Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100995786> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3100995786 abstract "Virtual assistants such as Google Assistant, Amazon Alexa, and Apple Siri enable users to interact with a large number of services and APIs on the web using natural language. In this work, we investigate two methods for Natural Language Generation (NLG) using a single domain-independent model across a large number of APIs. First, we propose a schema-guided approach which conditions the generation on a schema describing the API in natural language. Our second method investigates the use of a small number of templates, growing linearly in number of slots, to convey the semantics of the API. To generate utterances for an arbitrary slot combination, a few simple templates are first concatenated to give a semantically correct, but possibly incoherent and ungrammatical utterance. A pre-trained language model is subsequently employed to rewrite it into coherent, natural sounding text. Through automatic metrics and human evaluation, we show that our method improves over strong baselines, is robust to out-of-domain inputs and shows improved sample efficiency." @default.
- W3100995786 created "2020-11-23" @default.
- W3100995786 creator A5002931312 @default.
- W3100995786 creator A5087687501 @default.
- W3100995786 date "2020-01-01" @default.
- W3100995786 modified "2023-10-18" @default.
- W3100995786 title "Template Guided Text Generation for Task-Oriented Dialogue" @default.
- W3100995786 cites W1956340063 @default.
- W3100995786 cites W2012561700 @default.
- W3100995786 cites W2078861931 @default.
- W3100995786 cites W2101105183 @default.
- W3100995786 cites W2133512280 @default.
- W3100995786 cites W2154652894 @default.
- W3100995786 cites W2291723583 @default.
- W3100995786 cites W2748261613 @default.
- W3100995786 cites W2786660442 @default.
- W3100995786 cites W2798542795 @default.
- W3100995786 cites W2879018339 @default.
- W3100995786 cites W2891732163 @default.
- W3100995786 cites W2952013107 @default.
- W3100995786 cites W2953071719 @default.
- W3100995786 cites W2963018920 @default.
- W3100995786 cites W2963091658 @default.
- W3100995786 cites W2963341956 @default.
- W3100995786 cites W2963371754 @default.
- W3100995786 cites W2963578915 @default.
- W3100995786 cites W2963912046 @default.
- W3100995786 cites W2964588180 @default.
- W3100995786 cites W2965373594 @default.
- W3100995786 cites W2970444947 @default.
- W3100995786 cites W2970597249 @default.
- W3100995786 cites W2973049837 @default.
- W3100995786 cites W2994963504 @default.
- W3100995786 cites W2996176596 @default.
- W3100995786 cites W2997771882 @default.
- W3100995786 cites W3014391559 @default.
- W3100995786 cites W3035565536 @default.
- W3100995786 cites W3082274269 @default.
- W3100995786 cites W3102854726 @default.
- W3100995786 cites W3115264425 @default.
- W3100995786 doi "https://doi.org/10.18653/v1/2020.emnlp-main.527" @default.
- W3100995786 hasPublicationYear "2020" @default.
- W3100995786 type Work @default.
- W3100995786 sameAs 3100995786 @default.
- W3100995786 citedByCount "22" @default.
- W3100995786 countsByYear W31009957862021 @default.
- W3100995786 countsByYear W31009957862022 @default.
- W3100995786 countsByYear W31009957862023 @default.
- W3100995786 crossrefType "proceedings-article" @default.
- W3100995786 hasAuthorship W3100995786A5002931312 @default.
- W3100995786 hasAuthorship W3100995786A5087687501 @default.
- W3100995786 hasBestOaLocation W31009957861 @default.
- W3100995786 hasConcept C154945302 @default.
- W3100995786 hasConcept C162324750 @default.
- W3100995786 hasConcept C187736073 @default.
- W3100995786 hasConcept C195324797 @default.
- W3100995786 hasConcept C199360897 @default.
- W3100995786 hasConcept C204321447 @default.
- W3100995786 hasConcept C23123220 @default.
- W3100995786 hasConcept C2775852435 @default.
- W3100995786 hasConcept C2776187449 @default.
- W3100995786 hasConcept C2779439875 @default.
- W3100995786 hasConcept C2780451532 @default.
- W3100995786 hasConcept C41008148 @default.
- W3100995786 hasConcept C52146309 @default.
- W3100995786 hasConcept C82714645 @default.
- W3100995786 hasConceptScore W3100995786C154945302 @default.
- W3100995786 hasConceptScore W3100995786C162324750 @default.
- W3100995786 hasConceptScore W3100995786C187736073 @default.
- W3100995786 hasConceptScore W3100995786C195324797 @default.
- W3100995786 hasConceptScore W3100995786C199360897 @default.
- W3100995786 hasConceptScore W3100995786C204321447 @default.
- W3100995786 hasConceptScore W3100995786C23123220 @default.
- W3100995786 hasConceptScore W3100995786C2775852435 @default.
- W3100995786 hasConceptScore W3100995786C2776187449 @default.
- W3100995786 hasConceptScore W3100995786C2779439875 @default.
- W3100995786 hasConceptScore W3100995786C2780451532 @default.
- W3100995786 hasConceptScore W3100995786C41008148 @default.
- W3100995786 hasConceptScore W3100995786C52146309 @default.
- W3100995786 hasConceptScore W3100995786C82714645 @default.
- W3100995786 hasLocation W31009957861 @default.
- W3100995786 hasLocation W31009957862 @default.
- W3100995786 hasOpenAccess W3100995786 @default.
- W3100995786 hasPrimaryLocation W31009957861 @default.
- W3100995786 hasRelatedWork W2168034451 @default.
- W3100995786 hasRelatedWork W252643666 @default.
- W3100995786 hasRelatedWork W2575772232 @default.
- W3100995786 hasRelatedWork W2587329402 @default.
- W3100995786 hasRelatedWork W2886693075 @default.
- W3100995786 hasRelatedWork W2977842567 @default.
- W3100995786 hasRelatedWork W3020827637 @default.
- W3100995786 hasRelatedWork W3036725988 @default.
- W3100995786 hasRelatedWork W3101203785 @default.
- W3100995786 hasRelatedWork W4287803315 @default.
- W3100995786 isParatext "false" @default.
- W3100995786 isRetracted "false" @default.
- W3100995786 magId "3100995786" @default.
- W3100995786 workType "article" @default.