2025
DivMerge: A divergence-based model merging method for multi-tasking, B. Touayouch, L. Fosse, G. Damnati, G. Lecorvé, https://arxiv.org/abs/2509.02108v1, Sep. 2025.
Statistical Deficiency for Task Inclusion Estimation , L. Fosse, F. Bechet, B. Favre, G. Damnati, G. Lecorvé, M. Darrin, P. Formont, P. Piantanida, ACL'25, Vienna, Austria, 2025.
2024
TelcoLM: collecting data, adapting, and benchmarking language models for the telecommunication domain, C. Barboule, V-P Huyn, A. Bufort, Y. Chabot, G. Damnati, G. Lecorvé, https://arxiv.org/abs/2412.15891, Dec 2024.
A linguistically-motivated evaluation methodology for unraveling model's abilities in reading comprehension tasks , E. Antoine, F. Bechet, G. Damnati, P. Langlais, EMNLP'24, Miami, USA, 2024.
Extrinsic evaluation of question generation methods with user journey logs, E. Antoine, E. Besnehard, F. Béchet, G. Damnati, E. Kergosien, A. Laborderie, Workshop on Human Evaluation of NLP Systems (HumEval)@ LREC-COLING 2024, Turin, Italy, 2024.
2023
Team Darbarer @ AutoMin2023: Transcription simplification for concise minute generation from multi-party conversations, I. Rousseau, L. Fosse, Y. Dkhissi, G. Damnati, G. Lecorvé, GenChal, INLG, Prague, Czech Republic, 2023.
Exploring Social Sciences Archives with Explainable Document Linkage through Question Generation, E. Antoine, H. J. Kang, I. Rousseau, G. Azémard, F. Bechet and G. Damnati , EACL workshop, LaTeCH-CLfL, Dubrovnik, Croatia, 2023.
Abstract Representation for Multi-Intent Spoken Language Understanding, R. Abrougui, G. Damnati, J. Heinecke, F. Béchet, ICASSP'23, Rhodes, Greece, 2023.
2022
Question Generation and Answering for exploring Digital Humanities collections, F. Béchet, E. Antoine, J. Auguste , G. Damnati, LREC'22, Marseille, France, 2022.
CALOR-DIAL: a corpus for Conversational Question Answering on French encyclopedic documents, F. Bechet, L. Robert, L. Rojas-Barahona, G. Damnati, CIRCLE'22, Samatan, France, 2022.
2021
SpanAlign: Efficient Span Annotation Projection into Translated Data for Sequence Tagging as applied to Cross-Lingual Opinion Mining, L. Jacqmin, G.Marzinotto, J. Gromada, E. Szcekocka, R. Kolodynski, G. Damnati, EMNLP Workshop on Noisy User Generated Text (WNUT21), Dominican Republic, 2021.
Can we predict how challenging Spoken Language Understanding corpora are across sources, languages and domains?, Frederic Bechet, Christian Raymond, Achraf Hamane, Rim Abrougui, Gabriel Marzinotto and Géraldine Damnati, International Workshop on Spoken Dialogue System Technology (IWSDS 2021), Singapore, 2021.
2020
Cross-lingual and cross-domain evaluation of Machine Reading Comprehension with Squad and CALOR-Quest corpora , D. Charlet, G. Damnati, F. Béchet, G. Marzinotto, J. Heinecke, LREC, France, 2020.
A Multimodal Educational Corpus of Oral Courses: Annotation, Analysis and Case Study , S. Mdhaffar, Y. Estève, A. Laurent, N. Hernandez, R. Dufour, D. Charlet, G. Damnati, S. Quiniou, N. Camelin, LREC, France, 2020.
2019
CALOR-QUEST: generating a training corpus for Machine Reading Comprehension models from shallow semantic annotations, F. Béchet, C. Aloui, D. Charlet, G. Damnati, J. Heinecke, A. Nasr, F. Herlédan, Machine Reading Question Answering workshop, MRQAW@EMNLP 2019, Hong-Kong, 2019.
Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning, G. Marzinotto, G. Damnati, F. Béchet, Interspeech 2019, Austria, 2019.
MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging, G. Marzinotto, J. Heinecke, G. Damnati, SemEval@NAACL-HLT 2019, USA, 2019.
The Impact of Word Representations on Sequential Neural MWE Identification, N. Zampieri, C. Ramish, G. Damnati, Multi-Word Expression workshop, MWE-WN@ACL 2019, Italy, 2019.
Robust Semantic Parsing with Adversarial Learning for Domain Generalization, G. Marzinotto, F. Béchet, G. Damnati, B. Favre, NAACL, Industrial Track, USA, 2019.
Can we predict self-reported customer satisfaction from interactions? J. Auguste, D. Charlet, G. Damnati, F. Bechet, B. Favre, IEEE ICASSP, UK, 2019.
