document Frequency (TF--IDF) transform. The hyperparameters of the model can be selected according to the properties of data (e.g. sentence length and textual gender). Hyperparameter selection involves word embedding methods and dimensionalities, as well as weighting schemata. Our method offers advantages over existing methods: identifiable modules, short-term training, online inference of (unseen) sentence representations, as well as independence from domain, external knowledge and language resources. Results showed that our model outperformed the state of the art in well-known Semantic Textual Similarity (STS) benchmarks. Moreover, our model reached state-of-the-art performance when compared to supervised and knowledge-based STS systems.

Mohamed Morchid, Juan-Manuel Torres-Moreno, Richard Dufour et al.

The number of documents available into Internet moves each day up. For this reason, processing this amount of information effectively and expressibly becomes a major concern for companies and scientists. Methods that represent a textual document by a topic representation are widely used in Information Retrieval (IR) to process big data such as Wikipedia articles. One of the main difficulty in using topic model on huge data collection is related to the material resources (CPU time and memory) required for model estimate. To deal with this issue, we propose to build topic spaces from summarized documents. In this paper, we present a study of topic space representation in the context of big data. The topic space representation behavior is analyzed on different languages. Experiments show that topic spaces estimated from text summaries are as relevant as those estimated from the complete documents. The real advantage of such an approach is the processing time gain: we showed that the processing time can be drastically reduced using summarized documents (more than 60\% in general). This study finally points out the differences between thematic representations of documents depending on the targeted languages such as English or latin languages.

Elvys Linhares Pontes, Thiago Gouveia da Silva, Andréa Carneiro Linhares et al.

The Internet has led to a dramatic increase in the amount of available information. In this context, reading and understanding this flow of information have become costly tasks. In the last years, to assist people to understand textual data, various Natural Language Processing (NLP) applications based on Combinatorial Optimization have been devised. However, for Multi-Sentences Compression (MSC), method which reduces the sentence length without removing core information, the insertion of optimization methods requires further study to improve the performance of MSC. This article describes a method for MSC using Combinatorial Optimization and Graph Theory to generate more informative sentences while maintaining their grammaticality. An experiment led on a corpus of 40 clusters of sentences shows that our system has achieved a very good quality and is better than the state-of-the-art.

Iria da Cunha, Eric SanJuan, Juan-Manuel Torres-Moreno et al.

At present, automatic discourse analysis is a relevant research topic in the field of NLP. However, discourse is one of the phenomena most difficult to process. Although discourse parsers have been already developed for several languages, this tool does not exist for Catalan. In order to implement this kind of parser, the first step is to develop a discourse segmenter. In this article we present the first discourse segmenter for texts in Catalan. This segmenter is based on Rhetorical Structure Theory (RST) for Spanish, and uses lexical and syntactic information to translate rules valid for Spanish into rules for Catalan. We have evaluated the system by using a gold standard corpus including manually segmented texts and results are promising.

Juan-Manuel Torres-Moreno, Gerardo Sierra, Peter Peinl

Text similarity detection aims at measuring the degree of similarity between a pair of texts. Corpora available for text similarity detection are designed to evaluate the algorithms to assess the paraphrase level among documents. In this paper we present a textual German corpus for similarity detection. The purpose of this corpus is to automatically assess the similarity between a pair of texts and to evaluate different similarity measures, both for whole documents or for individual sentences. Therefore we have calculated several simple measures on our corpus based on a library of similarity functions.

Luis Adrián Cabrera-Diego, Stéphane Huet, Bassam Jabaian et al.

This year, the DEFT campaign (Défi Fouilles de Textes) incorporates a task which aims at identifying the session in which articles of previous TALN conferences were presented. We describe the three statistical systems developed at LIA/ADOC for this task. A fusion of these systems enables us to obtain interesting results (micro-precision score of 0.76 measured on the test corpus)

Xavier Bost, Ilaria Brunetti, Luis Adrián Cabrera-Diego et al.

The 2013 Défi de Fouille de Textes (DEFT) campaign is interested in two types of language analysis tasks, the document classification and the information extraction in the specialized domain of cuisine recipes. We present the systems that the LIA has used in DEFT 2013. Our systems show interesting results, even though the complexity of the proposed tasks.

Carlos-Emiliano González-Gallardo, Juan-Manuel Torres-Moreno, Azucena Montes Rendón et al.

In this paper we describe a dynamic normalization process applied to social network multilingual documents (Facebook and Twitter) to improve the performance of the Author profiling task for short texts. After the normalization process, $n$-grams of characters and n-grams of POS tags are obtained to extract all the possible stylistic information encoded in the documents (emoticons, character flooding, capital letters, references to other users, hyperlinks, hashtags, etc.). Experiments with SVM showed up to 90% of performance.

Elvys Linhares Pontes, Juan-Manuel Torres-Moreno, Andréa Carneiro Linhares

This paper aims to introduces a new algorithm for automatic speech-to-text summarization based on statistical divergences of probabilities and graphs. The input is a text from speech conversations with noise, and the output a compact text summary. Our results, on the pilot task CCCS Multiling 2015 French corpus are very encouraging

Gerardo Sierra, Juan-Manuel Torres-Moreno, Alejandro Molina

This article focuses on the description and evaluation of a new unsupervised learning method of clustering of definitions in Spanish according to their semantic. Textual Energy was used as a clustering measure, and we study an adaptation of the Precision and Recall to evaluate our method.

Mayeul Mathias, Assema Moussa, Fen Zhou et al.

This paper proposes a new method to provide personalized tour recommendation for museum visits. It combines an optimization of preference criteria of visitors with an automatic extraction of artwork importance from museum information based on Natural Language Processing using textual energy. This project includes researchers from computer and social sciences. Some results are obtained with numerical experiments. They show that our model clearly improves the satisfaction of the visitor who follows the proposed tour. This work foreshadows some interesting outcomes and applications about on-demand personalized visit of museums in a very near future.

Juan-Manuel Torres-Moreno, Javier Ramirez, Iria da Cunha

In this paper we present REG, a graph-based approach for study a fundamental problem of Natural Language Processing (NLP): the automatic text summarization. The algorithm maps a document as a graph, then it computes the weight of their sentences. We have applied this approach to summarize documents in three languages.

Juan-Manuel Torres-Moreno

This paper describes Artex, another algorithm for Automatic Text Summarization. In order to rank sentences, a simple inner product is calculated between each sentence, a document vector (text topic) and a lexical vector (vocabulary used by a sentence). Summaries are then generated by assembling the highest ranked sentences. No ruled-based linguistic post-processing is necessary in order to obtain summaries. Tests over several datasets (coming from Document Understanding Conferences (DUC), Text Analysis Conferences (TAC), evaluation campaigns, etc.) in French, English and Spanish have shown that summarizer achieves interesting results.

Juan-Manuel Torres-Moreno

In Automatic Text Summarization, preprocessing is an important phase to reduce the space of textual representation. Classically, stemming and lemmatization have been widely used for normalizing words. However, even using normalization on large texts, the curse of dimensionality can disturb the performance of summarizers. This paper describes a new method for normalization of words to further reduce the space of representation. We propose to reduce each word to its initial letters, as a form of Ultra-stemming. The results show that Ultra-stemming not only preserve the content of summaries produced by this representation, but often the performances of the systems can be dramatically improved. Summaries on trilingual corpora were evaluated automatically with Fresa. Results confirm an increase in the performance, regardless of summarizer system used.