FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014723908> ?p ?o ?g. }

• W3014723908 endingPage "842" @default.
• W3014723908 startingPage "828" @default.
• W3014723908 abstract "Text segmentation is a fundamental task in natural language processing. Depending on the levels of granularity, the task can be defined as segmenting a document into topical segments, or segmenting a sentence into elementary discourse units (EDUs). Traditional solutions to the two tasks heavily rely on carefully designed features. The recently proposed neural models do not need manual feature engineering, but they either suffer from sparse boundary tags or cannot efficiently handle the issue of variable size output vocabulary. In light of such limitations, we propose a generic end-to-end segmentation model, namely <inline-formula><tex-math notation=LaTeX>${mathrm{S}scriptstyle{mathrm{EG}}}{mathrm{B}scriptstyle{mathrm{OT}}}$</tex-math></inline-formula> , which first uses a bidirectional recurrent neural network to encode an input text sequence. <inline-formula><tex-math notation=LaTeX>${mathrm{S}scriptstyle{mathrm{EG}}}{mathrm{B}scriptstyle{mathrm{OT}}}$</tex-math></inline-formula> then uses another recurrent neural networks, together with a pointer network, to select text boundaries in the input sequence. In this way, <inline-formula><tex-math notation=LaTeX>${mathrm{S}scriptstyle{mathrm{EG}}}{mathrm{B}scriptstyle{mathrm{OT}}}$</tex-math></inline-formula> does not require any hand-crafted features. More importantly, <inline-formula><tex-math notation=LaTeX>${mathrm{S}scriptstyle{mathrm{EG}}}{mathrm{B}scriptstyle{mathrm{OT}}}$</tex-math></inline-formula> inherently handles the issue of variable size output vocabulary and the issue of sparse boundary tags. In our experiments, <inline-formula><tex-math notation=LaTeX>${mathrm{S}scriptstyle{mathrm{EG}}}{mathrm{B}scriptstyle{mathrm{OT}}}$</tex-math></inline-formula> outperforms state-of-the-art models on two tasks: document-level topic segmentation and sentence-level EDU segmentation. As a downstream application, we further propose a hierarchical attention model for sentence-level sentiment analysis based on the outcomes of <inline-formula><tex-math notation=LaTeX>${mathrm{S}scriptstyle{mathrm{EG}}}{mathrm{B}scriptstyle{mathrm{OT}}}$</tex-math></inline-formula> . The hierarchical model can make full use of both word-level and EDU-level information simultaneously for sentence-level sentiment analysis. In particular, it can effectively exploit EDU-level information, such as the inner properties of EDUs, which cannot be fully encoded in word-level features. Experimental results show that our hierarchical model achieves new state-of-the-art results on the Movie Review and Stanford Sentiment Treebank benchmarks." @default.
• W3014723908 created "2020-04-10" @default.
• W3014723908 creator A5007772416 @default.
• W3014723908 creator A5012677271 @default.
• W3014723908 creator A5024945225 @default.
• W3014723908 creator A5082634513 @default.
• W3014723908 date "2022-02-01" @default.
• W3014723908 modified "2023-10-02" @default.
• W3014723908 title "Neural Text Segmentation and its Application to Sentiment Analysis" @default.
• W3014723908 cites W1557074680 @default.
• W3014723908 cites W1567616047 @default.
• W3014723908 cites W1597655096 @default.
• W3014723908 cites W1623072288 @default.
• W3014723908 cites W1675155851 @default.
• W3014723908 cites W1809255060 @default.
• W3014723908 cites W1832693441 @default.
• W3014723908 cites W1894075015 @default.
• W3014723908 cites W1902237438 @default.
• W3014723908 cites W2001569578 @default.
• W3014723908 cites W2018627475 @default.
• W3014723908 cites W2027823133 @default.
• W3014723908 cites W2027869740 @default.
• W3014723908 cites W2028757787 @default.
• W3014723908 cites W2053569739 @default.
