Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104263599> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3104263599 abstract "The recently proposed quantum language model (QLM) aimed at a principled approach to modeling term dependency by applying the quantum probability theory. The latest development for a more effective QLM has adopted word embeddings as a kind of global dependency information and integrated the quantum-inspired idea in a neural network architecture. While these quantum-inspired LMs are theoretically more general and also practically effective, they have two major limitations. First, they have not taken into account the interaction among words with multiple meanings, which is common and important in understanding natural language text. Second, the integration of the quantum-inspired LM with the neural network was mainly for effective training of parameters, yet lacking a theoretical foundation accounting for such integration. To address these two issues, in this paper, we propose a Quantum Many-body Wave Function (QMWF) inspired language modeling approach. The QMWF inspired LM can adopt the tensor product to model the aforesaid interaction among words. It also enables us to reveal the inherent necessity of using Convolutional Neural Network (CNN) in QMWF language modeling. Furthermore, our approach delivers a simple algorithm to represent and match text/sentence pairs. Systematic evaluation shows the effectiveness of the proposed QMWF-LM algorithm, in comparison with the state of the art quantum-inspired LMs and a couple of CNN-based methods, on three typical Question Answering (QA) datasets." @default.
- W3104263599 created "2020-11-23" @default.
- W3104263599 creator A5029360035 @default.
- W3104263599 creator A5038307223 @default.
- W3104263599 creator A5050532724 @default.
- W3104263599 creator A5057282504 @default.
- W3104263599 creator A5060027762 @default.
- W3104263599 date "2018-10-17" @default.
- W3104263599 modified "2023-09-23" @default.
- W3104263599 title "A Quantum Many-body Wave Function Inspired Language Modeling Approach" @default.
- W3104263599 cites W1508593203 @default.
- W3104263599 cites W1915024344 @default.
- W3104263599 cites W1966443646 @default.
- W3104263599 cites W2055467685 @default.
- W3104263599 cites W2059059956 @default.
- W3104263599 cites W2070740689 @default.
- W3104263599 cites W2087746031 @default.
- W3104263599 cites W2099437808 @default.
- W3104263599 cites W2102306213 @default.
- W3104263599 cites W2160416736 @default.
- W3104263599 cites W2185337446 @default.
- W3104263599 cites W2250539671 @default.
- W3104263599 cites W2251818205 @default.
- W3104263599 cites W2419175238 @default.
- W3104263599 cites W2536015822 @default.
- W3104263599 cites W2610935556 @default.
- W3104263599 cites W2741924718 @default.
- W3104263599 cites W2756668352 @default.
- W3104263599 cites W3101747393 @default.
- W3104263599 cites W4211080241 @default.
- W3104263599 doi "https://doi.org/10.1145/3269206.3271723" @default.
- W3104263599 hasPublicationYear "2018" @default.
- W3104263599 type Work @default.
- W3104263599 sameAs 3104263599 @default.
- W3104263599 citedByCount "19" @default.
- W3104263599 countsByYear W31042635992018 @default.
- W3104263599 countsByYear W31042635992019 @default.
- W3104263599 countsByYear W31042635992020 @default.
- W3104263599 countsByYear W31042635992021 @default.
- W3104263599 countsByYear W31042635992022 @default.
- W3104263599 countsByYear W31042635992023 @default.
- W3104263599 crossrefType "proceedings-article" @default.
- W3104263599 hasAuthorship W3104263599A5029360035 @default.
- W3104263599 hasAuthorship W3104263599A5038307223 @default.
- W3104263599 hasAuthorship W3104263599A5050532724 @default.
- W3104263599 hasAuthorship W3104263599A5057282504 @default.
- W3104263599 hasAuthorship W3104263599A5060027762 @default.
- W3104263599 hasBestOaLocation W31042635992 @default.
- W3104263599 hasConcept C121332964 @default.
- W3104263599 hasConcept C137293760 @default.
- W3104263599 hasConcept C154945302 @default.
- W3104263599 hasConcept C19768560 @default.
- W3104263599 hasConcept C41008148 @default.
- W3104263599 hasConcept C62520636 @default.
- W3104263599 hasConcept C80444323 @default.
- W3104263599 hasConcept C84114770 @default.
- W3104263599 hasConceptScore W3104263599C121332964 @default.
- W3104263599 hasConceptScore W3104263599C137293760 @default.
- W3104263599 hasConceptScore W3104263599C154945302 @default.
- W3104263599 hasConceptScore W3104263599C19768560 @default.
- W3104263599 hasConceptScore W3104263599C41008148 @default.
- W3104263599 hasConceptScore W3104263599C62520636 @default.
- W3104263599 hasConceptScore W3104263599C80444323 @default.
- W3104263599 hasConceptScore W3104263599C84114770 @default.
- W3104263599 hasLocation W31042635991 @default.
- W3104263599 hasLocation W31042635992 @default.
- W3104263599 hasLocation W31042635993 @default.
- W3104263599 hasOpenAccess W3104263599 @default.
- W3104263599 hasPrimaryLocation W31042635991 @default.
- W3104263599 hasRelatedWork W1529400504 @default.
- W3104263599 hasRelatedWork W1989705153 @default.
- W3104263599 hasRelatedWork W2101452068 @default.
- W3104263599 hasRelatedWork W2351267244 @default.
- W3104263599 hasRelatedWork W2496228846 @default.
- W3104263599 hasRelatedWork W2888625260 @default.
- W3104263599 hasRelatedWork W2896411932 @default.
- W3104263599 hasRelatedWork W63071447 @default.
- W3104263599 hasRelatedWork W65617392 @default.
- W3104263599 hasRelatedWork W2169928498 @default.
- W3104263599 isParatext "false" @default.
- W3104263599 isRetracted "false" @default.
- W3104263599 magId "3104263599" @default.
- W3104263599 workType "article" @default.