logo Idiap Research Institute        
Project SUMMA
Name: SUMMA

Publications of project SUMMA
2020
2019
AN INVESTIGATION OF MULTILINGUAL ASR USING END-TO-END LF-MMI, Sibo Tong, Philip N. Garner and Hervé Bourlard, in: International Conference on Acoustics, Speech and Signal Processing, 2019
attachment
ANALYZING UNCERTAINTIES IN SPEECH RECOGNITION USING DROPOUT, Apoorv Vyas, Pranay Dighe, Sibo Tong and Hervé Bourlard, in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
Deep Residual Output Layers for Neural Language Generation, Nikolaos Pappas and James Henderson, in: Proceedings of the 36th International Conference on Machine Learning (ICML), 2019
attachment
EMPIRICAL EVALUATION AND COMBINATION OF PUNCTUATION PREDICTION MODELS APPLIED TO BROADCAST NEWS, Alexandre Nanchen and Philip N. Garner, in: Proceedings of 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2019
attachment
GILE: A Generalized Input-Label Embedding for Text Classification, Nikolaos Pappas and James Henderson, in: Transactions of the Association for Computational Linguistics (TACL), 2019
attachment
2018
CONTEXT-AWARE ATTENTION MECHANISM FOR SPEECH EMOTION RECOGNITION, Gaetan Ramet, Philip N. Garner, Michael Baeriswyl and Alexandros Lazaridis, in: IEEE Workshop on Spoken Language Technology, Athens, Greece, pages 126-131, 2018
attachment
[URL]
Document-Level Neural Machine Translation with Hierarchical Attention Networks, Lesly Miculicich, Dhananjay Ram, Nikolaos Pappas and James Henderson, in: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018
attachment
Fast Language Adaptation Using Phonological Information, Sibo Tong, Philip N. Garner and Hervé Bourlard, in: Proceedings of Interspeech 2018, Hyderabad, INDIA, pages 2459-2463, 2018
attachment
[DOI]
Self-Attentive Residual Decoder for Neural Machine Translation, Lesly Miculicich, Nikolaos Pappas, Dhananjay Ram and Andrei Popescu-Belis, in: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2018
attachment
2017
Explicit Document Modeling through Weighted Multiple-Instance Learning, Nikolaos Pappas and Andrei Popescu-Belis, in: Journal of Artificial Intelligence Research (JAIR), 58:591--626, 2017
attachment
Machine translation of Spanish personal and possessive pronouns using anaphora probabilities, Ngoc-Quang Luong and Andrei Popescu-Belis, in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Valencia, Spain, Association for Computational Linguistics, 2017
attachment
Multilingual Hierarchical Attention Networks for Document Classification, Nikolaos Pappas and Andrei Popescu-Belis, in: Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP), pages 1015-1025, 2017
attachment
The SUMMA Platform Prototype, Renars Liepins and et al., in: Proceedings of the EACL 2017 Software Demonstrations, Valencia, Spain, pages 116--119, 2017
attachment
[URL]
Using Coreference Links to Improve Spanish-to-English Machine Translation, Lesly Miculicich and Andrei Popescu-Belis, in: Proceedings of the 2nd Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2017), Valencia, Spain, pages 30-40, Association for Computational Linguistics (ACL), 2017
attachment
Validation of an Automatic Metric for the Accuracy of Pronoun Translation (APT), Lesly Miculicich and Andrei Popescu-Belis, in: Proceedings of the Third Workshop on Discourse in Machine Translation (DiscoMT), Denmark, Copenhagen, Association for Computational Linguistics (ACL), 2017
attachment
2016
Human versus Machine Attention in Document Classification: A Dataset with Crowdsourced Annotations, Nikolaos Pappas and Andrei Popescu-Belis, in: Proceedings of the EMNLP 2016 Workshop on Natural Language Processing for Social Media, Austin, USA, 2016
attachment