Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing
Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit Sanghai, Fei Sha
Abstract
A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative exemplars that help produce the correct parse, which is especially challenging in low-resource settings. Existing retrieval is commonly based on similarity of query and exemplar inputs. We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar. GandR first generates a preliminary prediction with input-based retrieval. Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction. GandR sets the state of the art on multiple low-resource semantic parsing tasks.- Anthology ID:
- 2022.coling-1.438
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Editors:
- Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 4946–4951
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.438
- DOI:
- Bibkey:
- Cite (ACL):
- Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit Sanghai, and Fei Sha. 2022. Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4946–4951, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing (Zemlyanskiy et al., COLING 2022)
- Copy Citation:
- PDF:
- https://aclanthology.org/2022.coling-1.438.pdf
- Data
- MTOP, TOPv2
Export citation
@inproceedings{zemlyanskiy-etal-2022-generate, title = "Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing", author = "Zemlyanskiy, Yury and de Jong, Michiel and Ainslie, Joshua and Pasupat, Panupong and Shaw, Peter and Qiu, Linlu and Sanghai, Sumit and Sha, Fei", editor = "Calzolari, Nicoletta and Huang, Chu-Ren and Kim, Hansaem and Pustejovsky, James and Wanner, Leo and Choi, Key-Sun and Ryu, Pum-Mo and Chen, Hsin-Hsi and Donatelli, Lucia and Ji, Heng and Kurohashi, Sadao and Paggio, Patrizia and Xue, Nianwen and Kim, Seokhwan and Hahm, Younggyun and He, Zhong and Lee, Tony Kyungil and Santus, Enrico and Bond, Francis and Na, Seung-Hoon", booktitle = "Proceedings of the 29th International Conference on Computational Linguistics", month = oct, year = "2022", address = "Gyeongju, Republic of Korea", publisher = "International Committee on Computational Linguistics", url = "https://aclanthology.org/2022.coling-1.438", pages = "4946--4951", abstract = "A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative exemplars that help produce the correct parse, which is especially challenging in low-resource settings. Existing retrieval is commonly based on similarity of query and exemplar inputs. We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar. GandR first generates a preliminary prediction with input-based retrieval. Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction. GandR sets the state of the art on multiple low-resource semantic parsing tasks.", }
<?xml version="1.0" encoding="UTF-8"?> <modsCollection xmlns="http://www.loc.gov/mods/v3"> <mods ID="zemlyanskiy-etal-2022-generate"> <titleInfo> <title>Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing</title> </titleInfo> <name type="personal"> <namePart type="given">Yury</namePart> <namePart type="family">Zemlyanskiy</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Michiel</namePart> <namePart type="family">de Jong</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Joshua</namePart> <namePart type="family">Ainslie</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Panupong</namePart> <namePart type="family">Pasupat</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Peter</namePart> <namePart type="family">Shaw</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Linlu</namePart> <namePart type="family">Qiu</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Sumit</namePart> <namePart type="family">Sanghai</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Fei</namePart> <namePart type="family">Sha</namePart> <role> <roleTerm authority="marcrelator" type="text">author</roleTerm> </role> </name> <originInfo> <dateIssued>2022-10</dateIssued> </originInfo> <typeOfResource>text</typeOfResource> <relatedItem type="host"> <titleInfo> <title>Proceedings of the 29th International Conference on Computational Linguistics</title> </titleInfo> <name type="personal"> <namePart type="given">Nicoletta</namePart> <namePart type="family">Calzolari</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Chu-Ren</namePart> <namePart type="family">Huang</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Hansaem</namePart> <namePart type="family">Kim</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">James</namePart> <namePart type="family">Pustejovsky</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Leo</namePart> <namePart type="family">Wanner</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Key-Sun</namePart> <namePart