Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification
Open-domain targeted sentiment analysis aims to detect opinion targets along with their sentiment polarities from a sentence. Prior work typically formulates this task as a sequence tagging problem. However, such formulation suffers from problems such as huge search space and sentiment inconsistency...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | |
container_volume | |
creator | Hu, Minghao Peng, Yuxing Huang, Zhen Li, Dongsheng Lv, Yiwei |
description | Open-domain targeted sentiment analysis aims to detect opinion targets along
with their sentiment polarities from a sentence. Prior work typically
formulates this task as a sequence tagging problem. However, such formulation
suffers from problems such as huge search space and sentiment inconsistency. To
address these problems, we propose a span-based extract-then-classify
framework, where multiple opinion targets are directly extracted from the
sentence under the supervision of target span boundaries, and corresponding
polarities are then classified using their span representations. We further
investigate three approaches under this framework, namely the pipeline, joint,
and collapsed models. Experiments on three benchmark datasets show that our
approach consistently outperforms the sequence tagging baseline. Moreover, we
find that the pipeline model achieves the best performance compared with the
other two models. |
doi_str_mv | 10.48550/arxiv.1906.03820 |
format | Article |
fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1906_03820</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1906_03820</sourcerecordid><originalsourceid>FETCH-LOGICAL-a670-17bdb0d5bcb24b69aec90a86ae544d205d2f86b13b3b6c8afa8648314669e51a3</originalsourceid><addsrcrecordid>eNotj8luwjAYhH3hUFEeoCf8Ak7teME5QkoXCYkDuUe_l1SWEhPZEYK3J9BeZqSZ0UgfQm-MFkJLSd8hXcOlYBVVBeW6pC-oOY4-ko_zACHiBtKvn7zDJx-nMMyCtxH6Ww4ZXwLg0wiR7CDPi_11SmCncI4YosN1DzmHLlh4RK9o0UGf_erfl6j53Df1Nzkcv37q7YGA2lDCNsYZ6qSxphRGVeBtRUEr8FIIV1Lpyk4rw7jhRlkN3dwJzZlQqvKSAV-i9d_tE6sdUxgg3doHXvvE43e01EtI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification</title><source>arXiv.org</source><creator>Hu, Minghao ; Peng, Yuxing ; Huang, Zhen ; Li, Dongsheng ; Lv, Yiwei</creator><creatorcontrib>Hu, Minghao ; Peng, Yuxing ; Huang, Zhen ; Li, Dongsheng ; Lv, Yiwei</creatorcontrib><description>Open-domain targeted sentiment analysis aims to detect opinion targets along
with their sentiment polarities from a sentence. Prior work typically
formulates this task as a sequence tagging problem. However, such formulation
suffers from problems such as huge search space and sentiment inconsistency. To
address these problems, we propose a span-based extract-then-classify
framework, where multiple opinion targets are directly extracted from the
sentence under the supervision of target span boundaries, and corresponding
polarities are then classified using their span representations. We further
investigate three approaches under this framework, namely the pipeline, joint,
and collapsed models. Experiments on three benchmark datasets show that our
approach consistently outperforms the sequence tagging baseline. Moreover, we
find that the pipeline model achieves the best performance compared with the
other two models.</description><identifier>DOI: 10.48550/arxiv.1906.03820</identifier><language>eng</language><subject>Computer Science - Computation and Language</subject><creationdate>2019-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1906.03820$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1906.03820$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hu, Minghao</creatorcontrib><creatorcontrib>Peng, Yuxing</creatorcontrib><creatorcontrib>Huang, Zhen</creatorcontrib><creatorcontrib>Li, Dongsheng</creatorcontrib><creatorcontrib>Lv, Yiwei</creatorcontrib><title>Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification</title><description>Open-domain targeted sentiment analysis aims to detect opinion targets along
with their sentiment polarities from a sentence. Prior work typically
formulates this task as a sequence tagging problem. However, such formulation
suffers from problems such as huge search space and sentiment inconsistency. To
address these problems, we propose a span-based extract-then-classify
framework, where multiple opinion targets are directly extracted from the
sentence under the supervision of target span boundaries, and corresponding
polarities are then classified using their span representations. We further
investigate three approaches under this framework, namely the pipeline, joint,
and collapsed models. Experiments on three benchmark datasets show that our
approach consistently outperforms the sequence tagging baseline. Moreover, we
find that the pipeline model achieves the best performance compared with the
other two models.</description><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8luwjAYhH3hUFEeoCf8Ak7teME5QkoXCYkDuUe_l1SWEhPZEYK3J9BeZqSZ0UgfQm-MFkJLSd8hXcOlYBVVBeW6pC-oOY4-ko_zACHiBtKvn7zDJx-nMMyCtxH6Ww4ZXwLg0wiR7CDPi_11SmCncI4YosN1DzmHLlh4RK9o0UGf_erfl6j53Df1Nzkcv37q7YGA2lDCNsYZ6qSxphRGVeBtRUEr8FIIV1Lpyk4rw7jhRlkN3dwJzZlQqvKSAV-i9d_tE6sdUxgg3doHXvvE43e01EtI</recordid><startdate>20190610</startdate><enddate>20190610</enddate><creator>Hu, Minghao</creator><creator>Peng, Yuxing</creator><creator>Huang, Zhen</creator><creator>Li, Dongsheng</creator><creator>Lv, Yiwei</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190610</creationdate><title>Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification</title><author>Hu, Minghao ; Peng, Yuxing ; Huang, Zhen ; Li, Dongsheng ; Lv, Yiwei</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a670-17bdb0d5bcb24b69aec90a86ae544d205d2f86b13b3b6c8afa8648314669e51a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Hu, Minghao</creatorcontrib><creatorcontrib>Peng, Yuxing</creatorcontrib><creatorcontrib>Huang, Zhen</creatorcontrib><creatorcontrib>Li, Dongsheng</creatorcontrib><creatorcontrib>Lv, Yiwei</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hu, Minghao</au><au>Peng, Yuxing</au><au>Huang, Zhen</au><au>Li, Dongsheng</au><au>Lv, Yiwei</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification</atitle><date>2019-06-10</date><risdate>2019</risdate><abstract>Open-domain targeted sentiment analysis aims to detect opinion targets along
with their sentiment polarities from a sentence. Prior work typically
formulates this task as a sequence tagging problem. However, such formulation
suffers from problems such as huge search space and sentiment inconsistency. To
address these problems, we propose a span-based extract-then-classify
framework, where multiple opinion targets are directly extracted from the
sentence under the supervision of target span boundaries, and corresponding
polarities are then classified using their span representations. We further
investigate three approaches under this framework, namely the pipeline, joint,
and collapsed models. Experiments on three benchmark datasets show that our
approach consistently outperforms the sequence tagging baseline. Moreover, we
find that the pipeline model achieves the best performance compared with the
other two models.</abstract><doi>10.48550/arxiv.1906.03820</doi><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | DOI: 10.48550/arxiv.1906.03820 |
ispartof | |
issn | |
language | eng |
recordid | cdi_arxiv_primary_1906_03820 |
source | arXiv.org |
subjects | Computer Science - Computation and Language |
title | Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T08%3A04%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Open-Domain%20Targeted%20Sentiment%20Analysis%20via%20Span-Based%20Extraction%20and%20Classification&rft.au=Hu,%20Minghao&rft.date=2019-06-10&rft_id=info:doi/10.48550/arxiv.1906.03820&rft_dat=%3Carxiv_GOX%3E1906_03820%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |