Cargando…
A message-passing multi-task architecture for the implicit event and polarity detection
Implicit sentiment analysis is a challenging task because the sentiment of a text is expressed in a connotative manner. To tackle this problem, we propose to use textual events as a knowledge source to enrich network representations. To consider task interactions, we present a novel lightweight join...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7920338/ https://www.ncbi.nlm.nih.gov/pubmed/33647054 http://dx.doi.org/10.1371/journal.pone.0247704 |
_version_ | 1783658254947057664 |
---|---|
author | Xiang, Chunli Zhang, Junchi Ji, Donghong |
author_facet | Xiang, Chunli Zhang, Junchi Ji, Donghong |
author_sort | Xiang, Chunli |
collection | PubMed |
description | Implicit sentiment analysis is a challenging task because the sentiment of a text is expressed in a connotative manner. To tackle this problem, we propose to use textual events as a knowledge source to enrich network representations. To consider task interactions, we present a novel lightweight joint learning paradigm that can pass task-related messages between tasks during training iterations. This is distinct from previous methods that involve multi-task learning by simple parameter sharing. Besides, a human-annotated corpus with implicit sentiment labels and event labels is scarce, which hinders practical applications of deep neural models. Therefore, we further investigate a back-translation approach to expand training instances. Experiment results on a public benchmark demonstrate the effectiveness of both the proposed multi-task architecture and data augmentation strategy. |
format | Online Article Text |
id | pubmed-7920338 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-79203382021-03-09 A message-passing multi-task architecture for the implicit event and polarity detection Xiang, Chunli Zhang, Junchi Ji, Donghong PLoS One Research Article Implicit sentiment analysis is a challenging task because the sentiment of a text is expressed in a connotative manner. To tackle this problem, we propose to use textual events as a knowledge source to enrich network representations. To consider task interactions, we present a novel lightweight joint learning paradigm that can pass task-related messages between tasks during training iterations. This is distinct from previous methods that involve multi-task learning by simple parameter sharing. Besides, a human-annotated corpus with implicit sentiment labels and event labels is scarce, which hinders practical applications of deep neural models. Therefore, we further investigate a back-translation approach to expand training instances. Experiment results on a public benchmark demonstrate the effectiveness of both the proposed multi-task architecture and data augmentation strategy. Public Library of Science 2021-03-01 /pmc/articles/PMC7920338/ /pubmed/33647054 http://dx.doi.org/10.1371/journal.pone.0247704 Text en © 2021 Xiang et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Xiang, Chunli Zhang, Junchi Ji, Donghong A message-passing multi-task architecture for the implicit event and polarity detection |
title | A message-passing multi-task architecture for the implicit event and polarity detection |
title_full | A message-passing multi-task architecture for the implicit event and polarity detection |
title_fullStr | A message-passing multi-task architecture for the implicit event and polarity detection |
title_full_unstemmed | A message-passing multi-task architecture for the implicit event and polarity detection |
title_short | A message-passing multi-task architecture for the implicit event and polarity detection |
title_sort | message-passing multi-task architecture for the implicit event and polarity detection |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7920338/ https://www.ncbi.nlm.nih.gov/pubmed/33647054 http://dx.doi.org/10.1371/journal.pone.0247704 |
work_keys_str_mv | AT xiangchunli amessagepassingmultitaskarchitecturefortheimpliciteventandpolaritydetection AT zhangjunchi amessagepassingmultitaskarchitecturefortheimpliciteventandpolaritydetection AT jidonghong amessagepassingmultitaskarchitecturefortheimpliciteventandpolaritydetection AT xiangchunli messagepassingmultitaskarchitecturefortheimpliciteventandpolaritydetection AT zhangjunchi messagepassingmultitaskarchitecturefortheimpliciteventandpolaritydetection AT jidonghong messagepassingmultitaskarchitecturefortheimpliciteventandpolaritydetection |