Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136000054> ?p ?o ?g. }
- W3136000054 abstract "Recognizing relations between entities is a pivotal task of relational learning. Learning relation representations from distantly-labeled datasets is difficult because of the abundant label noise and complicated expressions in human language. This paper aims to learn predictive, interpretable, and robust relation representations from distantly-labeled data that are effective in different settings, including supervised, distantly supervised, and few-shot learning. Instead of solely relying on the supervision from noisy labels, we propose to learn prototypes for each relation from contextual information to best explore the intrinsic semantics of relations. Prototypes are representations in the feature space abstracting the essential semantics of relations between entities in sentences. We learn prototypes based on objectives with clear geometric interpretation, where the prototypes are unit vectors uniformly dispersed in a unit ball, and statement embeddings are centered at the end of their corresponding prototype vectors on the surface of the ball. This approach allows us to learn meaningful, interpretable prototypes for the final classification. Results on several relation learning tasks show that our model significantly outperforms the previous state-of-the-art models. We further demonstrate the robustness of the encoder and the interpretability of prototypes with extensive experiments." @default.
- W3136000054 created "2021-03-29" @default.
- W3136000054 creator A5005535444 @default.
- W3136000054 creator A5013292507 @default.
- W3136000054 creator A5022672030 @default.
- W3136000054 creator A5029873349 @default.
- W3136000054 creator A5065037360 @default.
- W3136000054 creator A5070812231 @default.
- W3136000054 creator A5073840778 @default.
- W3136000054 creator A5074799043 @default.
- W3136000054 creator A5091640552 @default.
- W3136000054 creator A5091877711 @default.
- W3136000054 date "2021-03-22" @default.
- W3136000054 modified "2023-09-27" @default.
- W3136000054 title "Prototypical Representation Learning for Relation Extraction" @default.
- W3136000054 cites W143521272 @default.
- W3136000054 cites W1493490255 @default.
- W3136000054 cites W1529875955 @default.
- W3136000054 cites W1604644367 @default.
- W3136000054 cites W1750263989 @default.
- W3136000054 cites W2052059088 @default.
- W3136000054 cites W2059799772 @default.
- W3136000054 cites W2099779943 @default.
- W3136000054 cites W2103931177 @default.
- W3136000054 cites W2107598941 @default.
- W3136000054 cites W2127795553 @default.
- W3136000054 cites W2129842875 @default.
- W3136000054 cites W2141545068 @default.
- W3136000054 cites W2145544171 @default.
- W3136000054 cites W2163362093 @default.
- W3136000054 cites W2167187514 @default.
- W3136000054 cites W2184957013 @default.
- W3136000054 cites W2187089797 @default.
- W3136000054 cites W2250342289 @default.
- W3136000054 cites W2251135946 @default.
- W3136000054 cites W2251913848 @default.
- W3136000054 cites W2283196293 @default.
- W3136000054 cites W2336681149 @default.
- W3136000054 cites W2577666659 @default.
- W3136000054 cites W2601450892 @default.
- W3136000054 cites W2604314403 @default.
- W3136000054 cites W2620968868 @default.
- W3136000054 cites W2624677889 @default.
- W3136000054 cites W2626778328 @default.
- W3136000054 cites W2725395424 @default.
- W3136000054 cites W2760600531 @default.
- W3136000054 cites W2768282280 @default.
- W3136000054 cites W2775300540 @default.
- W3136000054 cites W2788798739 @default.
- W3136000054 cites W2798507918 @default.
- W3136000054 cites W2804311790 @default.
- W3136000054 cites W2896457183 @default.
- W3136000054 cites W2897509371 @default.
- W3136000054 cites W2909137510 @default.
- W3136000054 cites W2948131150 @default.
- W3136000054 cites W2950118387 @default.
- W3136000054 cites W2950371387 @default.
- W3136000054 cites W2951193785 @default.
- W3136000054 cites W2951525151 @default.
- W3136000054 cites W2970971581 @default.
- W3136000054 cites W2971104547 @default.
- W3136000054 cites W3003507729 @default.
- W3136000054 cites W3099708324 @default.
- W3136000054 hasPublicationYear "2021" @default.
- W3136000054 type Work @default.
- W3136000054 sameAs 3136000054 @default.
- W3136000054 citedByCount "3" @default.
- W3136000054 countsByYear W31360000542021 @default.
- W3136000054 crossrefType "posted-content" @default.
- W3136000054 hasAuthorship W3136000054A5005535444 @default.
- W3136000054 hasAuthorship W3136000054A5013292507 @default.
- W3136000054 hasAuthorship W3136000054A5022672030 @default.
- W3136000054 hasAuthorship W3136000054A5029873349 @default.
- W3136000054 hasAuthorship W3136000054A5065037360 @default.
- W3136000054 hasAuthorship W3136000054A5070812231 @default.
- W3136000054 hasAuthorship W3136000054A5073840778 @default.
- W3136000054 hasAuthorship W3136000054A5074799043 @default.
- W3136000054 hasAuthorship W3136000054A5091640552 @default.
- W3136000054 hasAuthorship W3136000054A5091877711 @default.
- W3136000054 hasConcept C104317684 @default.
- W3136000054 hasConcept C119857082 @default.
- W3136000054 hasConcept C124101348 @default.
- W3136000054 hasConcept C136389625 @default.
- W3136000054 hasConcept C153604712 @default.
- W3136000054 hasConcept C154945302 @default.
- W3136000054 hasConcept C177877439 @default.
- W3136000054 hasConcept C184337299 @default.
- W3136000054 hasConcept C185592680 @default.
- W3136000054 hasConcept C195807954 @default.
- W3136000054 hasConcept C199360897 @default.
- W3136000054 hasConcept C204321447 @default.
- W3136000054 hasConcept C25343380 @default.
- W3136000054 hasConcept C2781067378 @default.
- W3136000054 hasConcept C41008148 @default.
- W3136000054 hasConcept C50644808 @default.
- W3136000054 hasConcept C55493867 @default.
- W3136000054 hasConcept C5655090 @default.
- W3136000054 hasConcept C59404180 @default.
- W3136000054 hasConcept C63479239 @default.
- W3136000054 hasConceptScore W3136000054C104317684 @default.