Skip Act Vectors: integrating dialogue context into sentence embeddings, J. Auguste, F. Bechet, G. Damnati, D. Charlet, IWSDS workshop, Italy, 2019.
2018
Sources of Complexity in Semantic Frame Parsing for Information Extraction, G. Marzinotto, F. Béchet, G. Damnati, A. Nasr, The International FrameNet Workshop 2018: Multilingual FrameNets and Constructicons, collocated with LREC, Japan, 2018.
Linking written News and TV Broadcast News topic segments with semantic textual similarity, D. Charlet, G. Damnati, Natural Language Meets Journalism III workshop, collocated with LREC, Japan, 2018.
Semantic Frame Parsing for Information Extraction : the CALOR corpus, G. Marzinotto, J. Auguste, F. Béchet, G. Damnati, A. Nasr, LREC'18, Japan, 2018.
Handling Normalization Issues for Part-of-Speech Tagging of Online Conversational Text, GDamnati, J. Auguste, A. Nasr, D.Charlet, J. Heinecke, F. Béchet, LREC'18, Japan, 2018.
FrNewsLink : a corpus linking TV Broadcast News Segments and Press Articles, N. Camelin, G. Damnati, A. Bouchekif, A. Landeau,D. Charlet, Y. Estève, LREC'18, Japan, 2018.
2017
SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering, D. Charlet, G. Damnati, 11th International Workshop on Semantic Evaluation (SemEval 2017). Canada, 2017.
Evaluating Automatic Topic Segmentation as a Segment Retrieval Task, A. Bouchekif, D. Charlet, G. Damnati, N. Camelin, Y. Estève, Interspeech’17, Sweden, 2017.
2016
Exploring collections of multimedia archives through innovative interfaces in the context of Digital Humanities, G. Damnati, D. Charlet, M. Denjean, Show and Tell Interspeech'16, USA, 2016.
Syntactic parsing of chat language in contact center conversation corpus, A. Nasr, G. Damnati, A. Guerraz,F. Béchet, SigDial'16, USA, 2016.
Web Chat Conversations from Contact Centers: a Descriptive Study, G. Damnati, A. Guerraz, D. Charlet, LREC'16, Slovenia, 2016.
Title Assignment for Automatic Topic Segments in TV Broadcast News, A. Bouchekif, G. Damnati, D. Charlet, N. Camelin,Y. Estève,ICASSP’16, China, 2016.
2015
Diachronic Semantic Cohesion for Topic Segmentation of TV Broadcast News, A. Bouchekif, G. Damnati, Y. Estève, D. Charlet, N. Camelin,Interspeech’15, Germany, 2015.
News Talk-Show Chaptering with Journalistic Genres, D. Charlet, G. Damnati, J. Trione, Interspeech’15, Germany, 2015.
PERCOLATTE : a multimodal person discovery system in TV broadcast for the Medieval 2015 evaluation campaign, M. Bendris, D. Charlet, B. Favre, G. Senay, M.Y. Kim, M. Rouvier, G. Damnati, F. Béchet, MediaEval workshop, Person Discovery in TV, Germany, 2015.
Fusion of speaker and lexical information for topic segmentation: A co-segmentation approach, D. Charlet, G. Damnati, A. Bouchekif, A. Douib, ICASSP'15, Australia, 2015.
2014
Speech cohesion for topic segmentation of spoken content, A. Bouchekif, G. Damnati, D. Charlet, Interspeech’14, Singapore, 2014.
Multimodal understanding for person recognition in video bradcasts, F. Bechet, M. Bendris, D. Charlet, G. Damnati, B. Favre, M. Rouvier, R. Auguste, B. Bigot, R. Dufour, C. Fredouille, G. Linares, J. Martinet, G. Senay, P. Tirilly, Interspeech'14, Singapore, 2014.
Person Name Recognition and Linking from Overlay Text in TV Broadcast Shows, G. Damnati, B. Favre, F. Béchet, D. Charlet, SLAM'14, Malaysia, 2014.
Intra-content term weighting for topic segmentation, A. Bouchekif, G. Damnati, D. Charlet, ICASSP'14, Italy, 2014.
Unsupervised Face Identification in TV Content using Audio-Visual Sources, M. Rouvier, B. Favre, M. Bendris, D. Charlet, G. Damnati, CBMI’14, Austria, 2014.
2013
Improving speaker identification of TV-shows using person name detection in overlaid text and speech, D. Charlet, C. Fredouille, G. Damnati, G. Senay, Interspeech’13, France, 2013.
PERCOLI: a person identification system for the 2013 REPERE challenge, B. Favre, G. Damnati, F. Béchet, M. Bendris, D. Charlet, R. Auguste, S. Ayache, B. Bigot, A. Delteil, R. Dufour, C. Fredouille, G. Linares, J. Martinet, G. Senay, P. Tirilly, SLAM’13, France, 2013.
