Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382651806> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4382651806 endingPage "100023" @default.
- W4382651806 startingPage "100023" @default.
- W4382651806 abstract "Natural Language Inference (NLI) has been one of the fundamental tasks in Natural Language Processing (NLP). Recognizing Textual Entailment (RTE) between the two pieces of text is a crucial problem. It adds further challenges when it involves two languages, i.e., in the cross-lingual scenario. In this paper, we propose VisioTextual-Attention (VTA) - an effective visual-textual coattention mechanism for multi-modal cross-lingual NLI. Through our research, we show that instead of using only linguistic input features, introducing visual features supporting the textual inputs improves the performance of NLI models if an effective cross-modal attention mechanism is carefully constructed. We perform several experiments on a standard cross-lingual textual entailment dataset in Hindi-English language pairs and show that the addition of visual information to the dataset along with our proposed VisioTextual Attention (VTA) enhances performance and surpasses the current state-of-the-art by 4.5%. Through monolingual experiments, we also show that the proposed VTA mechanism surpasses monolingual state-of-the-art by a margin of 2.89%. We argue that our VTA mechanism is model agnostic and can be used with other deep learning-based architectures for grounded cross-lingual NLI." @default.
- W4382651806 created "2023-07-01" @default.
- W4382651806 creator A5043602469 @default.
- W4382651806 creator A5085370631 @default.
- W4382651806 creator A5087152480 @default.
- W4382651806 date "2023-09-01" @default.
- W4382651806 modified "2023-10-14" @default.
- W4382651806 title "Towards Improvement of Grounded Cross-lingual Natural Language Inference with VisioTextual Attention" @default.
- W4382651806 cites W1503434654 @default.
- W4382651806 cites W1677182931 @default.
- W4382651806 cites W1933349210 @default.
- W4382651806 cites W1975879668 @default.
- W4382651806 cites W2036931463 @default.
- W4382651806 cites W2108598243 @default.
- W4382651806 cites W2114766444 @default.
- W4382651806 cites W2164777277 @default.
- W4382651806 cites W2185175083 @default.
- W4382651806 cites W2560730294 @default.
- W4382651806 cites W2593833795 @default.
- W4382651806 cites W3015889210 @default.
- W4382651806 cites W4311233892 @default.
- W4382651806 cites W4317564561 @default.
- W4382651806 doi "https://doi.org/10.1016/j.nlp.2023.100023" @default.
- W4382651806 hasPublicationYear "2023" @default.
- W4382651806 type Work @default.
- W4382651806 citedByCount "0" @default.
- W4382651806 crossrefType "journal-article" @default.
- W4382651806 hasAuthorship W4382651806A5043602469 @default.
- W4382651806 hasAuthorship W4382651806A5085370631 @default.
- W4382651806 hasAuthorship W4382651806A5087152480 @default.
- W4382651806 hasBestOaLocation W43826518061 @default.
- W4382651806 hasConcept C119857082 @default.
- W4382651806 hasConcept C154945302 @default.
- W4382651806 hasConcept C185592680 @default.
- W4382651806 hasConcept C188027245 @default.
- W4382651806 hasConcept C195324797 @default.
- W4382651806 hasConcept C204321447 @default.
- W4382651806 hasConcept C2776214188 @default.
- W4382651806 hasConcept C41008148 @default.
- W4382651806 hasConcept C71139939 @default.
- W4382651806 hasConcept C774472 @default.
- W4382651806 hasConceptScore W4382651806C119857082 @default.
- W4382651806 hasConceptScore W4382651806C154945302 @default.
- W4382651806 hasConceptScore W4382651806C185592680 @default.
- W4382651806 hasConceptScore W4382651806C188027245 @default.
- W4382651806 hasConceptScore W4382651806C195324797 @default.
- W4382651806 hasConceptScore W4382651806C204321447 @default.
- W4382651806 hasConceptScore W4382651806C2776214188 @default.
- W4382651806 hasConceptScore W4382651806C41008148 @default.
- W4382651806 hasConceptScore W4382651806C71139939 @default.
- W4382651806 hasConceptScore W4382651806C774472 @default.
- W4382651806 hasLocation W43826518061 @default.
- W4382651806 hasOpenAccess W4382651806 @default.
- W4382651806 hasPrimaryLocation W43826518061 @default.
- W4382651806 hasRelatedWork W159132833 @default.
- W4382651806 hasRelatedWork W2293457016 @default.
- W4382651806 hasRelatedWork W2502722637 @default.
- W4382651806 hasRelatedWork W2953084091 @default.
- W4382651806 hasRelatedWork W2977842567 @default.
- W4382651806 hasRelatedWork W3198474835 @default.
- W4382651806 hasRelatedWork W4284679208 @default.
- W4382651806 hasRelatedWork W4298027009 @default.
- W4382651806 hasRelatedWork W4299318496 @default.
- W4382651806 hasRelatedWork W1872130062 @default.
- W4382651806 hasVolume "4" @default.
- W4382651806 isParatext "false" @default.
- W4382651806 isRetracted "false" @default.
- W4382651806 workType "article" @default.