DC Field | Value | Language |
---|---|---|
dc.contributor.author | Parshakova, Tetiana | ko |
dc.contributor.author | Rameau, Francois | ko |
dc.contributor.author | Serdega, Andriy | ko |
dc.contributor.author | Kweon, In-So | ko |
dc.contributor.author | Kim, Dae-Shik | ko |
dc.date.accessioned | 2019-08-27T08:20:03Z | - |
dc.date.available | 2019-08-27T08:20:03Z | - |
dc.date.created | 2019-08-26 | - |
dc.date.created | 2019-08-26 | - |
dc.date.created | 2019-08-26 | - |
dc.date.created | 2019-08-26 | - |
dc.date.created | 2019-08-26 | - |
dc.date.created | 2019-08-26 | - |
dc.date.issued | 2019-11 | - |
dc.identifier.citation | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, v.27, no.11, pp.1713 - 1724 | - |
dc.identifier.issn | 2329-9290 | - |
dc.identifier.uri | http://hdl.handle.net/10203/265541 | - |
dc.description.abstract | Most artificial neural network models for question-answering rely on complex attention mechanisms. These techniques demonstrate high performance on existing datasets; however, they are limited in their ability to capture natural language variability, and to generate diverse relevant answers. To address this limitation, we propose a model that learns multiple interpretations of a given question. This diversity is ensured by our interpretation policy module which automatically adapts the parameters of a question-answering model with respect to a discrete latent variable. This variable follows the distribution of interpretations learned by the interpretation policy through a semi-supervised variational inference framework. To boost the performance further, the resulting policy is fine-tuned using the rewards from the answer accuracy with a policy gradient. We demonstrate the relevance and efficiency of our model through a large panel of experiments. Qualitative results, in particular, underline the ability of the proposed architecture to discover multiple interpretations of a question. When tested using the Stanford Question Answering Dataset 1.1, our model outperforms the baseline methods in finding multiple and diverse answers. To assess our strategy from a human standpoint, we also conduct a large-scale user study. This study highlights the ability of our network to produce diverse and coherent answers compared to existing approaches. Our Pytorch implementation is available as open source.(1) | - |
dc.language | English | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Latent Question Interpretation Through Variational Adaptation | - |
dc.type | Article | - |
dc.identifier.wosid | 000480309600005 | - |
dc.identifier.scopusid | 2-s2.0-85070478937 | - |
dc.type.rims | ART | - |
dc.citation.volume | 27 | - |
dc.citation.issue | 11 | - |
dc.citation.beginningpage | 1713 | - |
dc.citation.endingpage | 1724 | - |
dc.citation.publicationname | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING | - |
dc.identifier.doi | 10.1109/TASLP.2019.2929647 | - |
dc.contributor.localauthor | Kweon, In-So | - |
dc.contributor.localauthor | Kim, Dae-Shik | - |
dc.contributor.nonIdAuthor | Parshakova, Tetiana | - |
dc.contributor.nonIdAuthor | Serdega, Andriy | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Question answering | - |
dc.subject.keywordAuthor | neural variational inference | - |
dc.subject.keywordAuthor | semi-supervised learning | - |
dc.subject.keywordAuthor | policy gradient | - |
dc.subject.keywordAuthor | discrete latent variable | - |
dc.subject.keywordAuthor | information retrieval | - |
dc.subject.keywordAuthor | neural networks | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.