• W3014723908 cites W2055150316 @default.
• W3014723908 cites W2064675550 @default.
• W3014723908 cites W2079735306 @default.
• W3014723908 cites W2090276733 @default.
• W3014723908 cites W2096707493 @default.
• W3014723908 cites W2100626830 @default.
• W3014723908 cites W2104192042 @default.
• W3014723908 cites W2106918957 @default.
• W3014723908 cites W2141520705 @default.
• W3014723908 cites W2148818577 @default.
• W3014723908 cites W2154407881 @default.
• W3014723908 cites W2163455955 @default.
• W3014723908 cites W2250473257 @default.
• W3014723908 cites W2250539671 @default.
• W3014723908 cites W2251124635 @default.
• W3014723908 cites W2296283641 @default.
• W3014723908 cites W2461708311 @default.
• W3014723908 cites W2512217112 @default.
• W3014723908 cites W2567406479 @default.
• W3014723908 cites W2613831280 @default.
• W3014723908 cites W2741989495 @default.
• W3014723908 cites W2758765981 @default.
• W3014723908 cites W2763401128 @default.
• W3014723908 cites W2785787385 @default.
• W3014723908 cites W2788347302 @default.
• W3014723908 cites W2789326730 @default.
• W3014723908 cites W2791817847 @default.
• W3014723908 cites W2807938752 @default.
• W3014723908 cites W2884859571 @default.
• W3014723908 cites W2952280064 @default.
• W3014723908 cites W2962739339 @default.
• W3014723908 cites W2962853227 @default.
• W3014723908 cites W2962902328 @default.
• W3014723908 cites W2963140597 @default.
• W3014723908 cites W2963341956 @default.
• W3014723908 cites W2963355447 @default.
• W3014723908 cites W2963625095 @default.
• W3014723908 cites W2964199361 @default.
• W3014723908 cites W2964236337 @default.
• W3014723908 cites W2964288660 @default.
• W3014723908 cites W2965435509 @default.
• W3014723908 cites W3011594683 @default.
• W3014723908 cites W3099880460 @default.
• W3014723908 cites W3124174211 @default.
• W3014723908 cites W4210984920 @default.
• W3014723908 cites W4238205294 @default.
• W3014723908 doi "https://doi.org/10.1109/tkde.2020.2983360" @default.
• W3014723908 hasPublicationYear "2022" @default.
• W3014723908 type Work @default.
• W3014723908 sameAs 3014723908 @default.
• W3014723908 citedByCount "17" @default.
• W3014723908 countsByYear W30147239082021 @default.
• W3014723908 countsByYear W30147239082022 @default.
• W3014723908 countsByYear W30147239082023 @default.
• W3014723908 crossrefType "journal-article" @default.
• W3014723908 hasAuthorship W3014723908A5007772416 @default.
• W3014723908 hasAuthorship W3014723908A5012677271 @default.
• W3014723908 hasAuthorship W3014723908A5024945225 @default.
• W3014723908 hasAuthorship W3014723908A5082634513 @default.
• W3014723908 hasConcept C11413529 @default.
• W3014723908 hasConcept C114614502 @default.
• W3014723908 hasConcept C118615104 @default.
• W3014723908 hasConcept C154945302 @default.
• W3014723908 hasConcept C33923547 @default.
• W3014723908 hasConcept C41008148 @default.
• W3014723908 hasConcept C45357846 @default.
• W3014723908 hasConcept C89600930 @default.
• W3014723908 hasConcept C94375191 @default.
• W3014723908 hasConceptScore W3014723908C11413529 @default.
• W3014723908 hasConceptScore W3014723908C114614502 @default.
• W3014723908 hasConceptScore W3014723908C118615104 @default.
• W3014723908 hasConceptScore W3014723908C154945302 @default.
• W3014723908 hasConceptScore W3014723908C33923547 @default.
• W3014723908 hasConceptScore W3014723908C41008148 @default.

• next