Semantic parsing with semi-supervised sequential autoencoders
We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on doma...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Conference item |
| Published: |
Association for Computational Linguistics
2016
|
| _version_ | 1826257771553619968 |
|---|---|
| author | Kočiský, T Melis, G Grefenstette, E Dyer, C Ling, W Blunsom, P Hermann, K |
| author_facet | Kočiský, T Melis, G Grefenstette, E Dyer, C Ling, W Blunsom, P Hermann, K |
| author_sort | Kočiský, T |
| collection | OXFORD |
| description | We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on domains with limited access to labelled training data and extend those datasets with synthetically generated logical forms. |
| first_indexed | 2024-03-06T18:23:27Z |
| format | Conference item |
| id | oxford-uuid:071abf74-decf-421c-96e4-2b8724967fac |
| institution | University of Oxford |
| last_indexed | 2024-03-06T18:23:27Z |
| publishDate | 2016 |
| publisher | Association for Computational Linguistics |
| record_format | dspace |
| spelling | oxford-uuid:071abf74-decf-421c-96e4-2b8724967fac2022-03-26T09:05:57ZSemantic parsing with semi-supervised sequential autoencodersConference itemhttp://purl.org/coar/resource_type/c_5794uuid:071abf74-decf-421c-96e4-2b8724967facSymplectic Elements at OxfordAssociation for Computational Linguistics2016Kočiský, TMelis, GGrefenstette, EDyer, CLing, WBlunsom, PHermann, KWe present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on domains with limited access to labelled training data and extend those datasets with synthetically generated logical forms. |
| spellingShingle | Kočiský, T Melis, G Grefenstette, E Dyer, C Ling, W Blunsom, P Hermann, K Semantic parsing with semi-supervised sequential autoencoders |
| title | Semantic parsing with semi-supervised sequential autoencoders |
| title_full | Semantic parsing with semi-supervised sequential autoencoders |
| title_fullStr | Semantic parsing with semi-supervised sequential autoencoders |
| title_full_unstemmed | Semantic parsing with semi-supervised sequential autoencoders |
| title_short | Semantic parsing with semi-supervised sequential autoencoders |
| title_sort | semantic parsing with semi supervised sequential autoencoders |
| work_keys_str_mv | AT kociskyt semanticparsingwithsemisupervisedsequentialautoencoders AT melisg semanticparsingwithsemisupervisedsequentialautoencoders AT grefenstettee semanticparsingwithsemisupervisedsequentialautoencoders AT dyerc semanticparsingwithsemisupervisedsequentialautoencoders AT lingw semanticparsingwithsemisupervisedsequentialautoencoders AT blunsomp semanticparsingwithsemisupervisedsequentialautoencoders AT hermannk semanticparsingwithsemisupervisedsequentialautoencoders |