Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962939608> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2962939608 abstract "Distant supervision has become the standard method for relation extraction. However, even though it is an efficient method, it does not come at no cost—The resulted distantly-supervised training samples are often very noisy. To combat the noise, most of the recent state-of-the-art approaches focus on selecting one-best sentence or calculating soft attention weights over the set of the sentences of one specific entity pair. However, these methods are suboptimal, and the false positive problem is still a key stumbling bottleneck for the performance. We argue that those incorrectly-labeled candidate sentences must be treated with a hard decision, rather than being dealt with soft attention weights. To do this, our paper describes a radical solution—We explore a deep reinforcement learning strategy to generate the false-positive indicator, where we automatically recognize false positives for each relation type without any supervised information. Unlike the removal operation in the previous studies, we redistribute them into the negative examples. The experimental results show that the proposed strategy significantly improves the performance of distant supervision comparing to state-of-the-art systems." @default.
- W2962939608 created "2019-07-30" @default.
- W2962939608 creator A5016651990 @default.
- W2962939608 creator A5050195037 @default.
- W2962939608 creator A5066488435 @default.
- W2962939608 date "2018-01-01" @default.
- W2962939608 modified "2023-10-06" @default.
- W2962939608 title "Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning" @default.
- W2962939608 cites W1551842868 @default.
- W2962939608 cites W1604644367 @default.
- W2962939608 cites W174427690 @default.
- W2962939608 cites W1757796397 @default.
- W2962939608 cites W1981082061 @default.
- W2962939608 cites W2023352384 @default.
- W2962939608 cites W2053238041 @default.
- W2962939608 cites W2096765155 @default.
- W2962939608 cites W2107598941 @default.
- W2962939608 cites W2132679783 @default.
- W2962939608 cites W2155454737 @default.
- W2962939608 cites W2163362093 @default.
- W2962939608 cites W2250521169 @default.
- W2962939608 cites W2250575108 @default.
- W2962939608 cites W2251135946 @default.
- W2962939608 cites W2257979135 @default.
- W2962939608 cites W2515462165 @default.
- W2962939608 cites W2604610161 @default.
- W2962939608 cites W2745868649 @default.
- W2962939608 cites W2951274974 @default.
- W2962939608 cites W2963696295 @default.
- W2962939608 doi "https://doi.org/10.18653/v1/p18-1199" @default.
- W2962939608 hasPublicationYear "2018" @default.
- W2962939608 type Work @default.
- W2962939608 sameAs 2962939608 @default.
- W2962939608 citedByCount "163" @default.
- W2962939608 countsByYear W29629396082018 @default.
- W2962939608 countsByYear W29629396082019 @default.
- W2962939608 countsByYear W29629396082020 @default.
- W2962939608 countsByYear W29629396082021 @default.
- W2962939608 countsByYear W29629396082022 @default.
- W2962939608 countsByYear W29629396082023 @default.
- W2962939608 crossrefType "proceedings-article" @default.
- W2962939608 hasAuthorship W2962939608A5016651990 @default.
- W2962939608 hasAuthorship W2962939608A5050195037 @default.
- W2962939608 hasAuthorship W2962939608A5066488435 @default.
- W2962939608 hasBestOaLocation W29629396081 @default.
- W2962939608 hasConcept C115961682 @default.
- W2962939608 hasConcept C119857082 @default.
- W2962939608 hasConcept C124101348 @default.
- W2962939608 hasConcept C149635348 @default.
- W2962939608 hasConcept C153604712 @default.
- W2962939608 hasConcept C154945302 @default.
- W2962939608 hasConcept C177264268 @default.
- W2962939608 hasConcept C195807954 @default.
- W2962939608 hasConcept C199360897 @default.
- W2962939608 hasConcept C25343380 @default.
- W2962939608 hasConcept C2777530160 @default.
- W2962939608 hasConcept C2780513914 @default.
- W2962939608 hasConcept C41008148 @default.
- W2962939608 hasConcept C64869954 @default.
- W2962939608 hasConcept C97541855 @default.
- W2962939608 hasConcept C99498987 @default.
- W2962939608 hasConceptScore W2962939608C115961682 @default.
- W2962939608 hasConceptScore W2962939608C119857082 @default.
- W2962939608 hasConceptScore W2962939608C124101348 @default.
- W2962939608 hasConceptScore W2962939608C149635348 @default.
- W2962939608 hasConceptScore W2962939608C153604712 @default.
- W2962939608 hasConceptScore W2962939608C154945302 @default.
- W2962939608 hasConceptScore W2962939608C177264268 @default.
- W2962939608 hasConceptScore W2962939608C195807954 @default.
- W2962939608 hasConceptScore W2962939608C199360897 @default.
- W2962939608 hasConceptScore W2962939608C25343380 @default.
- W2962939608 hasConceptScore W2962939608C2777530160 @default.
- W2962939608 hasConceptScore W2962939608C2780513914 @default.
- W2962939608 hasConceptScore W2962939608C41008148 @default.
- W2962939608 hasConceptScore W2962939608C64869954 @default.
- W2962939608 hasConceptScore W2962939608C97541855 @default.
- W2962939608 hasConceptScore W2962939608C99498987 @default.
- W2962939608 hasLocation W29629396081 @default.
- W2962939608 hasLocation W29629396082 @default.
- W2962939608 hasOpenAccess W2962939608 @default.
- W2962939608 hasPrimaryLocation W29629396081 @default.
- W2962939608 hasRelatedWork W1904009680 @default.
- W2962939608 hasRelatedWork W2770047107 @default.
- W2962939608 hasRelatedWork W2947903144 @default.
- W2962939608 hasRelatedWork W3021392770 @default.
- W2962939608 hasRelatedWork W3030068568 @default.
- W2962939608 hasRelatedWork W3185518029 @default.
- W2962939608 hasRelatedWork W4297909932 @default.
- W2962939608 hasRelatedWork W4319083788 @default.
- W2962939608 hasRelatedWork W4376607254 @default.
- W2962939608 hasRelatedWork W4380136304 @default.
- W2962939608 isParatext "false" @default.
- W2962939608 isRetracted "false" @default.
- W2962939608 magId "2962939608" @default.
- W2962939608 workType "article" @default.