Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003308145> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3003308145 abstract "We present our work on Track 4 in the Dialogue System Technology Challenges 8 (DSTC8). The DSTC8-Track 4 aims to perform dialogue state tracking (DST) under the zero-shot settings, in which the model needs to generalize on unseen service APIs given a schema definition of these target APIs. Serving as the core for many virtual assistants such as Siri, Alexa, and Google Assistant, the DST keeps track of the user's goal and what happened in the dialogue history, mainly including intent prediction, slot filling, and user state tracking, which tests models' ability of natural language understanding. Recently, the pretrained language models have achieved state-of-the-art results and shown impressive generalization ability on various NLP tasks, which provide a promising way to perform zero-shot learning for language understanding. Based on this, we propose a schema-guided paradigm for zero-shot dialogue state tracking (SGP-DST) by fine-tuning BERT, one of the most popular pretrained language models. The SGP-DST system contains four modules for intent prediction, slot prediction, slot transfer prediction, and user state summarizing respectively. According to the official evaluation results, our SGP-DST (team12) ranked 3rd on the joint goal accuracy (primary evaluation metric for ranking submissions) and 1st on the requsted slots F1 among 25 participant teams." @default.
- W3003308145 created "2020-02-07" @default.
- W3003308145 creator A5005572782 @default.
- W3003308145 creator A5054105228 @default.
- W3003308145 creator A5059767940 @default.
- W3003308145 creator A5060107207 @default.
- W3003308145 date "2020-02-01" @default.
- W3003308145 modified "2023-09-27" @default.
- W3003308145 title "Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking." @default.
- W3003308145 cites W2251058040 @default.
- W3003308145 cites W2748594250 @default.
- W3003308145 cites W2749436976 @default.
- W3003308145 cites W2784070054 @default.
- W3003308145 cites W2888849322 @default.
- W3003308145 cites W2962739339 @default.
- W3003308145 cites W2963341956 @default.
- W3003308145 cites W2963578915 @default.
- W3003308145 cites W2964101860 @default.
- W3003308145 cites W2964236684 @default.
- W3003308145 cites W2970597249 @default.
- W3003308145 cites W2997771882 @default.
- W3003308145 hasPublicationYear "2020" @default.
- W3003308145 type Work @default.
- W3003308145 sameAs 3003308145 @default.
- W3003308145 citedByCount "5" @default.
- W3003308145 countsByYear W30033081452020 @default.
- W3003308145 countsByYear W30033081452021 @default.
- W3003308145 countsByYear W30033081452022 @default.
- W3003308145 crossrefType "posted-content" @default.
- W3003308145 hasAuthorship W3003308145A5005572782 @default.
- W3003308145 hasAuthorship W3003308145A5054105228 @default.
- W3003308145 hasAuthorship W3003308145A5059767940 @default.
- W3003308145 hasAuthorship W3003308145A5060107207 @default.
- W3003308145 hasConcept C119857082 @default.
- W3003308145 hasConcept C137293760 @default.
- W3003308145 hasConcept C154945302 @default.
- W3003308145 hasConcept C204321447 @default.
- W3003308145 hasConcept C41008148 @default.
- W3003308145 hasConcept C52146309 @default.
- W3003308145 hasConceptScore W3003308145C119857082 @default.
- W3003308145 hasConceptScore W3003308145C137293760 @default.
- W3003308145 hasConceptScore W3003308145C154945302 @default.
- W3003308145 hasConceptScore W3003308145C204321447 @default.
- W3003308145 hasConceptScore W3003308145C41008148 @default.
- W3003308145 hasConceptScore W3003308145C52146309 @default.
- W3003308145 hasLocation W30033081451 @default.
- W3003308145 hasOpenAccess W3003308145 @default.
- W3003308145 hasPrimaryLocation W30033081451 @default.
- W3003308145 hasRelatedWork W1606936740 @default.
- W3003308145 hasRelatedWork W2137998396 @default.
- W3003308145 hasRelatedWork W2433730358 @default.
- W3003308145 hasRelatedWork W2791220943 @default.
- W3003308145 hasRelatedWork W2940836789 @default.
- W3003308145 hasRelatedWork W2963201498 @default.
- W3003308145 hasRelatedWork W2965998974 @default.
- W3003308145 hasRelatedWork W2968289115 @default.
- W3003308145 hasRelatedWork W2980362680 @default.
- W3003308145 hasRelatedWork W2994958991 @default.
- W3003308145 hasRelatedWork W3018752902 @default.
- W3003308145 hasRelatedWork W3045812080 @default.
- W3003308145 hasRelatedWork W3071356955 @default.
- W3003308145 hasRelatedWork W3090305424 @default.
- W3003308145 hasRelatedWork W3100921056 @default.
- W3003308145 hasRelatedWork W3110971054 @default.
- W3003308145 hasRelatedWork W3169793187 @default.
- W3003308145 hasRelatedWork W3172545652 @default.
- W3003308145 hasRelatedWork W3197874349 @default.
- W3003308145 hasRelatedWork W7965686 @default.
- W3003308145 isParatext "false" @default.
- W3003308145 isRetracted "false" @default.
- W3003308145 magId "3003308145" @default.
- W3003308145 workType "article" @default.