Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890436498> ?p ?o ?g. }
- W2890436498 abstract "Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions. Previous studies address this problem by discovering a shared space across genres using manually crafted features, which requires great human effort. To effectively automate this process, we design a genre-separation network, which applies two encoders, one genre-independent and one genre-shared, to explicitly extract genre-specific and genre-agnostic features. Then we train a relation classifier using the genre-agnostic features on the source genre and directly apply to the target genre. Experiment results on three distinct genres of the ACE dataset show that our approach achieves up to 6.1% absolute F1-score gain compared to previous methods. By incorporating a set of external linguistic features, our approach outperforms the state-of-the-art by 1.7% absolute F1 gain. We make all programs of our model publicly available for research purpose" @default.
- W2890436498 created "2018-09-27" @default.
- W2890436498 creator A5035304642 @default.
- W2890436498 creator A5042819803 @default.
- W2890436498 creator A5044196762 @default.
- W2890436498 creator A5062124133 @default.
- W2890436498 creator A5066140774 @default.
- W2890436498 creator A5075033889 @default.
- W2890436498 creator A5087631670 @default.
- W2890436498 date "2018-01-01" @default.
- W2890436498 modified "2023-10-02" @default.
- W2890436498 title "Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction" @default.
- W2890436498 cites W114517082 @default.
- W2890436498 cites W1731081199 @default.
- W2890436498 cites W1849277567 @default.
- W2890436498 cites W2124964692 @default.
- W2890436498 cites W2136502946 @default.
- W2890436498 cites W2138627627 @default.
- W2890436498 cites W2181629536 @default.
- W2890436498 cites W2240668419 @default.
- W2890436498 cites W2250646484 @default.
- W2890436498 cites W2294414650 @default.
- W2890436498 cites W2295528990 @default.
- W2890436498 cites W2511131004 @default.
- W2890436498 cites W2564425030 @default.
- W2890436498 cites W2773963565 @default.
- W2890436498 cites W2807345617 @default.
- W2890436498 cites W2807400292 @default.
- W2890436498 cites W2915114476 @default.
- W2890436498 cites W2962688168 @default.
- W2890436498 cites W2962897020 @default.
- W2890436498 cites W2963171262 @default.
- W2890436498 cites W2963355640 @default.
- W2890436498 cites W2964349647 @default.
- W2890436498 doi "https://doi.org/10.18653/v1/d18-1125" @default.
- W2890436498 hasPublicationYear "2018" @default.
- W2890436498 type Work @default.
- W2890436498 sameAs 2890436498 @default.
- W2890436498 citedByCount "22" @default.
- W2890436498 countsByYear W28904364982018 @default.
- W2890436498 countsByYear W28904364982019 @default.
- W2890436498 countsByYear W28904364982020 @default.
- W2890436498 countsByYear W28904364982021 @default.
- W2890436498 countsByYear W28904364982022 @default.
- W2890436498 countsByYear W28904364982023 @default.
- W2890436498 crossrefType "proceedings-article" @default.
- W2890436498 hasAuthorship W2890436498A5035304642 @default.
- W2890436498 hasAuthorship W2890436498A5042819803 @default.
- W2890436498 hasAuthorship W2890436498A5044196762 @default.
- W2890436498 hasAuthorship W2890436498A5062124133 @default.
- W2890436498 hasAuthorship W2890436498A5066140774 @default.
- W2890436498 hasAuthorship W2890436498A5075033889 @default.
- W2890436498 hasAuthorship W2890436498A5087631670 @default.
- W2890436498 hasBestOaLocation W28904364981 @default.
- W2890436498 hasConcept C111919701 @default.
- W2890436498 hasConcept C118505674 @default.
- W2890436498 hasConcept C119857082 @default.
- W2890436498 hasConcept C124101348 @default.
- W2890436498 hasConcept C153604712 @default.
- W2890436498 hasConcept C154945302 @default.
- W2890436498 hasConcept C177264268 @default.
- W2890436498 hasConcept C195807954 @default.
- W2890436498 hasConcept C199360897 @default.
- W2890436498 hasConcept C204321447 @default.
- W2890436498 hasConcept C25343380 @default.
- W2890436498 hasConcept C37736160 @default.
- W2890436498 hasConcept C41008148 @default.
- W2890436498 hasConcept C52622490 @default.
- W2890436498 hasConcept C95623464 @default.
- W2890436498 hasConceptScore W2890436498C111919701 @default.
- W2890436498 hasConceptScore W2890436498C118505674 @default.
- W2890436498 hasConceptScore W2890436498C119857082 @default.
- W2890436498 hasConceptScore W2890436498C124101348 @default.
- W2890436498 hasConceptScore W2890436498C153604712 @default.
- W2890436498 hasConceptScore W2890436498C154945302 @default.
- W2890436498 hasConceptScore W2890436498C177264268 @default.
- W2890436498 hasConceptScore W2890436498C195807954 @default.
- W2890436498 hasConceptScore W2890436498C199360897 @default.
- W2890436498 hasConceptScore W2890436498C204321447 @default.
- W2890436498 hasConceptScore W2890436498C25343380 @default.
- W2890436498 hasConceptScore W2890436498C37736160 @default.
- W2890436498 hasConceptScore W2890436498C41008148 @default.
- W2890436498 hasConceptScore W2890436498C52622490 @default.
- W2890436498 hasConceptScore W2890436498C95623464 @default.
- W2890436498 hasLocation W28904364981 @default.
- W2890436498 hasOpenAccess W2890436498 @default.
- W2890436498 hasPrimaryLocation W28904364981 @default.
- W2890436498 hasRelatedWork W2368651715 @default.
- W2890436498 hasRelatedWork W2460937040 @default.
- W2890436498 hasRelatedWork W2528512298 @default.
- W2890436498 hasRelatedWork W2961085424 @default.
- W2890436498 hasRelatedWork W3017503936 @default.
- W2890436498 hasRelatedWork W3205128835 @default.
- W2890436498 hasRelatedWork W4286899967 @default.
- W2890436498 hasRelatedWork W4293092754 @default.
- W2890436498 hasRelatedWork W4300511536 @default.
- W2890436498 hasRelatedWork W4321434406 @default.
- W2890436498 isParatext "false" @default.
- W2890436498 isRetracted "false" @default.
- W2890436498 magId "2890436498" @default.