Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897190009> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W2897190009 abstract "Question Classification is a core module of Question Answering paradigm. Development of classification models based on neural networks showed that convolutional architectures allow obtaining uppermost results for this task. In particular, this type of approach avoids extracting features from questions, by treating text as a sequence of words, and transforming each word in a dense vector, named word embedding. Among different techniques to learn word embeddings, a recent approach takes into account also subword information, which could be very useful for morphologically rich languages. In this paper, a Question Classification approach based on word embedding using subword information and Convolutional Neural Networks is proposed, in order to improve classification accuracy. In particular, questions taken from a TRC dataset are considered, and a comparison between English and Italian languages is reported, by highlighting eventual improvements obtained by initializing word embeddings with advanced vectors learned in an unsupervised manner using skip- gram model and comprising character-based information." @default.
- W2897190009 created "2018-10-26" @default.
- W2897190009 creator A5060643104 @default.
- W2897190009 creator A5086794713 @default.
- W2897190009 date "2018-07-01" @default.
- W2897190009 modified "2023-09-28" @default.
- W2897190009 title "Question Classification by Convolutional Neural Networks Embodying Subword Information" @default.
- W2897190009 cites W1761765343 @default.
- W2897190009 cites W1806891645 @default.
- W2897190009 cites W1832693441 @default.
- W2897190009 cites W1984010941 @default.
- W2897190009 cites W2019307700 @default.
- W2897190009 cites W2061495585 @default.
- W2897190009 cites W2086004682 @default.
- W2897190009 cites W2120615054 @default.
- W2897190009 cites W2250473257 @default.
- W2897190009 cites W2250539671 @default.
- W2897190009 cites W2251103205 @default.
- W2897190009 cites W2320227961 @default.
- W2897190009 cites W2493916176 @default.
- W2897190009 cites W2610934608 @default.
- W2897190009 cites W2749747389 @default.
- W2897190009 cites W2760392765 @default.
- W2897190009 cites W2962996334 @default.
- W2897190009 cites W2963042536 @default.
- W2897190009 cites W2963421945 @default.
- W2897190009 cites W2294756950 @default.
- W2897190009 doi "https://doi.org/10.1109/ijcnn.2018.8489406" @default.
- W2897190009 hasPublicationYear "2018" @default.
- W2897190009 type Work @default.
- W2897190009 sameAs 2897190009 @default.
- W2897190009 citedByCount "4" @default.
- W2897190009 countsByYear W28971900092019 @default.
- W2897190009 countsByYear W28971900092020 @default.
- W2897190009 countsByYear W28971900092022 @default.
- W2897190009 crossrefType "proceedings-article" @default.
- W2897190009 hasAuthorship W2897190009A5060643104 @default.
- W2897190009 hasAuthorship W2897190009A5086794713 @default.
- W2897190009 hasConcept C154945302 @default.
- W2897190009 hasConcept C204321447 @default.
- W2897190009 hasConcept C41008148 @default.
- W2897190009 hasConcept C81363708 @default.
- W2897190009 hasConceptScore W2897190009C154945302 @default.
- W2897190009 hasConceptScore W2897190009C204321447 @default.
- W2897190009 hasConceptScore W2897190009C41008148 @default.
- W2897190009 hasConceptScore W2897190009C81363708 @default.
- W2897190009 hasLocation W28971900091 @default.
- W2897190009 hasOpenAccess W2897190009 @default.
- W2897190009 hasPrimaryLocation W28971900091 @default.
- W2897190009 hasRelatedWork W2285788670 @default.
- W2897190009 hasRelatedWork W2521062615 @default.
- W2897190009 hasRelatedWork W2735477435 @default.
- W2897190009 hasRelatedWork W2946452775 @default.
- W2897190009 hasRelatedWork W2955938200 @default.
- W2897190009 hasRelatedWork W2998526951 @default.
- W2897190009 hasRelatedWork W3016958897 @default.
- W2897190009 hasRelatedWork W3090822330 @default.
- W2897190009 hasRelatedWork W3181746755 @default.
- W2897190009 hasRelatedWork W4239686595 @default.
- W2897190009 isParatext "false" @default.
- W2897190009 isRetracted "false" @default.
- W2897190009 magId "2897190009" @default.
- W2897190009 workType "article" @default.