File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.18653/v1/2021.naacl-main.27
- Scopus: eid_2-s2.0-85113648482
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition
| Title | Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition |
|---|---|
| Authors | |
| Issue Date | 2021 |
| Publisher | Association for Computational Linguistics |
| Citation | 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2021), Virtual, Online, 6-11 June 2021. In NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, 2021, p. 289-295 How to Cite? |
| Abstract | We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances. |
| Persistent Identifier | http://hdl.handle.net/10722/321961 |
| ISBN |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Wang, Dingmin | - |
| dc.contributor.author | Lin, Chenghua | - |
| dc.contributor.author | Liu, Qi | - |
| dc.contributor.author | Wong, Kam Fai | - |
| dc.date.accessioned | 2022-11-03T02:22:39Z | - |
| dc.date.available | 2022-11-03T02:22:39Z | - |
| dc.date.issued | 2021 | - |
| dc.identifier.citation | 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2021), Virtual, Online, 6-11 June 2021. In NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, 2021, p. 289-295 | - |
| dc.identifier.isbn | 9781954085466 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/321961 | - |
| dc.description.abstract | We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances. | - |
| dc.language | eng | - |
| dc.publisher | Association for Computational Linguistics | - |
| dc.relation.ispartof | NAACL-HLT 2021 - 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference | - |
| dc.title | Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition | - |
| dc.type | Conference_Paper | - |
| dc.description.nature | link_to_OA_fulltext | - |
| dc.identifier.doi | 10.18653/v1/2021.naacl-main.27 | - |
| dc.identifier.scopus | eid_2-s2.0-85113648482 | - |
| dc.identifier.spage | 289 | - |
| dc.identifier.epage | 295 | - |
| dc.publisher.place | Stroudsburg, PA | - |