Augmenting Transformers with KNN-Based Composite Memory for Dialog

Autor: Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes

Publikováno v: Transactions of the Association for Computational Linguistics, Vol 9, Pp 82-99 (2021)

AbstractVarious machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propo

Externí odkaz: https://doaj.org/article/4f1283341a834a3690659ffa2d2e90ff

ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations

Autor: Antoine Bordes, Lucia Specia, Fernando Alva-Manchego, Benoît Sagot, Louis Martin, Carolina Scarton

Publikováno v: ACL

In order to simplify a sentence, human editors perform multiple rewriting transformations: they split it into several shorter sentences, paraphrase words (i.e. replacing complex words or phrases by simpler synonyms), reorder components, and/or delete

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f566b40fdaf6d38532f71561267e7b95
https://doi.org/10.18653/v1/2020.acl-main.424

Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs

Autor: Chloé Braud, Angela Fan, Antoine Bordes, Claire Gardent

Publikováno v: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing
2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong Kong, China. ⟨10.18653/v1/D19-1428⟩
EMNLP/IJCNLP (1)

International audience; Query-based open-domain NLP tasks require information synthesis from long and diverse web results. Current approaches extrac-tively select portions of web text as input to Sequence-to-Sequence models using methods such as TF-I

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f06ad85abbf33a490d6d29a991ae2870
https://hal.archives-ouvertes.fr/hal-02277063

Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

Autor: Jason Weston, Braden Hancock, Antoine Bordes, Pierre-Emmanuel Mazaré

Publikováno v: ACL (1)

The majority of conversations a dialogue agent sees over its lifetime occur after it has already been trained and deployed, leaving a vast store of potential training signal untapped. In this work, we propose the self-feeding chatbot, a dialogue agen

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b3f60db2132318e3559d87aaa6d32abe
http://arxiv.org/abs/1901.05415

Training Millions of Personalized Dialogue Agents

Autor: Martin Raison, Samuel Humeau, Antoine Bordes, Pierre-Emmanuel Mazaré

Publikováno v: EMNLP

Current dialogue systems are not very engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies. Zhang et al. (2018) showed that the engagement level of end-to-end dialogue models increases whe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15039be8cda7cef6fb628023c9b3260b
http://arxiv.org/abs/1809.01984