type="family">Choi</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Pum-Mo</namePart> <namePart type="family">Ryu</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Hsin-Hsi</namePart> <namePart type="family">Chen</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Lucia</namePart> <namePart type="family">Donatelli</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Heng</namePart> <namePart type="family">Ji</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Sadao</namePart> <namePart type="family">Kurohashi</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Patrizia</namePart> <namePart type="family">Paggio</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Nianwen</namePart> <namePart type="family">Xue</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Seokhwan</namePart> <namePart type="family">Kim</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Younggyun</namePart> <namePart type="family">Hahm</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Zhong</namePart> <namePart type="family">He</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Tony</namePart> <namePart type="given">Kyungil</namePart> <namePart type="family">Lee</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Enrico</namePart> <namePart type="family">Santus</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Francis</namePart> <namePart type="family">Bond</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <name type="personal"> <namePart type="given">Seung-Hoon</namePart> <namePart type="family">Na</namePart> <role> <roleTerm authority="marcrelator" type="text">editor</roleTerm> </role> </name> <originInfo> <publisher>International Committee on Computational Linguistics</publisher> <place> <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm> </place> </originInfo> <genre authority="marcgt">conference publication</genre> </relatedItem> <abstract>A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative exemplars that help produce the correct parse, which is especially challenging in low-resource settings. Existing retrieval is commonly based on similarity of query and exemplar inputs. We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar. GandR first generates a preliminary prediction with input-based retrieval. Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction. GandR sets the state of the art on multiple low-resource semantic parsing tasks.</abstract> <identifier type="citekey">zemlyanskiy-etal-2022-generate</identifier> <location> <url>https://aclanthology.org/2022.coling-1.438</url> </location> <part> <date>2022-10</date> <extent unit="page"> <start>4946</start> <end>4951</end> </extent> </part> </mods> </modsCollection>
%0 Conference Proceedings %T Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing %A Zemlyanskiy, Yury %A de Jong, Michiel %A Ainslie, Joshua %A Pasupat, Panupong %A Shaw, Peter %A Qiu, Linlu %A Sanghai, Sumit %A Sha, Fei %Y Calzolari, Nicoletta %Y Huang, Chu-Ren %Y Kim, Hansaem %Y Pustejovsky, James %Y Wanner, Leo %Y Choi, Key-Sun %Y Ryu, Pum-Mo %Y Chen, Hsin-Hsi %Y Donatelli, Lucia %Y Ji, Heng %Y Kurohashi, Sadao %Y Paggio, Patrizia %Y Xue, Nianwen %Y Kim, Seokhwan %Y Hahm, Younggyun %Y He, Zhong %Y Lee, Tony Kyungil %Y Santus, Enrico %Y Bond, Francis %Y Na, Seung-Hoon %S Proceedings of the 29th International Conference on Computational Linguistics %D 2022 %8 October %I International Committee on Computational Linguistics %C Gyeongju, Republic of Korea %F zemlyanskiy-etal-2022-generate %X A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative exemplars that help produce the correct parse, which is especially challenging in low-resource settings. Existing retrieval is commonly based on similarity of query and exemplar inputs. We propose GandR, a retrieval procedure that retrieves exemplars for which outputs are also similar. GandR first generates a preliminary prediction with input-based retrieval. Then, it retrieves exemplars with outputs similar to the preliminary prediction which are used to generate a final prediction. GandR sets the state of the art on multiple low-resource semantic parsing tasks. %U https://aclanthology.org/2022.coling-1.438 %P 4946-4951
Markdown (Informal)
[Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing](https://aclanthology.org/2022.coling-1.438) (Zemlyanskiy et al., COLING 2022)
- Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing (Zemlyanskiy et al., COLING 2022)
ACL
- Yury Zemlyanskiy, Michiel de Jong, Joshua Ainslie, Panupong Pasupat, Peter Shaw, Linlu Qiu, Sumit Sanghai, and Fei Sha. 2022. Generate-and-Retrieve: Use Your Predictions to Improve Retrieval for Semantic Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4946–4951, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.