Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890170470> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2890170470 endingPage "104" @default.
- W2890170470 startingPage "93" @default.
- W2890170470 abstract "Machine reading comprehension (MRC) on real web data, which means finding answers from a set of candidate passages for a question, is a quite arduous task in natural language processing. Most state-of-the-art approaches select answers from all passages or from only one single golden paragraph, which may cause the overlapping information and the lack of key information. To address these problems, this paper proposes a hierarchical answer selection framework that can select main content from a set of passages based on the question, and predict final answer within this main content. Specifically, three main parts are employed in this pipeline: First, the passage selection model uses a classification mechanism to select passages by passages content and title information which is not fully used in other models; Second, a key sentences sequence selection mechanism is modeled by Markov-Decision-Process (MDP) in order to gain as much as effectual answer information as possible; Finally, a match-LSTM model is employed to extract the final answer from the selected main content. These three modules that shared the same attention-based semantic network and we conduct experimental on DuReader search dataset. The results show that our framework outperforms the baseline by a large margin." @default.
- W2890170470 created "2018-09-27" @default.
- W2890170470 creator A5029998682 @default.
- W2890170470 creator A5032087333 @default.
- W2890170470 creator A5036291399 @default.
- W2890170470 creator A5036476029 @default.
- W2890170470 creator A5071547136 @default.
- W2890170470 creator A5088621320 @default.
- W2890170470 date "2018-01-01" @default.
- W2890170470 modified "2023-09-27" @default.
- W2890170470 title "Hierarchical Answer Selection Framework for Multi-passage Machine Reading Comprehension" @default.
- W2890170470 cites W2521709538 @default.
- W2890170470 cites W2606964149 @default.
- W2890170470 cites W2887331219 @default.
- W2890170470 cites W2963748441 @default.
- W2890170470 cites W2963898730 @default.
- W2890170470 cites W2963957489 @default.
- W2890170470 doi "https://doi.org/10.1007/978-3-030-01012-6_8" @default.
- W2890170470 hasPublicationYear "2018" @default.
- W2890170470 type Work @default.
- W2890170470 sameAs 2890170470 @default.
- W2890170470 citedByCount "3" @default.
- W2890170470 countsByYear W28901704702019 @default.
- W2890170470 countsByYear W28901704702021 @default.
- W2890170470 crossrefType "book-chapter" @default.
- W2890170470 hasAuthorship W2890170470A5029998682 @default.
- W2890170470 hasAuthorship W2890170470A5032087333 @default.
- W2890170470 hasAuthorship W2890170470A5036291399 @default.
- W2890170470 hasAuthorship W2890170470A5036476029 @default.
- W2890170470 hasAuthorship W2890170470A5071547136 @default.
- W2890170470 hasAuthorship W2890170470A5088621320 @default.
- W2890170470 hasConcept C138885662 @default.
- W2890170470 hasConcept C154945302 @default.
- W2890170470 hasConcept C199360897 @default.
- W2890170470 hasConcept C204321447 @default.
- W2890170470 hasConcept C2778780117 @default.
- W2890170470 hasConcept C41008148 @default.
- W2890170470 hasConcept C41895202 @default.
- W2890170470 hasConcept C511192102 @default.
- W2890170470 hasConcept C554936623 @default.
- W2890170470 hasConcept C81917197 @default.
- W2890170470 hasConceptScore W2890170470C138885662 @default.
- W2890170470 hasConceptScore W2890170470C154945302 @default.
- W2890170470 hasConceptScore W2890170470C199360897 @default.
- W2890170470 hasConceptScore W2890170470C204321447 @default.
- W2890170470 hasConceptScore W2890170470C2778780117 @default.
- W2890170470 hasConceptScore W2890170470C41008148 @default.
- W2890170470 hasConceptScore W2890170470C41895202 @default.
- W2890170470 hasConceptScore W2890170470C511192102 @default.
- W2890170470 hasConceptScore W2890170470C554936623 @default.
- W2890170470 hasConceptScore W2890170470C81917197 @default.
- W2890170470 hasLocation W28901704701 @default.
- W2890170470 hasOpenAccess W2890170470 @default.
- W2890170470 hasPrimaryLocation W28901704701 @default.
- W2890170470 hasRelatedWork W1969359128 @default.
- W2890170470 hasRelatedWork W1982811735 @default.
- W2890170470 hasRelatedWork W2362662964 @default.
- W2890170470 hasRelatedWork W2389366623 @default.
- W2890170470 hasRelatedWork W240922204 @default.
- W2890170470 hasRelatedWork W2524839221 @default.
- W2890170470 hasRelatedWork W2890708534 @default.
- W2890170470 hasRelatedWork W2898238898 @default.
- W2890170470 hasRelatedWork W3107474891 @default.
- W2890170470 hasRelatedWork W4223892844 @default.
- W2890170470 isParatext "false" @default.
- W2890170470 isRetracted "false" @default.
- W2890170470 magId "2890170470" @default.
- W2890170470 workType "book-chapter" @default.