Matches in SemOpenAlex for { <https://semopenalex.org/work/W2803469432> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2803469432 abstract "Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and compose sentence-level semantics in varied ways; however, few works have attempted to verify whether we really need pretrained embeddings in these tasks. In this paper, we study how effective subword-level (character and character n-gram) representations are in sentence pair modeling. Though it is well-known that subword models are effective in tasks with single sentence input, including language modeling and machine translation, they have not been systematically studied in sentence pair modeling tasks where the semantic and string similarities between texts matter. Our experiments show that subword models without any pretrained word embedding can achieve new state-of-the-art results on two social media datasets and competitive results on news data for paraphrase identification." @default.
- W2803469432 created "2018-06-01" @default.
- W2803469432 creator A5058348064 @default.
- W2803469432 creator A5070905937 @default.
- W2803469432 date "2018-05-21" @default.
- W2803469432 modified "2023-10-18" @default.
- W2803469432 title "Character-based Neural Networks for Sentence Pair Modeling" @default.
- W2803469432 cites W1814992895 @default.
- W2803469432 cites W2153702313 @default.
- W2803469432 cites W2159849140 @default.
- W2803469432 cites W2211192759 @default.
- W2803469432 cites W2250539671 @default.
- W2803469432 cites W2413794162 @default.
- W2803469432 cites W2417736714 @default.
- W2803469432 cites W2464186148 @default.
- W2803469432 cites W2609130030 @default.
- W2803469432 cites W2760753016 @default.
- W2803469432 cites W2949563612 @default.
- W2803469432 cites W2952341153 @default.
- W2803469432 cites W2953084091 @default.
- W2803469432 cites W2963499246 @default.
- W2803469432 cites W2963508788 @default.
- W2803469432 cites W2963731165 @default.
- W2803469432 cites W2964090065 @default.
- W2803469432 cites W560371024 @default.
- W2803469432 doi "https://doi.org/10.48550/arxiv.1805.08297" @default.
- W2803469432 hasPublicationYear "2018" @default.
- W2803469432 type Work @default.
- W2803469432 sameAs 2803469432 @default.
- W2803469432 citedByCount "0" @default.
- W2803469432 crossrefType "posted-content" @default.
- W2803469432 hasAuthorship W2803469432A5058348064 @default.
- W2803469432 hasAuthorship W2803469432A5070905937 @default.
- W2803469432 hasBestOaLocation W28034694321 @default.
- W2803469432 hasConcept C116834253 @default.
- W2803469432 hasConcept C121332964 @default.
- W2803469432 hasConcept C137293760 @default.
- W2803469432 hasConcept C138885662 @default.
- W2803469432 hasConcept C154945302 @default.
- W2803469432 hasConcept C157486923 @default.
- W2803469432 hasConcept C203005215 @default.
- W2803469432 hasConcept C204321447 @default.
- W2803469432 hasConcept C2524010 @default.
- W2803469432 hasConcept C2776214188 @default.
- W2803469432 hasConcept C2777530160 @default.
- W2803469432 hasConcept C2780861071 @default.
- W2803469432 hasConcept C2780922921 @default.
- W2803469432 hasConcept C28490314 @default.
- W2803469432 hasConcept C33923547 @default.
- W2803469432 hasConcept C41008148 @default.
- W2803469432 hasConcept C41608201 @default.
- W2803469432 hasConcept C41895202 @default.
- W2803469432 hasConcept C59822182 @default.
- W2803469432 hasConcept C62520636 @default.
- W2803469432 hasConcept C86803240 @default.
- W2803469432 hasConcept C90805587 @default.
- W2803469432 hasConceptScore W2803469432C116834253 @default.
- W2803469432 hasConceptScore W2803469432C121332964 @default.
- W2803469432 hasConceptScore W2803469432C137293760 @default.
- W2803469432 hasConceptScore W2803469432C138885662 @default.
- W2803469432 hasConceptScore W2803469432C154945302 @default.
- W2803469432 hasConceptScore W2803469432C157486923 @default.
- W2803469432 hasConceptScore W2803469432C203005215 @default.
- W2803469432 hasConceptScore W2803469432C204321447 @default.
- W2803469432 hasConceptScore W2803469432C2524010 @default.
- W2803469432 hasConceptScore W2803469432C2776214188 @default.
- W2803469432 hasConceptScore W2803469432C2777530160 @default.
- W2803469432 hasConceptScore W2803469432C2780861071 @default.
- W2803469432 hasConceptScore W2803469432C2780922921 @default.
- W2803469432 hasConceptScore W2803469432C28490314 @default.
- W2803469432 hasConceptScore W2803469432C33923547 @default.
- W2803469432 hasConceptScore W2803469432C41008148 @default.
- W2803469432 hasConceptScore W2803469432C41608201 @default.
- W2803469432 hasConceptScore W2803469432C41895202 @default.
- W2803469432 hasConceptScore W2803469432C59822182 @default.
- W2803469432 hasConceptScore W2803469432C62520636 @default.
- W2803469432 hasConceptScore W2803469432C86803240 @default.
- W2803469432 hasConceptScore W2803469432C90805587 @default.
- W2803469432 hasLocation W28034694321 @default.
- W2803469432 hasLocation W28034694322 @default.
- W2803469432 hasOpenAccess W2803469432 @default.
- W2803469432 hasPrimaryLocation W28034694321 @default.
- W2803469432 hasRelatedWork W1947252915 @default.
- W2803469432 hasRelatedWork W1973985309 @default.
- W2803469432 hasRelatedWork W2886767593 @default.
- W2803469432 hasRelatedWork W2951718443 @default.
- W2803469432 hasRelatedWork W2963001247 @default.
- W2803469432 hasRelatedWork W2964212550 @default.
- W2803469432 hasRelatedWork W2969773591 @default.
- W2803469432 hasRelatedWork W2971292192 @default.
- W2803469432 hasRelatedWork W3093843097 @default.
- W2803469432 hasRelatedWork W4292355812 @default.
- W2803469432 isParatext "false" @default.
- W2803469432 isRetracted "false" @default.
- W2803469432 magId "2803469432" @default.
- W2803469432 workType "article" @default.