Suchergebnisse

International audience ; Emotion analysis in polarized contexts represents a challenge for Natural Language Processing modeling. As a step in the aforementioned direction, we present a methodology to extend the task of Aspect-based Sentiment Analysis (ABSA) toward the affect and emotion representation in polarized settings. In particular, we adopt the three-dimensional model of affect based on Valence, Arousal, and Dominance (VAD). We then present a Brexit scenario that proves how affect varies toward the same aspect when politically polarized stances are presented. Our approach captures aspect-based polarization from newspapers regarding the Brexit scenario of 1.2m entities at sentence-level. We demonstrate how basic constituents of emotions can be mapped to the VAD model, along with their interactions respecting the polarized context in ABSA settings using biased key-concepts (e.g., "stop Brexit" vs. "support Brexit"). Quite intriguingly, the framework achieves to produce coherent aspect evidences of Brexit's stance from key-concepts, showing that VAD influence the support and opposition aspects.

International audience ; Emotion analysis in polarized contexts represents a challenge for Natural Language Processing modeling. As a step in the aforementioned direction, we present a methodology to extend the task of Aspect-based Sentiment Analysis (ABSA) toward the affect and emotion representation in polarized settings. In particular, we adopt the three-dimensional model of affect based on Valence, Arousal, and Dominance (VAD). We then present a Brexit scenario that proves how affect varies toward the same aspect when politically polarized stances are presented. Our approach captures aspect-based polarization from newspapers regarding the Brexit scenario of 1.2m entities at sentence-level. We demonstrate how basic constituents of emotions can be mapped to the VAD model, along with their interactions respecting the polarized context in ABSA settings using biased key-concepts (e.g., "stop Brexit" vs. "support Brexit"). Quite intriguingly, the framework achieves to produce coherent aspect evidences of Brexit's stance from key-concepts, showing that VAD influence the support and opposition aspects.

International audience ; Emotion analysis in polarized contexts represents a challenge for Natural Language Processing modeling. As a step in the aforementioned direction, we present a methodology to extend the task of Aspect-based Sentiment Analysis (ABSA) toward the affect and emotion representation in polarized settings. In particular, we adopt the three-dimensional model of affect based on Valence, Arousal, and Dominance (VAD). We then present a Brexit scenario that proves how affect varies toward the same aspect when politically polarized stances are presented. Our approach captures aspect-based polarization from newspapers regarding the Brexit scenario of 1.2m entities at sentence-level. We demonstrate how basic constituents of emotions can be mapped to the VAD model, along with their interactions respecting the polarized context in ABSA settings using biased key-concepts (e.g., "stop Brexit" vs. "support Brexit"). Quite intriguingly, the framework achieves to produce coherent aspect evidences of Brexit's stance from key-concepts, showing that VAD influence the support and opposition aspects.

International audience ; In this presentation, we have three key claims. First, we wish to make a case for an alternative conception of linguistic diversity, which sees language pluralism not as an "obstacle" or "barrier" that needs to be (dis)solved, but rather as a value that needs to be cherished and promoted, at different levels of politics and society. Second, we also hold that the "Digital Humanities" create new possibilities and thus open a "new age" for literary translation, which will also deeply impact research and education [Lacour, P. et alii (2010a)]. Third, as we should argue, the application of interpretive and corpus-driven linguistics to Computer Assisted Translation should foster collaboration on the realm of precise translation of cultural texts [Bénel, A. and Lacour, P. (2011)] and therefore help reinforcing the sustainability of culture(s) and identity(ies), "on" and "off" line. Behind these claims, lies a conception of "language as a common good" which can (or should) be freely disposed by all its users. This paper aims consequently at proposing a more appropriate definition of the copyright for digital literary translation, especially for multilingual corpora.

International audience ; In this presentation, we have three key claims. First, we wish to make a case for an alternative conception of linguistic diversity, which sees language pluralism not as an "obstacle" or "barrier" that needs to be (dis)solved, but rather as a value that needs to be cherished and promoted, at different levels of politics and society. Second, we also hold that the "Digital Humanities" create new possibilities and thus open a "new age" for literary translation, which will also deeply impact research and education [Lacour, P. et alii (2010a)]. Third, as we should argue, the application of interpretive and corpus-driven linguistics to Computer Assisted Translation should foster collaboration on the realm of precise translation of cultural texts [Bénel, A. and Lacour, P. (2011)] and therefore help reinforcing the sustainability of culture(s) and identity(ies), "on" and "off" line. Behind these claims, lies a conception of "language as a common good" which can (or should) be freely disposed by all its users. This paper aims consequently at proposing a more appropriate definition of the copyright for digital literary translation, especially for multilingual corpora.

