Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199832406> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3199832406 abstract "We study the problem of performing automatic stance classification on social media with neural architectures such as BERT. Although these architectures deliver impressive results, their level is not yet comparable to the one of humans and they might produce errors that have a significant impact on the downstream task (e.g., fact-checking). To improve the performance, we present a new neural architecture where the input also includes automatically generated negated perspectives over a given claim. The model is jointly learned to make simultaneously multiple predictions, which can be used either to improve the classification of the original perspective or to filter out doubtful predictions. In the first case, we propose a weakly supervised method for combining the predictions into a final one. In the second case, we show that using the confidence scores to remove doubtful predictions allows our method to achieve human-like performance over the retained information, which is still a sizable part of the original input." @default.
- W3199832406 created "2021-09-27" @default.
- W3199832406 creator A5025482368 @default.
- W3199832406 creator A5090620447 @default.
- W3199832406 date "2021-01-01" @default.
- W3199832406 modified "2023-10-18" @default.
- W3199832406 title "Tribrid: Stance Classification with Neural Inconsistency Detection" @default.
- W3199832406 cites W106870163 @default.
- W3199832406 cites W1532503642 @default.
- W3199832406 cites W1854537555 @default.
- W3199832406 cites W1967807490 @default.
- W3199832406 cites W2006834952 @default.
- W3199832406 cites W2084591134 @default.
- W3199832406 cites W2118677368 @default.
- W3199832406 cites W2143398792 @default.
- W3199832406 cites W2145327091 @default.
- W3199832406 cites W2150850338 @default.
- W3199832406 cites W2171590421 @default.
- W3199832406 cites W2251214593 @default.
- W3199832406 cites W2251635323 @default.
- W3199832406 cites W2252133813 @default.
- W3199832406 cites W2462365838 @default.
- W3199832406 cites W2566287401 @default.
- W3199832406 cites W2604265558 @default.
- W3199832406 cites W2607700676 @default.
- W3199832406 cites W2612605908 @default.
- W3199832406 cites W2735017898 @default.
- W3199832406 cites W2739836857 @default.
- W3199832406 cites W2741386817 @default.
- W3199832406 cites W2757749329 @default.
- W3199832406 cites W2767329425 @default.
- W3199832406 cites W2869686875 @default.
- W3199832406 cites W2887804579 @default.
- W3199832406 cites W2891177506 @default.
- W3199832406 cites W2915238810 @default.
- W3199832406 cites W2946364534 @default.
- W3199832406 cites W2950782805 @default.
- W3199832406 cites W2963058357 @default.
- W3199832406 cites W2963126845 @default.
- W3199832406 cites W2963277000 @default.
- W3199832406 cites W2963341956 @default.
- W3199832406 cites W2963661177 @default.
- W3199832406 cites W2964130895 @default.
- W3199832406 cites W2964165804 @default.
- W3199832406 cites W2998277219 @default.
- W3199832406 cites W3015001695 @default.
- W3199832406 cites W3034454003 @default.
- W3199832406 cites W3034649382 @default.
- W3199832406 cites W3035436280 @default.
- W3199832406 cites W3035507081 @default.
- W3199832406 cites W3089631405 @default.
- W3199832406 cites W3099206234 @default.
- W3199832406 doi "https://doi.org/10.18653/v1/2021.emnlp-main.547" @default.
- W3199832406 hasPublicationYear "2021" @default.
- W3199832406 type Work @default.
- W3199832406 sameAs 3199832406 @default.
- W3199832406 citedByCount "1" @default.
- W3199832406 countsByYear W31998324062023 @default.
- W3199832406 crossrefType "proceedings-article" @default.
- W3199832406 hasAuthorship W3199832406A5025482368 @default.
- W3199832406 hasAuthorship W3199832406A5090620447 @default.
- W3199832406 hasBestOaLocation W31998324061 @default.
- W3199832406 hasConcept C153180895 @default.
- W3199832406 hasConcept C154945302 @default.
- W3199832406 hasConcept C41008148 @default.
- W3199832406 hasConcept C50644808 @default.
- W3199832406 hasConceptScore W3199832406C153180895 @default.
- W3199832406 hasConceptScore W3199832406C154945302 @default.
- W3199832406 hasConceptScore W3199832406C41008148 @default.
- W3199832406 hasConceptScore W3199832406C50644808 @default.
- W3199832406 hasLocation W31998324061 @default.
- W3199832406 hasLocation W31998324062 @default.
- W3199832406 hasLocation W31998324063 @default.
- W3199832406 hasOpenAccess W3199832406 @default.
- W3199832406 hasPrimaryLocation W31998324061 @default.
- W3199832406 hasRelatedWork W1978450727 @default.
- W3199832406 hasRelatedWork W2033914206 @default.
- W3199832406 hasRelatedWork W2146076056 @default.
- W3199832406 hasRelatedWork W2163831990 @default.
- W3199832406 hasRelatedWork W2378160586 @default.
- W3199832406 hasRelatedWork W2386387936 @default.
- W3199832406 hasRelatedWork W3003836766 @default.
- W3199832406 hasRelatedWork W3107474891 @default.
- W3199832406 hasRelatedWork W4244943737 @default.
- W3199832406 hasRelatedWork W2289108895 @default.
- W3199832406 isParatext "false" @default.
- W3199832406 isRetracted "false" @default.
- W3199832406 magId "3199832406" @default.
- W3199832406 workType "article" @default.