Complementarity of lexical cohesion and speaker role information for story segmentation of french TV broadcast news, A. Bouchekif, G. Damnati, D. Charlet, SLSP’13, Spain, 2013.
Unsupervised Face Identification in TV Content using Audio-Visual Sources, M. Bendris, B. Favre, D. Charlet, G. Damnati, R. Auguste, J. Martinet, G. Senay, CBMI’13, Hungary, 2013.
2012
A speaker-role based approach for detecting politicians in TV Broadcast News, D. Charlet, G. Damnati, Interspeech’12, USA, 2012.
Automatic transcription error recovery for Person Name Recognition, R. Dufour, G. Damnati, D. Charlet, F. Béchet, Interspeech’12, USA, 2012.
Detecting politician speech in TV Broadcast News shows, D. Charlet, G. Damnati, CBMI’12, France, 2012.
Automatic error region detection and characterization in LVCSR transcriptions of TV news shows, R. Dufour, G. Damnati, D. Charlet, ICASSP’12, Japan, 2012.
Detecting person presence in TV shows with linguistic and structural features, F. Béchet, B. Favre,G. Damnati, ICASSP’12, Japan, 2012.
2011
Applying Multiclass Bandit algorithms to call-type classification, L. Ralaivola, B. Favre, P. Gotab, F. Béchet, G. Damnati, IEEE Workshop on ASRU, Hawaï, 2011.
Multi-view approach for speaker turn role labeling in TV Broadcast News shows, G. Damnati, D. Charlet, Interspeech'11, Italie, 2011.
Robust speaker turn role labelling of TV Broadcast News shows, G. Damnati, D. Charlet, ICASSP'11, République Tchèque, 2011.
2010
Online SLU Model Adaptation with a Partial Oracle, P. Gotab, G. Damnati, F. Béchet, L. Delphin-Poulat, Interspeech'10, Japon, 2010.
Detection and Interpretation of Opinion Expressions in Spoken Surveys, N. Camelin, F. Béchet, G. Damnati, R. de Mori, IEEE Transactions on Audio, Speech, and Language Processing, Volume 18, N° 2, February 2010, Pages 369-381.
2009
Active Learning for rule-based and corpus-based Spoken Language Understanding models, P. Gotab, F. Béchet, G. Damnati, IEEE Workshop on ASRU, Italy, 2009.
Towards Intonation Control in Unit Selection Speech Synthesis, C. Boidin, O. Boeffard, T. Moudenc, G. Damnati, Interspeech'09Angleterre, 2009
Error correction of proportions in spoken opinion surveys, N.Camelin, R. De Mori F. Béchet, . Damnati, Interspeech'09, Angleterre, 2009.
2008
Speaker turn characterization for spoken dialog system monitoring and adaptation, G. Damnati, F. Béchet, R. De Mori, SLT'08 - Spoken Language Technology Workshop, Inde, 2008.
Automatic customer feedback processing: alarm detection in open question spoken messages, N.Camelin, G. Damnati, F. Béchet, R. De Mori, Interspeech'08, Australie, 2008.
Normalizing SMS: are two metaphors better than one ?, C. Kobus, F. Yvon, G. Damnati, COLING'08, Grande Bretagne, 2008.
First implementation of the LUNA Spoken Language Understanding strategy on a telephone service application, G. Damnati, F. Béchet, R. de Mori, SLUDS'08, IIS Workshop on Spoken Language Understanding and Dialogue Systems, Pologne, 2008.
2007
Conditional use of Word Lattices, Confusion Networks and 1-best string hypotheses in a Sequential Interpretation Strategy, B. Minescu, G. Damnati, F. Béchet, R. De Mori, Interspeech'07, Belgique, 2007.
Approaches for adaptive database reduction for Text-To-Speech synthesis, A. Krul, G. Damnati, F. Yvon, C. Boidin, T. Moudenc, Interspeech'07, Belgique, 2007.
Speech Mining in Noisy Audio Message Corpus, N.Camelin, F. Béchet, G. Damnati, R. De Mori, Interspeech'07, Belgique, 2007.
Experiments on the France Telecom 3000 Voice Agency corpus: academic research on an industrial spoken dialog system, G. Damnati, F. Béchet, R. de Mori, HLT-NAACL'07, Workshop on Bridging the Gap: Academic and Industrial Research in Dialog Technologies, USA, 2007.
Spoken Language Understanding strategies on the France Telecom 3000 Voice Agency corpus, G. Damnati, F. Béchet, R. de Mori, ICASSP'07, Hawaï, 2007.
