Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963325985> ?p ?o ?g. }
- W2963325985 abstract "Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models from the perspectives of coherence and cohesion. In this work, we propose a new neural language model that is equipped with two neural discriminators which provide feedback signals at the levels of sentence (cohesion) and paragraph (coherence). Our model is trained using a simple yet efficient variant of policy gradient, called negative-critical sequence training, which is proposed to eliminate the need of training a separate critic for estimating baseline. Results demonstrate the effectiveness of our approach, showing improvements over the strong baseline -- recurrent attention-based bidirectional MLE-trained neural language model." @default.
- W2963325985 created "2019-07-30" @default.
- W2963325985 creator A5015656536 @default.
- W2963325985 creator A5021140826 @default.
- W2963325985 creator A5037066465 @default.
- W2963325985 creator A5047233371 @default.
- W2963325985 creator A5052683643 @default.
- W2963325985 creator A5054747226 @default.
- W2963325985 creator A5059735251 @default.
- W2963325985 creator A5081872106 @default.
- W2963325985 date "2019-01-01" @default.
- W2963325985 modified "2023-09-24" @default.
- W2963325985 title "Towards Coherent and Cohesive Long-form Text Generation" @default.
- W2963325985 cites W125554750 @default.
- W2963325985 cites W1514027499 @default.
- W2963325985 cites W1518951372 @default.
- W2963325985 cites W1570278093 @default.
- W2963325985 cites W1575964949 @default.
- W2963325985 cites W1591706642 @default.
- W2963325985 cites W1605174196 @default.
- W2963325985 cites W1810943226 @default.
- W2963325985 cites W1832693441 @default.
- W2963325985 cites W1992702627 @default.
- W2963325985 cites W2045738181 @default.
- W2963325985 cites W2054940200 @default.
- W2963325985 cites W2070016268 @default.
- W2963325985 cites W2091565802 @default.
- W2963325985 cites W2099471712 @default.
- W2963325985 cites W2101105183 @default.
- W2963325985 cites W2104573870 @default.
- W2963325985 cites W2130942839 @default.
- W2963325985 cites W2136189984 @default.
- W2963325985 cites W2137659643 @default.
- W2963325985 cites W2140676672 @default.
- W2963325985 cites W2155027007 @default.
- W2963325985 cites W2157331557 @default.
- W2963325985 cites W2158349948 @default.
- W2963325985 cites W2158467128 @default.
- W2963325985 cites W2158899491 @default.
- W2963325985 cites W2160409620 @default.
- W2963325985 cites W2166347079 @default.
- W2963325985 cites W2166806362 @default.
- W2963325985 cites W2250539671 @default.
- W2963325985 cites W2251008987 @default.
- W2963325985 cites W2487501366 @default.
- W2963325985 cites W2581637843 @default.
- W2963325985 cites W2616969219 @default.
- W2963325985 cites W2752172973 @default.
- W2963325985 cites W2757836268 @default.
- W2963325985 cites W2784823820 @default.
- W2963325985 cites W2797585226 @default.
- W2963325985 cites W2810840719 @default.
- W2963325985 cites W2890969459 @default.
- W2963325985 cites W2962852262 @default.
- W2963325985 cites W2962912551 @default.
- W2963325985 cites W2962955856 @default.
- W2963325985 cites W2963084599 @default.
- W2963325985 cites W2963167310 @default.
- W2963325985 cites W2963206148 @default.
- W2963325985 cites W2963283805 @default.
- W2963325985 cites W2963330684 @default.
- W2963325985 cites W2963499246 @default.
- W2963325985 cites W2963963856 @default.
- W2963325985 cites W2963966654 @default.
- W2963325985 cites W2964017345 @default.
- W2963325985 cites W2964121744 @default.
- W2963325985 cites W2964268978 @default.
- W2963325985 cites W2964308564 @default.
- W2963325985 cites W2964352131 @default.
- W2963325985 cites W3122775348 @default.
- W2963325985 doi "https://doi.org/10.18653/v1/w19-2401" @default.
- W2963325985 hasPublicationYear "2019" @default.
- W2963325985 type Work @default.
- W2963325985 sameAs 2963325985 @default.
- W2963325985 citedByCount "17" @default.
- W2963325985 countsByYear W29633259852019 @default.
- W2963325985 countsByYear W29633259852020 @default.
- W2963325985 countsByYear W29633259852021 @default.
- W2963325985 countsByYear W29633259852022 @default.
- W2963325985 countsByYear W29633259852023 @default.
- W2963325985 crossrefType "proceedings-article" @default.
- W2963325985 hasAuthorship W2963325985A5015656536 @default.
- W2963325985 hasAuthorship W2963325985A5021140826 @default.
- W2963325985 hasAuthorship W2963325985A5037066465 @default.
- W2963325985 hasAuthorship W2963325985A5047233371 @default.
- W2963325985 hasAuthorship W2963325985A5052683643 @default.
- W2963325985 hasAuthorship W2963325985A5054747226 @default.
- W2963325985 hasAuthorship W2963325985A5059735251 @default.
- W2963325985 hasAuthorship W2963325985A5081872106 @default.
- W2963325985 hasBestOaLocation W29633259852 @default.
- W2963325985 hasConcept C204321447 @default.
- W2963325985 hasConcept C41008148 @default.
- W2963325985 hasConceptScore W2963325985C204321447 @default.
- W2963325985 hasConceptScore W2963325985C41008148 @default.
- W2963325985 hasLocation W29633259851 @default.
- W2963325985 hasLocation W29633259852 @default.
- W2963325985 hasOpenAccess W2963325985 @default.
- W2963325985 hasPrimaryLocation W29633259851 @default.
- W2963325985 hasRelatedWork W1552159754 @default.
- W2963325985 hasRelatedWork W2131420137 @default.