Leveraging Abstract Meaning Representation for Knowledge Base Question Answering
Knowledge base question answering (KBQA)is an important task in Natural Language Processing. Existing approaches face significant challenges including complex question understanding, necessity for reasoning, and lack of large end-to-end training datasets. In this work, we propose Neuro-Symbolic Ques...
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 | Kapanipathi, Pavan Abdelaziz, Ibrahim Ravishankar, Srinivas Roukos, Salim Gray, Alexander Astudillo, Ramon Chang, Maria Cornelio, Cristina Dana, Saswati Fokoue, Achille Garg, Dinesh Gliozzo, Alfio Gurajada, Sairam Karanam, Hima Khan, Naweed Khandelwal, Dinesh Lee, Young-Suk Li, Yunyao Luus, Francois Makondo, Ndivhuwo Mihindukulasooriya, Nandana Naseem, Tahira Neelam, Sumit Popa, Lucian Reddy, Revanth Riegel, Ryan Rossiello, Gaetano Sharma, Udit Bhargav, G P Shrivatsa Yu, Mo |
| description | Knowledge base question answering (KBQA)is an important task in Natural
Language Processing. Existing approaches face significant challenges including
complex question understanding, necessity for reasoning, and lack of large
end-to-end training datasets. In this work, we propose Neuro-Symbolic Question
Answering (NSQA), a modular KBQA system, that leverages (1) Abstract Meaning
Representation (AMR) parses for task-independent question understanding; (2) a
simple yet effective graph transformation approach to convert AMR parses into
candidate logical queries that are aligned to the KB; (3) a pipeline-based
approach which integrates multiple, reusable modules that are trained
specifically for their individual tasks (semantic parser, entity
andrelationship linkers, and neuro-symbolic reasoner) and do not require
end-to-end training data. NSQA achieves state-of-the-art performance on two
prominent KBQA datasets based on DBpedia (QALD-9 and LC-QuAD1.0). Furthermore,
our analysis emphasizes that AMR is a powerful tool for KBQA systems. |
| doi_str_mv | 10.48550/arxiv.2012.01707 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2012_01707</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2012_01707</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-e6bbb550517e890bb18d9805297b5257b95c7ccf155fb15f452090b2f9de72953</originalsourceid><addsrcrecordid>eNotj8tOwzAQRb1hgQofwAr_QILtdjrxMlS8RBAPdR95knEUqTiVHVr4e9LA6kr3MZojxJVW-aoAUDcufveH3ChtcqVR4bl4q_jA0XV96GRJaYyuGeULu3AyPngfOXEY3dgPQfohyucwHHfcdixvXWL5_sVpzsqQjhyn0YU4826X-PJfF2J7f7fdPGbV68PTpqwyt0bMeE1E00egkQuriHTR2kKBsUhgAMlCg03jNYAnDX4FRk01423LaCwsF-L67-yMVO9j_-niT31Cq2e05S9zaUl6</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Leveraging Abstract Meaning Representation for Knowledge Base Question Answering</title><source>arXiv.org</source><creator>Kapanipathi, Pavan ; Abdelaziz, Ibrahim ; Ravishankar, Srinivas ; Roukos, Salim ; Gray, Alexander ; Astudillo, Ramon ; Chang, Maria ; Cornelio, Cristina ; Dana, Saswati ; Fokoue, Achille ; Garg, Dinesh ; Gliozzo, Alfio ; Gurajada, Sairam ; Karanam, Hima ; Khan, Naweed ; Khandelwal, Dinesh ; Lee, Young-Suk ; Li, Yunyao ; Luus, Francois ; Makondo, Ndivhuwo ; Mihindukulasooriya, Nandana ; Naseem, Tahira ; Neelam, Sumit ; Popa, Lucian ; Reddy, Revanth ; Riegel, Ryan ; Rossiello, Gaetano ; Sharma, Udit ; Bhargav, G P Shrivatsa ; Yu, Mo</creator><creatorcontrib>Kapanipathi, Pavan ; Abdelaziz, Ibrahim ; Ravishankar, Srinivas ; Roukos, Salim ; Gray, Alexander ; Astudillo, Ramon ; Chang, Maria ; Cornelio, Cristina ; Dana, Saswati ; Fokoue, Achille ; Garg, Dinesh ; Gliozzo, Alfio ; Gurajada, Sairam ; Karanam, Hima ; Khan, Naweed ; Khandelwal, Dinesh ; Lee, Young-Suk ; Li, Yunyao ; Luus, Francois ; Makondo, Ndivhuwo ; Mihindukulasooriya, Nandana ; Naseem, Tahira ; Neelam, Sumit ; Popa, Lucian ; Reddy, Revanth ; Riegel, Ryan ; Rossiello, Gaetano ; Sharma, Udit ; Bhargav, G P Shrivatsa ; Yu, Mo</creatorcontrib><description>Knowledge base question answering (KBQA)is an important task in Natural
