FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2917049430> ?p ?o ?g. }

• W2917049430 endingPage "26156" @default.
• W2917049430 startingPage "26146" @default.
• W2917049430 abstract "Answer selection is a crucial subtask in the question answering (QA) system. Conventional avenues for this task mainly concentrate on developing linguistic tools that are limited in both performance and practicability. Answer selection approaches based on deep learning have been well investigated with the tremendous success of deep learning in natural language processing. However, the traditional neural networks employed in existing answer selection models, i.e., recursive neural network or convolutional neural network, typically suffer from obtaining the global text information due to their operating mechanisms. The recent Transformer neural network is considered to be good at extracting the global information by employing only self-attention mechanism. Thus, in this paper, we design a Transformer-based neural network for answer selection, where we deploy a bidirectional long short-term memory (BiLSTM) behind the Transformer to acquire both global information and sequential features in the question or answer sentence. Different from the original Transformer, our Transformer-based network focuses on sentence embedding rather than the seq2seq task. In addition, we employ a BiLSTM rather than utilizing the position encoding to incorporate sequential features as the universal Transformer does. Furthermore, we apply three aggregated strategies to generate sentence embeddings for question and answer, i.e., the weighted mean pooling, the max pooling, and the attentive pooling, leading to three corresponding Transformer-based models, i.e., QA-TF $_{{W!P}}$ , QA-TF $_{{M!P}}$ , and QA-TF $_{{A!P}}$ , respectively. Finally, we evaluate our proposals on a popular QA dataset WikiQA. The experimental results demonstrate that our proposed Transformer-based answer selection models can produce a better performance compared with several competitive baselines. In detail, our best model outperforms the state-of-the-art baseline by up to 2.37%, 2.83%, and 3.79% in terms of MAP, MRR, and accuracy, respectively." @default.
• W2917049430 created "2019-03-02" @default.
• W2917049430 creator A5006578545 @default.
• W2917049430 creator A5026327666 @default.
• W2917049430 creator A5047402353 @default.
• W2917049430 creator A5088713288 @default.
• W2917049430 date "2019-01-01" @default.
• W2917049430 modified "2023-10-12" @default.
• W2917049430 title "Transformer-Based Neural Network for Answer Selection in Question Answering" @default.
• W2917049430 cites W1678356000 @default.
• W2917049430 cites W1966443646 @default.
• W2917049430 cites W1971844566 @default.
• W2917049430 cites W2064675550 @default.
• W2917049430 cites W2103452139 @default.
• W2917049430 cites W2106121453 @default.
• W2917049430 cites W2112796928 @default.
• W2917049430 cites W2171278097 @default.
• W2917049430 cites W2251202616 @default.
• W2917049430 cites W2251818205 @default.
• W2917049430 cites W2301095666 @default.
• W2917049430 cites W2511929605 @default.
• W2917049430 cites W2517148058 @default.
• W2917049430 cites W2907588548 @default.
• W2917049430 cites W2964154091 @default.
• W2917049430 cites W2964199361 @default.
• W2917049430 doi "https://doi.org/10.1109/access.2019.2900753" @default.
• W2917049430 hasPublicationYear "2019" @default.
• W2917049430 type Work @default.
• W2917049430 sameAs 2917049430 @default.
• W2917049430 citedByCount "57" @default.
• W2917049430 countsByYear W29170494302019 @default.
• W2917049430 countsByYear W29170494302020 @default.
• W2917049430 countsByYear W29170494302021 @default.
• W2917049430 countsByYear W29170494302022 @default.
• W2917049430 countsByYear W29170494302023 @default.
• W2917049430 crossrefType "journal-article" @default.
• W2917049430 hasAuthorship W2917049430A5006578545 @default.
• W2917049430 hasAuthorship W2917049430A5026327666 @default.
• W2917049430 hasAuthorship W2917049430A5047402353 @default.
• W2917049430 hasAuthorship W2917049430A5088713288 @default.
• W2917049430 hasBestOaLocation W29170494301 @default.
• W2917049430 hasConcept C119599485 @default.
• W2917049430 hasConcept C119857082 @default.
• W2917049430 hasConcept C127413603 @default.
• W2917049430 hasConcept C154945302 @default.
• W2917049430 hasConcept C165801399 @default.
• W2917049430 hasConcept C204321447 @default.
• W2917049430 hasConcept C41008148 @default.
• W2917049430 hasConcept C44291984 @default.
• W2917049430 hasConcept C50644808 @default.
• W2917049430 hasConcept C66322947 @default.
• W2917049430 hasConcept C81917197 @default.
• W2917049430 hasConceptScore W2917049430C119599485 @default.
• W2917049430 hasConceptScore W2917049430C119857082 @default.
• W2917049430 hasConceptScore W2917049430C127413603 @default.
• W2917049430 hasConceptScore W2917049430C154945302 @default.
• W2917049430 hasConceptScore W2917049430C165801399 @default.
• W2917049430 hasConceptScore W2917049430C204321447 @default.
• W2917049430 hasConceptScore W2917049430C41008148 @default.
• W2917049430 hasConceptScore W2917049430C44291984 @default.
• W2917049430 hasConceptScore W2917049430C50644808 @default.
• W2917049430 hasConceptScore W2917049430C66322947 @default.
• W2917049430 hasConceptScore W2917049430C81917197 @default.
• W2917049430 hasFunder F4320321001 @default.
• W2917049430 hasLocation W29170494301 @default.
• W2917049430 hasOpenAccess W2917049430 @default.
• W2917049430 hasPrimaryLocation W29170494301 @default.
• W2917049430 hasRelatedWork W128392744 @default.
• W2917049430 hasRelatedWork W1517743118 @default.
• W2917049430 hasRelatedWork W1518289136 @default.
• W2917049430 hasRelatedWork W1527340856 @default.
• W2917049430 hasRelatedWork W1560657467 @default.
• W2917049430 hasRelatedWork W207304934 @default.
• W2917049430 hasRelatedWork W2251181482 @default.
• W2917049430 hasRelatedWork W2747680751 @default.
• W2917049430 hasRelatedWork W3107474891 @default.
• W2917049430 hasRelatedWork W1629725936 @default.
• W2917049430 hasVolume "7" @default.
• W2917049430 isParatext "false" @default.
• W2917049430 isRetracted "false" @default.
• W2917049430 magId "2917049430" @default.
• W2917049430 workType "article" @default.