Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306651521> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W4306651521 endingPage "10459" @default.
- W4306651521 startingPage "10459" @default.
- W4306651521 abstract "Machine reading comprehension (MRC) is an important research topic in the field of Natural Language Processing (NLP). However, traditional MRC models often face challenges of information loss, lack of capability to retain long-distance dependence, and inability to deal with unanswerable questions where answers are not available in given texts. In this paper, a Chinese reading comprehension algorithm, called the Attention and Conditional Random Filed (AT-CRF) Reader, is proposed to address the above challenges. Firstly, RoBERTa, a pre-trained language model, is introduced to obtain the embedding representations of input. Then, a depthwise separable convolution neural network and attention mechanisms are used to replace the recurrent neural network for encoding. Next, the attention flow and self-attention mechanisms are used to obtain the context–query internal relation. Finally, the conditional random field is used to handle unanswerable questions and predict the correct answer. Experiments were conducted on the two Chinese machine reading comprehension datasets, CMRC2018 and DuReader-checklist, and the results showed that, compared with the baseline model, the F1 scores achieved by our AT-CRF Reader model has improved by 2.65% and 2.68%, and the EM values increased by 4.45% and 3.88%." @default.
- W4306651521 created "2022-10-18" @default.
- W4306651521 creator A5031941572 @default.
- W4306651521 creator A5076282777 @default.
- W4306651521 creator A5080764253 @default.
- W4306651521 date "2022-10-17" @default.
- W4306651521 modified "2023-09-30" @default.
- W4306651521 title "AT-CRF: A Chinese Reading Comprehension Algorithm Based on Attention Mechanism and Conditional Random Fields" @default.
- W4306651521 cites W2121300346 @default.
- W4306651521 cites W2740747242 @default.
- W4306651521 cites W3002072934 @default.
- W4306651521 cites W3130020357 @default.
- W4306651521 cites W3148040514 @default.
- W4306651521 cites W3189064355 @default.
- W4306651521 cites W3191703922 @default.
- W4306651521 cites W3210120707 @default.
- W4306651521 doi "https://doi.org/10.3390/app122010459" @default.
- W4306651521 hasPublicationYear "2022" @default.
- W4306651521 type Work @default.
- W4306651521 citedByCount "0" @default.
- W4306651521 crossrefType "journal-article" @default.
- W4306651521 hasAuthorship W4306651521A5031941572 @default.
- W4306651521 hasAuthorship W4306651521A5076282777 @default.
- W4306651521 hasAuthorship W4306651521A5080764253 @default.
- W4306651521 hasBestOaLocation W43066515211 @default.
- W4306651521 hasConcept C138885662 @default.
- W4306651521 hasConcept C152565575 @default.
- W4306651521 hasConcept C154945302 @default.
- W4306651521 hasConcept C199360897 @default.
- W4306651521 hasConcept C204321447 @default.
- W4306651521 hasConcept C2778780117 @default.
- W4306651521 hasConcept C41008148 @default.
- W4306651521 hasConcept C41895202 @default.
- W4306651521 hasConcept C511192102 @default.
- W4306651521 hasConcept C554936623 @default.
- W4306651521 hasConceptScore W4306651521C138885662 @default.
- W4306651521 hasConceptScore W4306651521C152565575 @default.
- W4306651521 hasConceptScore W4306651521C154945302 @default.
- W4306651521 hasConceptScore W4306651521C199360897 @default.
- W4306651521 hasConceptScore W4306651521C204321447 @default.
- W4306651521 hasConceptScore W4306651521C2778780117 @default.
- W4306651521 hasConceptScore W4306651521C41008148 @default.
- W4306651521 hasConceptScore W4306651521C41895202 @default.
- W4306651521 hasConceptScore W4306651521C511192102 @default.
- W4306651521 hasConceptScore W4306651521C554936623 @default.
- W4306651521 hasFunder F4320324519 @default.
- W4306651521 hasIssue "20" @default.
- W4306651521 hasLocation W43066515211 @default.
- W4306651521 hasOpenAccess W4306651521 @default.
- W4306651521 hasPrimaryLocation W43066515211 @default.
- W4306651521 hasRelatedWork W1522304454 @default.
- W4306651521 hasRelatedWork W1917284140 @default.
- W4306651521 hasRelatedWork W1999620267 @default.
- W4306651521 hasRelatedWork W2078793151 @default.
- W4306651521 hasRelatedWork W2293457016 @default.
- W4306651521 hasRelatedWork W2789919619 @default.
- W4306651521 hasRelatedWork W2886890203 @default.
- W4306651521 hasRelatedWork W3169305685 @default.
- W4306651521 hasRelatedWork W65845428 @default.
- W4306651521 hasRelatedWork W2082296339 @default.
- W4306651521 hasVolume "12" @default.
- W4306651521 isParatext "false" @default.
- W4306651521 isRetracted "false" @default.
- W4306651521 workType "article" @default.