Language Processing. Existing approaches face significant challenges including
complex question understanding, necessity for reasoning, and lack of large
end-to-end training datasets. In this work, we propose Neuro-Symbolic Question
Answering (NSQA), a modular KBQA system, that leverages (1) Abstract Meaning
Representation (AMR) parses for task-independent question understanding; (2) a
simple yet effective graph transformation approach to convert AMR parses into
candidate logical queries that are aligned to the KB; (3) a pipeline-based
approach which integrates multiple, reusable modules that are trained
specifically for their individual tasks (semantic parser, entity
andrelationship linkers, and neuro-symbolic reasoner) and do not require
end-to-end training data. NSQA achieves state-of-the-art performance on two
prominent KBQA datasets based on DBpedia (QALD-9 and LC-QuAD1.0). Furthermore,
our analysis emphasizes that AMR is a powerful tool for KBQA systems.</description><identifier>DOI: 10.48550/arxiv.2012.01707</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language</subject><creationdate>2020-12</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/2012.01707$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2012.01707$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kapanipathi, Pavan</creatorcontrib><creatorcontrib>Abdelaziz, Ibrahim</creatorcontrib><creatorcontrib>Ravishankar, Srinivas</creatorcontrib><creatorcontrib>Roukos, Salim</creatorcontrib><creatorcontrib>Gray, Alexander</creatorcontrib><creatorcontrib>Astudillo, Ramon</creatorcontrib><creatorcontrib>Chang, Maria</creatorcontrib><creatorcontrib>Cornelio, Cristina</creatorcontrib><creatorcontrib>Dana, Saswati</creatorcontrib><creatorcontrib>Fokoue, Achille</creatorcontrib><creatorcontrib>Garg, Dinesh</creatorcontrib><creatorcontrib>Gliozzo, Alfio</creatorcontrib><creatorcontrib>Gurajada, Sairam</creatorcontrib><creatorcontrib>Karanam, Hima</creatorcontrib><creatorcontrib>Khan, Naweed</creatorcontrib><creatorcontrib>Khandelwal, Dinesh</creatorcontrib><creatorcontrib>Lee, Young-Suk</creatorcontrib><creatorcontrib>Li, Yunyao</creatorcontrib><creatorcontrib>Luus, Francois</creatorcontrib><creatorcontrib>Makondo, Ndivhuwo</creatorcontrib><creatorcontrib>Mihindukulasooriya, Nandana</creatorcontrib><creatorcontrib>Naseem, Tahira</creatorcontrib><creatorcontrib>Neelam, Sumit</creatorcontrib><creatorcontrib>Popa, Lucian</creatorcontrib><creatorcontrib>Reddy, Revanth</creatorcontrib><creatorcontrib>Riegel, Ryan</creatorcontrib><creatorcontrib>Rossiello, Gaetano</creatorcontrib><creatorcontrib>Sharma, Udit</creatorcontrib><creatorcontrib>Bhargav, G P Shrivatsa</creatorcontrib><creatorcontrib>Yu, Mo</creatorcontrib><title>Leveraging Abstract Meaning Representation for Knowledge Base Question Answering</title><description>Knowledge base question answering (KBQA)is an important task in Natural
Language Processing. Existing approaches face significant challenges including
complex question understanding, necessity for reasoning, and lack of large
end-to-end training datasets. In this work, we propose Neuro-Symbolic Question
Answering (NSQA), a modular KBQA system, that leverages (1) Abstract Meaning
