Gwénolé Lecorvé
YOU?
Author Swipe
View article: Neural Models and Language Model Prompting for the Multidimensional Evaluation of Open-Ended Conversations
Neural Models and Language Model Prompting for the Multidimensional Evaluation of Open-Ended Conversations Open
The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1), w…
View article: Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations
Factual Knowledge in Language Models: Robustness and Anomalies under Simple Temporal Context Variations Open
This paper explores the robustness of language models (LMs) to variations in the temporal context within factual knowledge. It examines whether LMs can correctly associate a temporal context with a past fact valid over a defined period, by…
View article: Statistical Deficiency for Task Inclusion Estimation
Statistical Deficiency for Task Inclusion Estimation Open
International audience
View article: TelcoLM: collecting data, adapting, and benchmarking language models for the telecommunication domain
TelcoLM: collecting data, adapting, and benchmarking language models for the telecommunication domain Open
Despite outstanding processes in many tasks, Large Language Models (LLMs) still lack accuracy when dealing with highly technical domains. Especially, telecommunications (telco) is a particularly challenging domain due the large amount of l…
View article: Emotion Identification for French in Written Texts: Considering their Modes of Expression as a Step Towards Text Complexity Analysis
Emotion Identification for French in Written Texts: Considering their Modes of Expression as a Step Towards Text Complexity Analysis Open
The objective of this paper is to predict (A) whether a sentence in a written text expresses an emotion, (B) the mode(s) in which it is expressed, (C) whether it is basic or complex, and (D) its emotional category. One of our major contrib…
View article: Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation
Question Generation in Knowledge-Driven Dialog: Explainability and Evaluation Open
We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation. Inspired by previous work on planning-based summarisation, we present a model which instead of directly generating a que…
View article: WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models
WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models Open
The factuality of large language model (LLMs) tends to decay over time since events posterior to their training are "unknown" to them. One way to keep models up-to-date could be factual update: the task of inserting, replacing, or removing…
View article: WEBDial, a Multi-domain, Multitask Statistical Dialogue Framework with RDF
WEBDial, a Multi-domain, Multitask Statistical Dialogue Framework with RDF Open
Typically available dialogue frameworks have adopted a semantic representation based on dialogue-acts and slot-value pairs. Despite its simplicity, this representation has disadvantages such as the lack of expressivity, scalability and exp…
View article: KGConv, a Conversational Corpus grounded in Wikidata
KGConv, a Conversational Corpus grounded in Wikidata Open
We present KGConv, a large, conversational corpus of 71k conversations where each question-answer pair is grounded in a Wikidata fact. Conversations contain on average 8.6 questions and for each Wikidata fact, we provide multiple variants …
View article: Age Recommendation from Texts and Sentences for Children
Age Recommendation from Texts and Sentences for Children Open
Children have less text understanding capability than adults. Moreover, this capability differs among the children of different ages. Hence, automatically predicting a recommended age based on texts or sentences would be a great benefit to…
View article: CoQAR: Question Rewriting on CoQA
CoQAR: Question Rewriting on CoQA Open
Questions asked by humans during a conversation often contain contextual dependencies, i.e., explicit or implicit references to previous dialogue turns. These dependencies take the form of coreferences (e.g., via pronoun use) or ellipses, …
View article: BreizhCorpus: A Large Breton Language Speech Corpus and Its Use for Text-to-Speech Synthesis
BreizhCorpus: A Large Breton Language Speech Corpus and Its Use for Text-to-Speech Synthesis Open
International audience
View article: TREMoLo-Tweets: a Multi-Label Corpus of French Tweets for Language Register Characterization
TREMoLo-Tweets: a Multi-Label Corpus of French Tweets for Language Register Characterization Open
International audience
View article: TREMoLo-Tweets: a Multi-Label Corpus of French Tweets for Language Register Characterization
TREMoLo-Tweets: a Multi-Label Corpus of French Tweets for Language Register Characterization Open
The casual, neutral, and formal language registers are highly perceptible in discourse productions.However, they are still poorly studied in Natural Language Processing (NLP), especially outside English, and for new textual types like twee…
View article: Style versus Content: A distinction without a (learnable) difference?
Style versus Content: A distinction without a (learnable) difference? Open
International audience
View article: Age Recommendation for Texts
Age Recommendation for Texts Open
International audience
View article: Style versus Content: A distinction without a (learnable) difference?
Style versus Content: A distinction without a (learnable) difference? Open
Textual style transfer involves modifying the style of a text while preserving its content. This assumes that it is possible to separate style from content. This paper investigates whether this separation is possible. We use sentiment tran…
View article: Mama/Papa, Is this Text for Me?
Mama/Papa, Is this Text for Me? Open
International audience
View article: Can We Generate Emotional Pronunciations for Expressive Speech Synthesis?
Can We Generate Emotional Pronunciations for Expressive Speech Synthesis? Open
International audience
View article: Make text look like speech: disfluency generation using sequence-to-sequence neural networks
Make text look like speech: disfluency generation using sequence-to-sequence neural networks Open
The synthesis of spontaneous natural speech is a challenge. One way to approach it is to introduce disfluencies since the latter are very present in spontaneous speech. Recently, work has proposed a method to generate disfluencies using la…
View article: Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis
Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis Open
International audience
View article: The IRISA Text-To-Speech System for the Blizzard Challenge 2017
The IRISA Text-To-Speech System for the Blizzard Challenge 2017 Open
International audience
View article: The IRISA Text-To-Speech System for the Blizzard Challenge 2017
The IRISA Text-To-Speech System for the Blizzard Challenge 2017 Open
International audience