Matches in SemOpenAlex for { <https://semopenalex.org/work/W2592329103> ?p ?o ?g. }
- W2592329103 abstract "Fine-grained entity type classification (FETC) is the task of classifying an entity mention to a broad set of types. Distant supervision paradigm is extensively used to generate training data for this task. However, generated training data assigns same set of labels to every mention of an entity without considering its local context. Existing FETC systems have two major drawbacks: assuming training data to be noise free and use of hand crafted features. Our work overcomes both drawbacks. We propose a neural network model that jointly learns entity mentions and their context representation to eliminate use of hand crafted features. Our model treats training data as noisy and uses non-parametric variant of hinge loss function. Experiments show that the proposed model outperforms previous state-of-the-art methods on two publicly available datasets, namely FIGER (GOLD) and BBN with an average relative improvement of 2.69% in micro-F1 score. Knowledge learnt by our model on one dataset can be transferred to other datasets while using same model or other FETC systems. These approaches of transferring knowledge further improve the performance of respective models." @default.
- W2592329103 created "2017-03-16" @default.
- W2592329103 creator A5000346770 @default.
- W2592329103 creator A5040626471 @default.
- W2592329103 creator A5063234710 @default.
- W2592329103 date "2017-01-01" @default.
- W2592329103 modified "2023-09-25" @default.
- W2592329103 title "Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings" @default.
- W2592329103 cites W102708294 @default.
- W2592329103 cites W1818534184 @default.
- W2592329103 cites W1954715867 @default.
- W2592329103 cites W2004763266 @default.
- W2592329103 cites W2016753842 @default.
- W2592329103 cites W2022166150 @default.
- W2592329103 cites W2026810221 @default.
- W2592329103 cites W2064675550 @default.
- W2592329103 cites W2070246124 @default.
- W2592329103 cites W2094728533 @default.
- W2592329103 cites W2106837051 @default.
- W2592329103 cites W2107598941 @default.
- W2592329103 cites W2123442489 @default.
- W2592329103 cites W2124807415 @default.
- W2592329103 cites W2143612262 @default.
- W2592329103 cites W2144578941 @default.
- W2592329103 cites W2148861942 @default.
- W2592329103 cites W2149746394 @default.
- W2592329103 cites W2236405165 @default.
- W2592329103 cites W2250539671 @default.
- W2592329103 cites W2250718161 @default.
- W2592329103 cites W2251264718 @default.
- W2592329103 cites W2406945108 @default.
- W2592329103 cites W2564425030 @default.
- W2592329103 cites W2785349534 @default.
- W2592329103 cites W2963522845 @default.
- W2592329103 cites W2964121744 @default.
- W2592329103 cites W2964330146 @default.
- W2592329103 cites W3126976873 @default.
- W2592329103 cites W591148856 @default.
- W2592329103 cites W638568100 @default.
- W2592329103 doi "https://doi.org/10.18653/v1/e17-1075" @default.
- W2592329103 hasPublicationYear "2017" @default.
- W2592329103 type Work @default.
- W2592329103 sameAs 2592329103 @default.
- W2592329103 citedByCount "72" @default.
- W2592329103 countsByYear W25923291032018 @default.
- W2592329103 countsByYear W25923291032019 @default.
- W2592329103 countsByYear W25923291032020 @default.
- W2592329103 countsByYear W25923291032021 @default.
- W2592329103 countsByYear W25923291032022 @default.
- W2592329103 countsByYear W25923291032023 @default.
- W2592329103 crossrefType "proceedings-article" @default.
- W2592329103 hasAuthorship W2592329103A5000346770 @default.
- W2592329103 hasAuthorship W2592329103A5040626471 @default.
- W2592329103 hasAuthorship W2592329103A5063234710 @default.
- W2592329103 hasBestOaLocation W25923291031 @default.
- W2592329103 hasConcept C105795698 @default.
- W2592329103 hasConcept C115961682 @default.
- W2592329103 hasConcept C117251300 @default.
- W2592329103 hasConcept C119857082 @default.
- W2592329103 hasConcept C124101348 @default.
- W2592329103 hasConcept C14036430 @default.
- W2592329103 hasConcept C151730666 @default.
- W2592329103 hasConcept C153180895 @default.
- W2592329103 hasConcept C154945302 @default.
- W2592329103 hasConcept C162324750 @default.
- W2592329103 hasConcept C177264268 @default.
- W2592329103 hasConcept C17744445 @default.
- W2592329103 hasConcept C187736073 @default.
- W2592329103 hasConcept C199360897 @default.
- W2592329103 hasConcept C199539241 @default.
- W2592329103 hasConcept C2776359362 @default.
- W2592329103 hasConcept C2776482837 @default.
- W2592329103 hasConcept C2779343474 @default.
- W2592329103 hasConcept C2780451532 @default.
- W2592329103 hasConcept C33923547 @default.
- W2592329103 hasConcept C41008148 @default.
- W2592329103 hasConcept C50644808 @default.
- W2592329103 hasConcept C51632099 @default.
- W2592329103 hasConcept C78458016 @default.
- W2592329103 hasConcept C86803240 @default.
- W2592329103 hasConcept C94625758 @default.
- W2592329103 hasConcept C99498987 @default.
- W2592329103 hasConceptScore W2592329103C105795698 @default.
- W2592329103 hasConceptScore W2592329103C115961682 @default.
- W2592329103 hasConceptScore W2592329103C117251300 @default.
- W2592329103 hasConceptScore W2592329103C119857082 @default.
- W2592329103 hasConceptScore W2592329103C124101348 @default.
- W2592329103 hasConceptScore W2592329103C14036430 @default.
- W2592329103 hasConceptScore W2592329103C151730666 @default.
- W2592329103 hasConceptScore W2592329103C153180895 @default.
- W2592329103 hasConceptScore W2592329103C154945302 @default.
- W2592329103 hasConceptScore W2592329103C162324750 @default.
- W2592329103 hasConceptScore W2592329103C177264268 @default.
- W2592329103 hasConceptScore W2592329103C17744445 @default.
- W2592329103 hasConceptScore W2592329103C187736073 @default.
- W2592329103 hasConceptScore W2592329103C199360897 @default.
- W2592329103 hasConceptScore W2592329103C199539241 @default.
- W2592329103 hasConceptScore W2592329103C2776359362 @default.
- W2592329103 hasConceptScore W2592329103C2776482837 @default.
- W2592329103 hasConceptScore W2592329103C2779343474 @default.