Search Results for author:
Found 41 papers, 3 papers with code
Filtering conversations through dialogue acts labels for improving corpus-based convergence studies
Cognitive models of conversation and research on user-adaptation in dialogue systems involves a better understanding of speakers convergence in conversation.
Zero-Shot Aspect-Based Scientific Document Summarization using Self-Supervised Pre-training
We study the zero-shot setting for the aspect-based scientific document summarization task.
Development of Multi-level Linguistic Alignment in Child-adult Conversations
Interactive alignment is a major mechanism of linguistic coordination.
Abstraction ou hallucination ? État des lieux et évaluation du risque pour les modèles de génération de résumés automatiques de type séquence-à-séquence (Abstraction or Hallucination ? Status and Risk assessment for sequence-to-sequence Automatic)
La génération de texte a récemment connu un très fort intérêt au vu des avancées notables dans le domaine des modèles de langage neuronaux.
Using ASR-Generated Text for Spoken Language Modeling
This papers aims at improving spoken language modeling (LM) using very large amount of automatically transcribed speech.
Transferring Modern Named Entity Recognition to the Historical Domain: How to Take the Step?
Named entity recognition is of high interest to digital humanities, in particular when mining historical documents.
Simulation d’erreurs d’OCR dans les systèmes de TAL pour le traitement de données anachroniques (Simulation of OCR errors in NLP systems for processing anachronistic data)
Du fait d’un manque de ressources historiques dédiées au TAL, le traitement de ce domaine reste dépendant de l’utilisation de ressources contemporaines.
“Do you follow me?”: A Survey of Recent Approaches in Dialogue State Tracking
DST has received a lot of interest in recent years with the text-to-text paradigm emerging as the favored approach.
Increasing faithfulness in human-human dialog summarization with Spoken Language Understanding tasks
We suggest using the semantic information proposed for performing Spoken Language Understanding (SLU) in human-machine dialogue systems for goal-oriented human-human dialogues to obtain a more semantically faithful summary regarding the task.
Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?
Recent advances in vision-and-language modeling have seen the development of Transformer architectures that achieve remarkable performance on multimodal reasoning tasks.
"Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking
DST has received a lot of interest in recent years with the text-to-text paradigm emerging as the favored approach.
ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks
We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech.
Zero-Shot and Few-Shot Classification of Biomedical Articles in Context of the COVID-19 Pandemic
MeSH (Medical Subject Headings) is a large thesaurus created by the National Library of Medicine and used for fine-grained indexing of publications in the biomedical domain.
Robust Semantic Parsing with Adversarial Learning for Domain Generalization
This paper addresses the issue of generalization for Semantic Parsing in an adversarial framework.
Typological Features for Multilingual Delexicalised Dependency Parsing
The existence of universal models to describe the syntax of languages has been debated for decades.
Veyn at PARSEME Shared Task 2018: Recurrent Neural Networks for VMWE Identification
This paper describes the Veyn system, submitted to the closed track of the PARSEME Shared Task 2018 on automatic identification of verbal multiword expressions (VMWEs).
Evaluation automatique de la satisfaction client \`a partir de conversations de type ``chat'' par r\'eseaux de neurones r\'ecurrents avec m\'ecanisme d'attention (Customer satisfaction prediction with attention-based RNNs from a chat contact center corpus)
Cet article pr{\'e}sente des m{\'e}thodes permettant l{'}{\'e}valuation de la satisfaction client {\`a} partir de tr{\`e}s vastes corpus de conversation de type {``}chat{''} entre des clients et des op{\'e}rateurs.
D\'etection d'erreurs dans des transcriptions OCR de documents historiques par r\'eseaux de neurones r\'ecurrents multi-niveau (Combining character level and word level RNNs for post-OCR error detection)
Le traitement {\`a} posteriori de transcriptions OCR cherche {\`a} d{\'e}tecter les erreurs dans les sorties d{'}OCR pour tenter de les corriger, deux t{\^a}ches {\'e}valu{\'e}es par la comp{\'e}tition ICDAR-2017 Post-OCR Text Correction.
Evaluation of word embeddings against cognitive processes: primed reaction times in lexical decision and naming tasks
This work presents a framework for word similarity evaluation grounded on cognitive sciences experimental data.
Correcting prepositional phrase attachments using multimodal corpora
PP-attachments are an important source of errors in parsing natural language.
Apprentissage d'agents conversationnels pour la gestion de relations clients (Training chatbots for customer relation management)
Ce travail d{\'e}montre la faisabilit{\'e} d{'}entra{\^\i}ner des chatbots sur des traces de conversations dans le domaine de la relation client.
D\'etection de cor\'ef\'erences de bout en bout en fran\ccais (End-to-end coreference resolution for French)
Notre objectif est l{'}{\'e}laboration d{'}un syst{\`e}me de d{\'e}tection automatique de relations de cor{\'e}f{\'e}rence le plus g{\'e}n{\'e}ral possible, pour le traitement des anaphores pronominales et les cor{\'e}f{\'e}rences directes.
MultiLing 2017 Overview
In this brief report we present an overview of the MultiLing 2017 effort and workshop, as implemented within EACL 2017.
Building a robust sentiment lexicon with (almost) no resource
Creating sentiment polarity lexicons is labor intensive.
Fusion d'espaces de repr\'esentations multimodaux pour la reconnaissance du r\^ole du locuteur dans des documents t\'el\'evisuels (Multimodal embedding fusion for robust speaker role recognition in video broadcast )
L{'}identification du r{\^o}le d{'}un locuteur dans des {\'e}missions de t{\'e}l{\'e}vision est un probl{\`e}me de classification de personne selon une liste de r{\^o}les comme pr{\'e}sentateur, journaliste, invit{\'e}, etc.
D\'etection de concepts pertinents pour le r\'esum\'e automatique de conversations par recombinaison de patrons (Relevant concepts detection for the automatic summary of conversations using patterns recombination )
automatique de conversations par recombinaison de patrons J{\'e}r{\'e}my Trione Benoit Favre Fr{\'e}d{\'e}ric B{\'e}chet Aix-Marseille Universit{\'e}, CNRS, LIF UMR 7279, 13000, Marseille, France pr{\'e}nom. nom@lif. univ-mrs. fr R {\'E}SUM{\'E} Ce papier d{\'e}crit une approche pour cr{\'e}er des r{\'e}sum{\'e}s de conversations parl{\'e}es par remplissage de patrons.
Word Embedding Evaluation and Combination
Different approaches have been introduced to calculate word embeddings through neural networks.
Summarizing Behaviours: An Experiment on the Annotation of Call-Centre Conversations
Annotating and predicting behavioural aspects in conversations is becoming critical in the conversational analytics industry.
A Document Repository for Social Media and Speech Conversations
We present a successfully implemented document repository REST service for flexible SCRUD (search, crate, read, update, delete) storage of social media conversations, using a GATE/TIPSTER-like document object model and providing a query language for document features.
A Repository of State of the Art and Competitive Baseline Summaries for Generic News Summarization
In the period since 2004, many novel sophisticated approaches for generic multi-document summarization have been developed.
Automatically enriching spoken corpora with syntactic information for linguistic studies
Syntactic parsing of speech transcriptions faces the problem of the presence of disfluencies that break the syntactic structure of the utterances.
Syntactic annotation of spontaneous speech: application to call-center conversation data
This paper describes the syntactic annotation process of the DECODA corpus.
Leveraging study of robustness and portability of spoken language understanding systems across languages and domains: the PORTMEDIA corpora
The PORTMEDIA project is intended to develop new corpora for the evaluation of spoken language understanding systems.