Representation (AMR) parses for task-independent question understanding; (2) a
simple yet effective graph transformation approach to convert AMR parses into
candidate logical queries that are aligned to the KB; (3) a pipeline-based
approach which integrates multiple, reusable modules that are trained
specifically for their individual tasks (semantic parser, entity
andrelationship linkers, and neuro-symbolic reasoner) and do not require
end-to-end training data. NSQA achieves state-of-the-art performance on two
prominent KBQA datasets based on DBpedia (QALD-9 and LC-QuAD1.0). Furthermore,
our analysis emphasizes that AMR is a powerful tool for KBQA systems.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tOwzAQRb1hgQofwAr_QILtdjrxMlS8RBAPdR95knEUqTiVHVr4e9LA6kr3MZojxJVW-aoAUDcufveH3ChtcqVR4bl4q_jA0XV96GRJaYyuGeULu3AyPngfOXEY3dgPQfohyucwHHfcdixvXWL5_sVpzsqQjhyn0YU4826X-PJfF2J7f7fdPGbV68PTpqwyt0bMeE1E00egkQuriHTR2kKBsUhgAMlCg03jNYAnDX4FRk01423LaCwsF-L67-yMVO9j_-niT31Cq2e05S9zaUl6</recordid><startdate>20201203</startdate><enddate>20201203</enddate><creator>Kapanipathi, Pavan</creator><creator>Abdelaziz, Ibrahim</creator><creator>Ravishankar, Srinivas</creator><creator>Roukos, Salim</creator><creator>Gray, Alexander</creator><creator>Astudillo, Ramon</creator><creator>Chang, Maria</creator><creator>Cornelio, Cristina</creator><creator>Dana, Saswati</creator><creator>Fokoue, Achille</creator><creator>Garg, Dinesh</creator><creator>Gliozzo, Alfio</creator><creator>Gurajada, Sairam</creator><creator>Karanam, Hima</creator><creator>Khan, Naweed</creator><creator>Khandelwal, Dinesh</creator><creator>Lee, Young-Suk</creator><creator>Li, Yunyao</creator><creator>Luus, Francois</creator><creator>Makondo, Ndivhuwo</creator><creator>Mihindukulasooriya, Nandana</creator><creator>Naseem, Tahira</creator><creator>Neelam, Sumit</creator><creator>Popa, Lucian</creator><creator>Reddy, Revanth</creator><creator>Riegel, Ryan</creator><creator>Rossiello, Gaetano</creator><creator>Sharma, Udit</creator><creator>Bhargav, G P Shrivatsa</creator><creator>Yu, Mo</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201203</creationdate><title>Leveraging Abstract Meaning Representation for Knowledge Base Question Answering</title><author>Kapanipathi, Pavan ; Abdelaziz, Ibrahim ; Ravishankar, Srinivas ; Roukos, Salim ; Gray, Alexander ; Astudillo, Ramon ; Chang, Maria ; Cornelio, Cristina ; Dana, Saswati ; Fokoue, Achille ; Garg, Dinesh ; Gliozzo, Alfio ; Gurajada, Sairam ; Karanam, Hima ; Khan, Naweed ; Khandelwal, Dinesh ; Lee, Young-Suk ; Li, Yunyao ; Luus, Francois ; Makondo, Ndivhuwo ; Mihindukulasooriya, Nandana ; Naseem, Tahira ; Neelam, Sumit ; Popa, Lucian ; Reddy, Revanth ; Riegel, Ryan ; Rossiello, Gaetano ; Sharma, Udit ; Bhargav, G P Shrivatsa ; Yu, Mo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-e6bbb550517e890bb18d9805297b5257b95c7ccf155fb15f452090b2f9de72953</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Kapanipathi, Pavan</creatorcontrib><creatorcontrib>Abdelaziz, Ibrahim</creatorcontrib><creatorcontrib>Ravishankar, Srinivas</creatorcontrib><creatorcontrib>Roukos, Salim</creatorcontrib><creatorcontrib>Gray, Alexander</creatorcontrib><creatorcontrib>Astudillo, Ramon</creatorcontrib><creatorcontrib>Chang, Maria</creatorcontrib><creatorcontrib>Cornelio, Cristina</creatorcontrib><creatorcontrib>Dana, Saswati</creatorcontrib><creatorcontrib>Fokoue, Achille</creatorcontrib><creatorcontrib>Garg, Dinesh</creatorcontrib><creatorcontrib>Gliozzo, Alfio</creatorcontrib><creatorcontrib