FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964302308> ?p ?o ?g. }

• W2964302308 endingPage "1814" @default.
• W2964302308 startingPage "1802" @default.
• W2964302308 abstract "Representation learning is the foundation of machine reading comprehension. In state-of-the-art models, deep learning methods broadly use word and character level representations. However, character is not naturally the minimal linguistic unit. In addition, with a simple concatenation of character and word embedding, previous models actually give suboptimal solution. In this paper, we propose to use subword rather than character for word embedding enhancement. We also empirically explore different augmentation strategies on subword-augmented embedding to enhance the cloze-style reading comprehension model (reader). In detail, we present a reader that uses subword-level representation to augment word embedding with a short list to handle rare words effectively. A thorough examination is conducted to evaluate the comprehensive performance and generalization ability of the proposed reader. Experimental results show that the proposed approach helps the reader significantly outperform the state-of-the-art baselines on various public datasets." @default.
• W2964302308 created "2019-07-30" @default.
• W2964302308 creator A5036050911 @default.
• W2964302308 creator A5070962435 @default.
• W2964302308 creator A5080458772 @default.
• W2964302308 date "2018-08-01" @default.
• W2964302308 modified "2023-09-24" @default.
• W2964302308 title "Subword-augmented Embedding for Cloze Reading Comprehension." @default.
• W2964302308 cites W1505680913 @default.
• W2964302308 cites W1544827683 @default.
• W2964302308 cites W1815076433 @default.
• W2964302308 cites W1938755728 @default.
• W2964302308 cites W2157331557 @default.
• W2964302308 cites W2308486447 @default.
• W2964302308 cites W2417763662 @default.
• W2964302308 cites W2493916176 @default.
• W2964302308 cites W2507756961 @default.
• W2964302308 cites W2538616903 @default.
• W2964302308 cites W2551396370 @default.
• W2964302308 cites W2564875206 @default.
• W2964302308 cites W2591264712 @default.
• W2964302308 cites W2601201959 @default.
• W2964302308 cites W2606342375 @default.
• W2964302308 cites W2739845275 @default.
• W2964302308 cites W2740702290 @default.
• W2964302308 cites W2740747242 @default.
• W2964302308 cites W2787933937 @default.
• W2964302308 cites W2798304389 @default.
• W2964302308 cites W2804439688 @default.
• W2964302308 cites W2810519866 @default.
• W2964302308 cites W2822830299 @default.
• W2964302308 cites W2950577311 @default.
• W2964302308 cites W2962739339 @default.
• W2964302308 cites W2962784628 @default.
• W2964302308 cites W2962809918 @default.
• W2964302308 cites W2962934410 @default.
• W2964302308 cites W2963019137 @default.
• W2964302308 cites W2963080779 @default.
• W2964302308 cites W2963299810 @default.
• W2964302308 cites W2963324947 @default.
• W2964302308 cites W2963339397 @default.
• W2964302308 cites W2963344337 @default.
• W2964302308 cites W2963582782 @default.
• W2964302308 cites W2963591283 @default.
• W2964302308 cites W2963595025 @default.
• W2964302308 cites W2963626623 @default.
• W2964302308 cites W2963628345 @default.
• W2964302308 cites W2963748441 @default.
• W2964302308 cites W2963956494 @default.
• W2964302308 cites W2964121744 @default.
• W2964302308 cites W2964185324 @default.
• W2964302308 cites W2964267515 @default.
• W2964302308 cites W2964352165 @default.
• W2964302308 cites W3104486441 @default.
• W2964302308 cites W3121416198 @default.
• W2964302308 cites W46679369 @default.
• W2964302308 cites W2417356443 @default.
• W2964302308 hasPublicationYear "2018" @default.
• W2964302308 type Work @default.
• W2964302308 sameAs 2964302308 @default.
• W2964302308 citedByCount "26" @default.
• W2964302308 countsByYear W29643023082018 @default.
• W2964302308 countsByYear W29643023082019 @default.
• W2964302308 countsByYear W29643023082020 @default.
• W2964302308 crossrefType "proceedings-article" @default.
• W2964302308 hasAuthorship W2964302308A5036050911 @default.
• W2964302308 hasAuthorship W2964302308A5070962435 @default.
• W2964302308 hasAuthorship W2964302308A5080458772 @default.
• W2964302308 hasConcept C134306372 @default.
• W2964302308 hasConcept C138885662 @default.
• W2964302308 hasConcept C154945302 @default.
• W2964302308 hasConcept C177148314 @default.
• W2964302308 hasConcept C17744445 @default.
• W2964302308 hasConcept C199360897 @default.
• W2964302308 hasConcept C199539241 @default.
• W2964302308 hasConcept C204321447 @default.
• W2964302308 hasConcept C2524010 @default.
• W2964302308 hasConcept C2776359362 @default.
• W2964302308 hasConcept C2777462759 @default.
• W2964302308 hasConcept C2778780117 @default.
• W2964302308 hasConcept C2780861071 @default.
• W2964302308 hasConcept C33923547 @default.
• W2964302308 hasConcept C41008148 @default.
• W2964302308 hasConcept C41608201 @default.
• W2964302308 hasConcept C41895202 @default.
• W2964302308 hasConcept C511192102 @default.
• W2964302308 hasConcept C554936623 @default.
• W2964302308 hasConcept C87619178 @default.
• W2964302308 hasConcept C90805587 @default.
• W2964302308 hasConcept C94375191 @default.
• W2964302308 hasConcept C94625758 @default.
• W2964302308 hasConceptScore W2964302308C134306372 @default.
• W2964302308 hasConceptScore W2964302308C138885662 @default.
• W2964302308 hasConceptScore W2964302308C154945302 @default.
• W2964302308 hasConceptScore W2964302308C177148314 @default.
• W2964302308 hasConceptScore W2964302308C17744445 @default.
• W2964302308 hasConceptScore W2964302308C199360897 @default.
• W2964302308 hasConceptScore W2964302308C199539241 @default.

• next