Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100468923> ?p ?o ?g. }
- W3100468923 abstract "Answering questions in many real-world applications often requires complex and precise information excerpted from texts spanned across a long document. However, currently no such annotated dataset is publicly available, which hinders the development of neural question-answering (QA) systems. To this end, we present MASH-QA, a Multiple Answer Spans Healthcare Question Answering dataset from the consumer health domain, where answers may need to be excerpted from multiple, non-consecutive parts of text spanned across a long document. We also propose MultiCo, a neural architecture that is able to capture the relevance among multiple answer spans, by using a query-based contextualized sentence selection approach, for forming the answer to the given question. We also demonstrate that conventional QA models are not suitable for this type of task and perform poorly in this setting. Extensive experiments are conducted, and the experimental results confirm the proposed model significantly outperforms the state-of-the-art QA models in this multi-span QA setting." @default.
- W3100468923 created "2020-11-23" @default.
- W3100468923 creator A5001022750 @default.
- W3100468923 creator A5002327825 @default.
- W3100468923 creator A5003799076 @default.
- W3100468923 creator A5005730523 @default.
- W3100468923 creator A5060613396 @default.
- W3100468923 date "2020-01-01" @default.
- W3100468923 modified "2023-10-14" @default.
- W3100468923 title "Question Answering with Long Multiple-Span Answers" @default.
- W3100468923 cites W1591825359 @default.
- W3100468923 cites W2251818205 @default.
- W3100468923 cites W2551396370 @default.
- W3100468923 cites W2609826708 @default.
- W3100468923 cites W2891113091 @default.
- W3100468923 cites W2912924812 @default.
- W3100468923 cites W2913352150 @default.
- W3100468923 cites W2913640436 @default.
- W3100468923 cites W2948947170 @default.
- W3100468923 cites W2950681488 @default.
- W3100468923 cites W2950858167 @default.
- W3100468923 cites W2953384591 @default.
- W3100468923 cites W2963323070 @default.
- W3100468923 cites W2963339397 @default.
- W3100468923 cites W2963341956 @default.
- W3100468923 cites W2963386218 @default.
- W3100468923 cites W2963506049 @default.
- W3100468923 cites W2963748441 @default.
- W3100468923 cites W2963773425 @default.
- W3100468923 cites W2963871484 @default.
- W3100468923 cites W2963963993 @default.
- W3100468923 cites W2964110616 @default.
- W3100468923 cites W2964121744 @default.
- W3100468923 cites W2964223283 @default.
- W3100468923 cites W2965373594 @default.
- W3100468923 cites W2970597249 @default.
- W3100468923 cites W2970777192 @default.
- W3100468923 cites W2997090102 @default.
- W3100468923 cites W3011411500 @default.
- W3100468923 doi "https://doi.org/10.18653/v1/2020.findings-emnlp.342" @default.
- W3100468923 hasPublicationYear "2020" @default.
- W3100468923 type Work @default.
- W3100468923 sameAs 3100468923 @default.
- W3100468923 citedByCount "18" @default.
- W3100468923 countsByYear W31004689232021 @default.
- W3100468923 countsByYear W31004689232022 @default.
- W3100468923 countsByYear W31004689232023 @default.
- W3100468923 crossrefType "proceedings-article" @default.
- W3100468923 hasAuthorship W3100468923A5001022750 @default.
- W3100468923 hasAuthorship W3100468923A5002327825 @default.
- W3100468923 hasAuthorship W3100468923A5003799076 @default.
- W3100468923 hasAuthorship W3100468923A5005730523 @default.
- W3100468923 hasAuthorship W3100468923A5060613396 @default.
- W3100468923 hasBestOaLocation W31004689231 @default.
- W3100468923 hasConcept C123657996 @default.
- W3100468923 hasConcept C127413603 @default.
- W3100468923 hasConcept C134306372 @default.
- W3100468923 hasConcept C142362112 @default.
- W3100468923 hasConcept C147176958 @default.
- W3100468923 hasConcept C153349607 @default.
- W3100468923 hasConcept C154945302 @default.
- W3100468923 hasConcept C158154518 @default.
- W3100468923 hasConcept C162324750 @default.
- W3100468923 hasConcept C17744445 @default.
- W3100468923 hasConcept C187736073 @default.
- W3100468923 hasConcept C199539241 @default.
- W3100468923 hasConcept C204321447 @default.
- W3100468923 hasConcept C23123220 @default.
- W3100468923 hasConcept C2777530160 @default.
- W3100468923 hasConcept C2778753569 @default.
- W3100468923 hasConcept C2780451532 @default.
- W3100468923 hasConcept C33923547 @default.
- W3100468923 hasConcept C36503486 @default.
- W3100468923 hasConcept C41008148 @default.
- W3100468923 hasConcept C44291984 @default.
- W3100468923 hasConcept C81917197 @default.
- W3100468923 hasConceptScore W3100468923C123657996 @default.
- W3100468923 hasConceptScore W3100468923C127413603 @default.
- W3100468923 hasConceptScore W3100468923C134306372 @default.
- W3100468923 hasConceptScore W3100468923C142362112 @default.
- W3100468923 hasConceptScore W3100468923C147176958 @default.
- W3100468923 hasConceptScore W3100468923C153349607 @default.
- W3100468923 hasConceptScore W3100468923C154945302 @default.
- W3100468923 hasConceptScore W3100468923C158154518 @default.
- W3100468923 hasConceptScore W3100468923C162324750 @default.
- W3100468923 hasConceptScore W3100468923C17744445 @default.
- W3100468923 hasConceptScore W3100468923C187736073 @default.
- W3100468923 hasConceptScore W3100468923C199539241 @default.
- W3100468923 hasConceptScore W3100468923C204321447 @default.
- W3100468923 hasConceptScore W3100468923C23123220 @default.
- W3100468923 hasConceptScore W3100468923C2777530160 @default.
- W3100468923 hasConceptScore W3100468923C2778753569 @default.
- W3100468923 hasConceptScore W3100468923C2780451532 @default.
- W3100468923 hasConceptScore W3100468923C33923547 @default.
- W3100468923 hasConceptScore W3100468923C36503486 @default.
- W3100468923 hasConceptScore W3100468923C41008148 @default.
- W3100468923 hasConceptScore W3100468923C44291984 @default.
- W3100468923 hasConceptScore W3100468923C81917197 @default.
- W3100468923 hasLocation W31004689231 @default.
- W3100468923 hasOpenAccess W3100468923 @default.