Matches in SemOpenAlex for { <https://semopenalex.org/work/W2767988314> ?p ?o ?g. }
- W2767988314 abstract "Extracting relations from text corpora is an important task in text mining. It becomes particularly challenging when focusing on weakly-supervised relation extraction, that is, utilizing a few relation instances (i.e., a pair of entities and their relation) as seeds to extract more instances from corpora. Existing distributional approaches leverage the corpus-level co-occurrence statistics of entities to predict their relations, and require large number of labeled instances to learn effective relation classifiers. Alternatively, pattern-based approaches perform bootstrapping or apply neural networks to model the local contexts, but still rely on large number of labeled instances to build reliable models. In this paper, we study integrating the distributional and pattern-based methods in a weakly-supervised setting, such that the two types of methods can provide complementary supervision for each other to build an effective, unified model. We propose a novel co-training framework with a distributional module and a pattern module. During training, the distributional module helps the pattern module discriminate between the informative patterns and other patterns, and the pattern module generates some highly-confident instances to improve the distributional module. The whole framework can be effectively optimized by iterating between improving the pattern module and updating the distributional module. We conduct experiments on two tasks: knowledge base completion with text corpora and corpus-level relation extraction. Experimental results prove the effectiveness of our framework in the weakly-supervised setting." @default.
- W2767988314 created "2017-11-17" @default.
- W2767988314 creator A5009024773 @default.
- W2767988314 creator A5009408707 @default.
- W2767988314 creator A5019539533 @default.
- W2767988314 creator A5071773009 @default.
- W2767988314 date "2017-11-09" @default.
- W2767988314 modified "2023-10-16" @default.
- W2767988314 title "Overcoming Limited Supervision in Relation Extraction: A Pattern-enhanced Distributional Representation Approach." @default.
- W2767988314 cites W1533230146 @default.
- W2767988314 cites W1852412531 @default.
- W2767988314 cites W1983320747 @default.
- W2767988314 cites W2000769684 @default.
- W2767988314 cites W2026810221 @default.
- W2767988314 cites W2048679005 @default.
- W2767988314 cites W2107598941 @default.
- W2767988314 cites W2120814856 @default.
- W2767988314 cites W2123442489 @default.
- W2767988314 cites W2125076245 @default.
- W2767988314 cites W2127795553 @default.
- W2767988314 cites W2129842875 @default.
- W2767988314 cites W2132679783 @default.
- W2767988314 cites W2138627627 @default.
- W2767988314 cites W2158028897 @default.
- W2767988314 cites W2163362093 @default.
- W2767988314 cites W2187127363 @default.
- W2767988314 cites W2250308783 @default.
- W2767988314 cites W2250342289 @default.
- W2767988314 cites W2250539671 @default.
- W2767988314 cites W2250635077 @default.
- W2767988314 cites W2251135946 @default.
- W2767988314 cites W2528865365 @default.
- W2767988314 cites W2539469848 @default.
- W2767988314 cites W2566831985 @default.
- W2767988314 cites W2950133940 @default.
- W2767988314 cites W2950577311 @default.
- W2767988314 cites W2953301452 @default.
- W2767988314 cites W2962724755 @default.
- W2767988314 cites W2963171262 @default.
- W2767988314 cites W2963374550 @default.
- W2767988314 cites W2963454301 @default.
- W2767988314 cites W2964217331 @default.
- W2767988314 cites W3104717349 @default.
- W2767988314 cites W3105705953 @default.
- W2767988314 hasPublicationYear "2017" @default.
- W2767988314 type Work @default.
- W2767988314 sameAs 2767988314 @default.
- W2767988314 citedByCount "1" @default.
- W2767988314 countsByYear W27679883142019 @default.
- W2767988314 crossrefType "posted-content" @default.
- W2767988314 hasAuthorship W2767988314A5009024773 @default.
- W2767988314 hasAuthorship W2767988314A5009408707 @default.
- W2767988314 hasAuthorship W2767988314A5019539533 @default.
- W2767988314 hasAuthorship W2767988314A5071773009 @default.
- W2767988314 hasConcept C119857082 @default.
- W2767988314 hasConcept C124101348 @default.
- W2767988314 hasConcept C149782125 @default.
- W2767988314 hasConcept C153083717 @default.
- W2767988314 hasConcept C153180895 @default.
- W2767988314 hasConcept C153604712 @default.
- W2767988314 hasConcept C154945302 @default.
- W2767988314 hasConcept C162324750 @default.
- W2767988314 hasConcept C17744445 @default.
- W2767988314 hasConcept C187736073 @default.
- W2767988314 hasConcept C199539241 @default.
- W2767988314 hasConcept C204321447 @default.
- W2767988314 hasConcept C207609745 @default.
- W2767988314 hasConcept C25343380 @default.
- W2767988314 hasConcept C2776145971 @default.
- W2767988314 hasConcept C2776359362 @default.
- W2767988314 hasConcept C2780451532 @default.
- W2767988314 hasConcept C33923547 @default.
- W2767988314 hasConcept C41008148 @default.
- W2767988314 hasConcept C94625758 @default.
- W2767988314 hasConceptScore W2767988314C119857082 @default.
- W2767988314 hasConceptScore W2767988314C124101348 @default.
- W2767988314 hasConceptScore W2767988314C149782125 @default.
- W2767988314 hasConceptScore W2767988314C153083717 @default.
- W2767988314 hasConceptScore W2767988314C153180895 @default.
- W2767988314 hasConceptScore W2767988314C153604712 @default.
- W2767988314 hasConceptScore W2767988314C154945302 @default.
- W2767988314 hasConceptScore W2767988314C162324750 @default.
- W2767988314 hasConceptScore W2767988314C17744445 @default.
- W2767988314 hasConceptScore W2767988314C187736073 @default.
- W2767988314 hasConceptScore W2767988314C199539241 @default.
- W2767988314 hasConceptScore W2767988314C204321447 @default.
- W2767988314 hasConceptScore W2767988314C207609745 @default.
- W2767988314 hasConceptScore W2767988314C25343380 @default.
- W2767988314 hasConceptScore W2767988314C2776145971 @default.
- W2767988314 hasConceptScore W2767988314C2776359362 @default.
- W2767988314 hasConceptScore W2767988314C2780451532 @default.
- W2767988314 hasConceptScore W2767988314C33923547 @default.
- W2767988314 hasConceptScore W2767988314C41008148 @default.
- W2767988314 hasConceptScore W2767988314C94625758 @default.
- W2767988314 hasLocation W27679883141 @default.
- W2767988314 hasOpenAccess W2767988314 @default.
- W2767988314 hasPrimaryLocation W27679883141 @default.
- W2767988314 hasRelatedWork W1988576742 @default.
- W2767988314 hasRelatedWork W1998660072 @default.
- W2767988314 hasRelatedWork W2060922297 @default.