Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890835309> ?p ?o ?g. }
- W2890835309 abstract "Discourse segmentation aims to segment Elementary Discourse Units (EDUs) and is a fundamental task in discourse analysis. For Chinese, previous researches identify EDUs just through discriminating the functions of punctuations. In this paper, we argue that Chinese EDUs may not end at the punctuation positions and should follow the definition of EDU in RST-DT. With this definition, we conduct Chinese discourse segmentation with the help of English labeled data.Using discourse commonality between English and Chinese, we design an adversarial neural network framework to extract common language-independent features and language-specific features which are useful for discourse segmentation, when there is no or only a small scale of Chinese labeled data available. Experiments on discourse segmentation demonstrate that our models can leverage common features from bilingual data, and learn efficient Chinese-specific features from a small amount of Chinese labeled data, outperforming the baseline models." @default.
- W2890835309 created "2018-09-27" @default.
- W2890835309 creator A5044671587 @default.
- W2890835309 creator A5058353424 @default.
- W2890835309 date "2018-08-29" @default.
- W2890835309 modified "2023-10-16" @default.
- W2890835309 title "Chinese Discourse Segmentation Using Bilingual Discourse Commonality" @default.
- W2890835309 cites W1581597064 @default.
- W2890835309 cites W1828724394 @default.
- W2890835309 cites W1894075015 @default.
- W2890835309 cites W1940872118 @default.
- W2890835309 cites W2001283107 @default.
- W2890835309 cites W2016630033 @default.
- W2890835309 cites W2027869740 @default.
- W2890835309 cites W2045738181 @default.
- W2890835309 cites W2081266320 @default.
- W2890835309 cites W2104912629 @default.
- W2890835309 cites W2108997961 @default.
- W2890835309 cites W2116187224 @default.
- W2890835309 cites W2123442489 @default.
- W2890835309 cites W2130867674 @default.
- W2890835309 cites W2130903752 @default.
- W2890835309 cites W2154407881 @default.
- W2890835309 cites W2158217454 @default.
- W2890835309 cites W2162763612 @default.
- W2890835309 cites W2186069521 @default.
- W2890835309 cites W2186590411 @default.
- W2890835309 cites W2251500379 @default.
- W2890835309 cites W2251803607 @default.
- W2890835309 cites W2308486447 @default.
- W2890835309 cites W2335367650 @default.
- W2890835309 cites W2368081911 @default.
- W2890835309 cites W2413332972 @default.
- W2890835309 cites W2461928176 @default.
- W2890835309 cites W2567624515 @default.
- W2890835309 cites W2579343286 @default.
- W2890835309 cites W2581485081 @default.
- W2890835309 cites W2609414830 @default.
- W2890835309 cites W2758640791 @default.
- W2890835309 cites W2773052985 @default.
- W2890835309 cites W2789663917 @default.
- W2890835309 cites W2949541494 @default.
- W2890835309 cites W2949615363 @default.
- W2890835309 cites W2962902328 @default.
- W2890835309 cites W2963826681 @default.
- W2890835309 cites W2964325005 @default.
- W2890835309 cites W584032488 @default.
- W2890835309 doi "https://doi.org/10.48550/arxiv.1809.01497" @default.
- W2890835309 hasPublicationYear "2018" @default.
- W2890835309 type Work @default.
- W2890835309 sameAs 2890835309 @default.
- W2890835309 citedByCount "4" @default.
- W2890835309 countsByYear W28908353092019 @default.
- W2890835309 countsByYear W28908353092021 @default.
- W2890835309 crossrefType "posted-content" @default.
- W2890835309 hasAuthorship W2890835309A5044671587 @default.
- W2890835309 hasAuthorship W2890835309A5058353424 @default.
- W2890835309 hasBestOaLocation W28908353091 @default.
- W2890835309 hasConcept C138885662 @default.
- W2890835309 hasConcept C153083717 @default.
- W2890835309 hasConcept C154945302 @default.
- W2890835309 hasConcept C162324750 @default.
- W2890835309 hasConcept C187736073 @default.
- W2890835309 hasConcept C204321447 @default.
- W2890835309 hasConcept C2780451532 @default.
- W2890835309 hasConcept C37736160 @default.
- W2890835309 hasConcept C41008148 @default.
- W2890835309 hasConcept C41895202 @default.
- W2890835309 hasConcept C540372491 @default.
- W2890835309 hasConcept C84389358 @default.
- W2890835309 hasConcept C89600930 @default.
- W2890835309 hasConceptScore W2890835309C138885662 @default.
- W2890835309 hasConceptScore W2890835309C153083717 @default.
- W2890835309 hasConceptScore W2890835309C154945302 @default.
- W2890835309 hasConceptScore W2890835309C162324750 @default.
- W2890835309 hasConceptScore W2890835309C187736073 @default.
- W2890835309 hasConceptScore W2890835309C204321447 @default.
- W2890835309 hasConceptScore W2890835309C2780451532 @default.
- W2890835309 hasConceptScore W2890835309C37736160 @default.
- W2890835309 hasConceptScore W2890835309C41008148 @default.
- W2890835309 hasConceptScore W2890835309C41895202 @default.
- W2890835309 hasConceptScore W2890835309C540372491 @default.
- W2890835309 hasConceptScore W2890835309C84389358 @default.
- W2890835309 hasConceptScore W2890835309C89600930 @default.
- W2890835309 hasLocation W28908353091 @default.
- W2890835309 hasOpenAccess W2890835309 @default.
- W2890835309 hasPrimaryLocation W28908353091 @default.
- W2890835309 hasRelatedWork W2081647779 @default.
- W2890835309 hasRelatedWork W2167662847 @default.
- W2890835309 hasRelatedWork W2578916128 @default.
- W2890835309 hasRelatedWork W2603501458 @default.
- W2890835309 hasRelatedWork W2948262272 @default.
- W2890835309 hasRelatedWork W3185852197 @default.
- W2890835309 hasRelatedWork W3216776746 @default.
- W2890835309 hasRelatedWork W38394648 @default.
- W2890835309 hasRelatedWork W4281569454 @default.
- W2890835309 hasRelatedWork W4300659434 @default.
- W2890835309 isParatext "false" @default.
- W2890835309 isRetracted "false" @default.
- W2890835309 magId "2890835309" @default.