Sequential Decision Strategies for Machine Interpretation of Speech, C. Raymond, F. Béchet, N. Camelin, R. de Mori, G. Damnati, IEEE Transactions on Audio, Speech, and Language Processing, Volume 15, N° 1, January 2007, Pages 162-171.
2006
Spoken opinion extraction for detecting variations in user satisfaction, F. Béchet, G. Damnati, N. Camelin, R. de Mori, SLT'06 - Spoken Language Technology Workshop, Aruba, 2006.
Exploiting semantic relations for a Spoken Language Understanding application, C. Kobus, G. Damnati, L. Delphin-Poulat, R. de Mori, Interspeech'06, USA, 2006.
Opinion mining in a telephone survey corpus, N. Camelin, G. Damnati, F. Béchet, R. de Mori, Interspeech'06, USA, 2006.
Corpus design based on the Kullback-Leibler divergence for Text-To-Speech synthesis application, A. Krul, G. Damnati, T. Moudenc, F. Yvon, Interspeech'06, USA, 2006.
Adaptive database reduction for domain specific speech synthesis, A. Krul, G. Damnati, F. Yvon, C. Boidin, T. Moudenc,Sixth ISCA Workshop on Speech Synthesis, Allemagne, 2006.
Multilevel features for annotating application-driven spontaneous speech corpora, V. Maffiolo, G. Damnati, V. Botherel, E. Guimier de Neef E. Maillebuau, Workshop on corpora and emotion, LREC'06, Italy, 2006.
On the use of multigram models for automatic translation, Y. Mami, G. Damnati, TC-STAR workshop, Espagne, 2006.
On the use of finite state transducers for semantic interpretation, C. Raymond, F. Béchet, R. de Mori, G. Damnati, Speech Communication, special issue on spoken language understanding, Volume 48, Issues 3-4, March-April 2006, Pages 288-304.
2005
Conceptual Language Model Design for Spoken Language Understanding, C. Kobus, G. Damnati, L. Delphin-Poulat, R. de Mori, Interspeech'2005, Portugal, 2005.
Semantic Interpretation with Error Correction, C. Raymond, F. Béchet, N. Camelin, R. de Mori, G. Damnati, ICASSP'05, USA, 2005.
Natural Multilingual Dialogue with a 3D Conversational Agent Dedicated to Interactive Web and Mobile Applications, D. Pelé, G. Breton, F. Panaget, P. Bretier, T. Moudenc, G. Damnati, HCI International, USA, 2005.
2004
On the use of confidence for statistical decision in dialogue strategies, C. Raymond, F. Béchet, R. de Mori, G. Damnati, 5th SIGdial Workshop on Discourse and Dialogue, USA, 2004.
Find a restaurant with the 3D embodied conversational agent Nestor, C. Ancé, P. Bretier, G. Breton, G. Damnati, T. Moudenc, J-P Le Pape, F. Panaget, D. Pelé, D. Sadek, 5th SIGdial Workshop on Discourse and Dialogue, USA, 2004.
Automatic learning of interpretation strategies for spoken dialogue systems, C. Raymond, F. Béchet, R. de Mori, G. Damnati, Y. Estève, ICASSP'04, Canada, 2004.
2003
Belief Confirmation in Spoken Dialog Systems using Confidence Measures, C. Raymond, Y. Estève, F. Béchet, R. de Mori, G. Damnati, IEEE Workshop on ASRU, US-Virgin Islands, 2003.
2002
Integration of phonetic length properties in the acoustic models of false starts and out-of-vocabulary words, H. Hamimed, G. Damnati, ICSLP'02, USA, 2002.
2001
Evaluating Speech Recognition in the Context of a Spoken Dialogue System: Critical Error Rate, G. Damnati, IEEE Workshop on ASRU, Italy, 2001.
Robust Speech/Non-Speech Detection using LDA applied to MFCC for Continuous Speech Recognition, A. Martin, G. Damnati and L. Mauuary, Eurospeech'01, Danemark, 2001.
1999
Adding New Words in a Spoken Dialogue System Vocabulary Using Conceptual Information and Derived Class-based Language Model, G. Damnati, F. Panaget, IEEE Workshop on ASRU, USA, 1999.
Integration of Several Information Sources for Robust Class-Based Statistical Language Modelling, G. Damnati, Eurospeech'99, Hongrie, 1999.
1998
Gaussian Density Tree Structure in a Multi-gaussian HMM-Based Speech Recognition System, J. Simonin, L. Delphin-Poulat, G. Damnati, ICSLP'98, Australie, 1998.
1997
Deriving Phrase-based Language Models, P. Heeman, G. Damnati, IEEE Workshop on ASRU, USA, 1997.
A Novel Tree-Based Clustering Algorithm for Statistical Language Modelling, G. Damnati, J. Simonin, EUROSPEECH'97, Grèce, 1997.