>Gurajada, Sairam</creatorcontrib><creatorcontrib>Karanam, Hima</creatorcontrib><creatorcontrib>Khan, Naweed</creatorcontrib><creatorcontrib>Khandelwal, Dinesh</creatorcontrib><creatorcontrib>Lee, Young-Suk</creatorcontrib><creatorcontrib>Li, Yunyao</creatorcontrib><creatorcontrib>Luus, Francois</creatorcontrib><creatorcontrib>Makondo, Ndivhuwo</creatorcontrib><creatorcontrib>Mihindukulasooriya, Nandana</creatorcontrib><creatorcontrib>Naseem, Tahira</creatorcontrib><creatorcontrib>Neelam, Sumit</creatorcontrib><creatorcontrib>Popa, Lucian</creatorcontrib><creatorcontrib>Reddy, Revanth</creatorcontrib><creatorcontrib>Riegel, Ryan</creatorcontrib><creatorcontrib>Rossiello, Gaetano</creatorcontrib><creatorcontrib>Sharma, Udit</creatorcontrib><creatorcontrib>Bhargav, G P Shrivatsa</creatorcontrib><creatorcontrib>Yu, Mo</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kapanipathi, Pavan</au><au>Abdelaziz, Ibrahim</au><au>Ravishankar, Srinivas</au><au>Roukos, Salim</au><au>Gray, Alexander</au><au>Astudillo, Ramon</au><au>Chang, Maria</au><au>Cornelio, Cristina</au><au>Dana, Saswati</au><au>Fokoue, Achille</au><au>Garg, Dinesh</au><au>Gliozzo, Alfio</au><au>Gurajada, Sairam</au><au>Karanam, Hima</au><au>Khan, Naweed</au><au>Khandelwal, Dinesh</au><au>Lee, Young-Suk</au><au>Li, Yunyao</au><au>Luus, Francois</au><au>Makondo, Ndivhuwo</au><au>Mihindukulasooriya, Nandana</au><au>Naseem, Tahira</au><au>Neelam, Sumit</au><au>Popa, Lucian</au><au>Reddy, Revanth</au><au>Riegel, Ryan</au><au>Rossiello, Gaetano</au><au>Sharma, Udit</au><au>Bhargav, G P Shrivatsa</au><au>Yu, Mo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Leveraging Abstract Meaning Representation for Knowledge Base Question Answering</atitle><date>2020-12-03</date><risdate>2020</risdate><abstract>Knowledge base question answering (KBQA)is an important task in Natural
Language Processing. Existing approaches face significant challenges including
complex question understanding, necessity for reasoning, and lack of large
end-to-end training datasets. In this work, we propose Neuro-Symbolic Question
Answering (NSQA), a modular KBQA system, that leverages (1) Abstract Meaning
Representation (AMR) parses for task-independent question understanding; (2) a
simple yet effective graph transformation approach to convert AMR parses into
candidate logical queries that are aligned to the KB; (3) a pipeline-based
approach which integrates multiple, reusable modules that are trained
specifically for their individual tasks (semantic parser, entity
andrelationship linkers, and neuro-symbolic reasoner) and do not require
end-to-end training data. NSQA achieves state-of-the-art performance on two
prominent KBQA datasets based on DBpedia (QALD-9 and LC-QuAD1.0). Furthermore,
our analysis emphasizes that AMR is a powerful tool for KBQA systems.</abstract><doi>10.48550/arxiv.2012.01707</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2012.01707 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2012_01707 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Computation and Language |
| title | Leveraging Abstract Meaning Representation for Knowledge Base Question Answering |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T12%3A09%3A56IST&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=Leveraging%20Abstract%20Meaning%20Representation%20for%20Knowledge%20Base%20Question%20Answering&rft.au=Kapanipathi,%20Pavan&rft.date=2020-12-03&rft_id=info:doi/10.48550/arxiv.2012.01707&rft_dat=%3Carxiv_GOX%3E2012_01707%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 |