International audience ; In this presentation, we have three key claims. First, we wish to make a case for an alternative conception of linguistic diversity, which sees language pluralism not as an "obstacle" or "barrier" that needs to be (dis)solved, but rather as a value that needs to be cherished and promoted, at different levels of politics and society. Second, we also hold that the "Digital Humanities" create new possibilities and thus open a "new age" for literary translation, which will also deeply impact research and education [Lacour, P. et alii (2010a)]. Third, as we should argue, the application of interpretive and corpus-driven linguistics to Computer Assisted Translation should foster collaboration on the realm of precise translation of cultural texts [Bénel, A. and Lacour, P. (2011)] and therefore help reinforcing the sustainability of culture(s) and identity(ies), "on" and "off" line. Behind these claims, lies a conception of "language as a common good" which can (or should) be freely disposed by all its users. This paper aims consequently at proposing a more appropriate definition of the copyright for digital literary translation, especially for multilingual corpora.

International audience ; When two people engage in a conversation, knowingly or unknowingly, they are playing a game. Players of such games have diverse objectives, or winning conditions: an applicant trying to convince her potential employer of her eligibility over that of a competitor, a prosecutor trying to convict a defendant, a politician trying to convince an electorate in a political debate, and so on. We argue that infinitary games offer a natural model for many structural characteristics of such conversations. We call such games message exchange games, and we compare them to existing game theoretic frameworks used in linguistics—for example, signaling games—and show that message exchange games are needed to handle non-cooperative conversation. In this paper, we concentrate on conversational games where players' interests are opposed. We provide a taxonomy of conversations based on their winning conditions, and we investigate some essential features of winning conditions like consistency and what we call rhetorical cooperativity. We show that these features make our games decomposition sensitive, a property we define formally in the paper. We show that this property has far-reaching implications for the existence of winning strategies and their complexity. There is a class of winning conditions (decomposition invariant winning conditions) for which message exchange games are equivalent to Banach- Mazur games, which have been extensively studied and enjoy nice topological results. But decomposition sensitive goals are much more the norm and much more interesting linguistically and philosophically.

International audience ; When two people engage in a conversation, knowingly or unknowingly, they are playing a game. Players of such games have diverse objectives, or winning conditions: an applicant trying to convince her potential employer of her eligibility over that of a competitor, a prosecutor trying to convict a defendant, a politician trying to convince an electorate in a political debate, and so on. We argue that infinitary games offer a natural model for many structural characteristics of such conversations. We call such games message exchange games, and we compare them to existing game theoretic frameworks used in linguistics—for example, signaling games—and show that message exchange games are needed to handle non-cooperative conversation. In this paper, we concentrate on conversational games where players' interests are opposed. We provide a taxonomy of conversations based on their winning conditions, and we investigate some essential features of winning conditions like consistency and what we call rhetorical cooperativity. We show that these features make our games decomposition sensitive, a property we define formally in the paper. We show that this property has far-reaching implications for the existence of winning strategies and their complexity. There is a class of winning conditions (decomposition invariant winning conditions) for which message exchange games are equivalent to Banach- Mazur games, which have been extensively studied and enjoy nice topological results. But decomposition sensitive goals are much more the norm and much more interesting linguistically and philosophically.

International audience ; The need for linguistic resources in any natural language application is undeniable. Lexicons and terminologies play indeed a central role in any machine translation tool, regardless of the theoretical foundations upon which the machine translation tool is based (e.g. statistical machine translation or rule-based machine translation). The EU project TTC (''Terminology Extraction, Translation Tools and Comparable Corpora'') aims at leveraging machine translation tools, computer-assisted translation tools, and terminology management tools by automatically generating bilingual terminologies from comparable corpora in several European Union languages (English, French, German, Latvian and Spanish), as well as in Chinese and Russian. The TTC project will integrate developed and existing tools in an online platform including a tool to compile and handle comparable corpora, as well as a terminology management tool. The platform will be based on Web Services and will use reputable open solutions such as UIMA (Unstructured Information Management Architecture) and EuroTermBank.The need for linguistic resources in any natural language application is undeniable. Lexicons and terminologies play indeed a central role in any machine translation tool, regardless of the theoretical foundations upon which the machine translation tool is based (e.g. statistical machine translation or rule-based machine translation). The EU project TTC (''Terminology Extraction, Translation Tools and Comparable Corpora'') aims at leveraging machine translation tools, computer-assisted translation tools, and terminology management tools by automatically generating bilingual terminologies from comparable corpora in several European Union languages (English, French, German, Latvian and Spanish), as well as in Chinese and Russian. The TTC project will integrate developed and existing tools in an online platform including a tool to compile and handle comparable corpora, as well as a terminology management tool. The platform will ...

National audience ; Nous comparons les distributions de mots dans les communiqués de presse politiques récents. Nous proposons une méthodologie pour objectiver des associations entre notions participant au débat politique. Nous montrons comment les modèles de langage probabilistes peuvent révéler les concepts sous-jacents en tant qu'associations fortes à plusieurs termes pour aider à clarifier le débat politique, notamment pour la surveillance des médias sociaux. Cette approche tente de modéliser les termes du débat comme des distributions de probabilités d'apparition des mots.

National audience ; L'influence sociale est un phénomène important dans divers domaines, tels que l'économie et la politique, qui a gagné en résonnance avec la popularité des médias sociaux, notamment les réseaux sociaux et les forums. La majorité des travaux sur ce sujet propose des approches fondées sur des théories en sciences humaines (sociologie, linguistique), et des techniques d'analyse de réseau (mesures de propagation et de centralité) ou de TAL. Dans cet article, nous présentons un modèle d'influence inspiré de travaux en psychologie sociale, sur lequel nous construisons un système combinant un module de TAL pour détecter les messages reflétant les processus d'influence, associé à une analyse par centralité de la transmission de ces messages. Nos expériences sur le forum de débats Change My View montrent que l'approche par hybridation, comparée à la centralité seule, aide à mieux détecter les influenceurs.

National audience ; L'influence sociale est un phénomène important dans divers domaines, tels que l'économie et la politique, qui a gagné en résonnance avec la popularité des médias sociaux, notamment les réseaux sociaux et les forums. La majorité des travaux sur ce sujet propose des approches fondées sur des théories en sciences humaines (sociologie, linguistique), et des techniques d'analyse de réseau (mesures de propagation et de centralité) ou de TAL. Dans cet article, nous présentons un modèle d'influence inspiré de travaux en psychologie sociale, sur lequel nous construisons un système combinant un module de TAL pour détecter les messages reflétant les processus d'influence, associé à une analyse par centralité de la transmission de ces messages. Nos expériences sur le forum de débats Change My View montrent que l'approche par hybridation, comparée à la centralité seule, aide à mieux détecter les influenceurs.

National audience ; Nous comparons les distributions de mots dans les communiqués de presse politiques récents. Nous proposons une méthodologie pour objectiver des associations entre notions participant au débat politique. Nous montrons comment les modèles de langage probabilistes peuvent révéler les concepts sous-jacents en tant qu'associations fortes à plusieurs termes pour aider à clarifier le débat politique, notamment pour la surveillance des médias sociaux. Cette approche tente de modéliser les termes du débat comme des distributions de probabilités d'apparition des mots.

National audience ; L'influence sociale est un phénomène important dans divers domaines, tels que l'économie et la politique, qui a gagné en résonnance avec la popularité des médias sociaux, notamment les réseaux sociaux et les forums. La majorité des travaux sur ce sujet propose des approches fondées sur des théories en sciences humaines (sociologie, linguistique), et des techniques d'analyse de réseau (mesures de propagation et de centralité) ou de TAL. Dans cet article, nous présentons un modèle d'influence inspiré de travaux en psychologie sociale, sur lequel nous construisons un système combinant un module de TAL pour détecter les messages reflétant les processus d'influence, associé à une analyse par centralité de la transmission de ces messages. Nos expériences sur le forum de débats Change My View montrent que l'approche par hybridation, comparée à la centralité seule, aide à mieux détecter les influenceurs.

En analyse de discours (AD), la nomination désigne la recatégorisation du référent par le locuteur à travers l'usage d'un nouveau nom ou d'un nom modifié. Parfois utilisé pour influencer l'autre sur sa vision de voir le monde, ce phénomène sert d'indice sur l'idéologie du locuteur voire, en contexte adéquat, sur son affiliation politique. L'AD ne dispose pas à ce jour d'outils en mesure d'appréhender efficacement ce qui relève ou non de l'idéologie ou d'une visée argumentative face à une simple réutilisation de mots dont le sens est déjà consensuel. Dans le cadre d'une thèse entre AD et TAL, nous nous intéressons à l'exploitation de modèles distributionnels pour repérer de manière automatique ces variations de sens en discours dans un corpus d'interviews politiques. Dans cet article, nous nous interrogeons sur l'impact de leurs paramètres d'entraînement pour de la désambiguïsation lexicale et explorons une méthode de représentation de la variation sémantique interdiscursive.