FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952013107> ?p ?o ?g. }

• W2952013107 abstract "Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality. Most NLG systems in common use employ rules and heuristics and tend to generate rigid and stylised responses without the natural variation of human language. They are also not easily scaled to systems covering multiple domains and languages. This paper presents a statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure. The LSTM generator can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates. With fewer heuristics, an objective evaluation in two differing test domains showed the proposed method improved performance compared to previous methods. Human judges scored the LSTM system higher on informativeness and naturalness and overall preferred it to the other systems." @default.
• W2952013107 created "2019-06-27" @default.
• W2952013107 creator A5019913562 @default.
• W2952013107 creator A5030147577 @default.
• W2952013107 creator A5040922365 @default.
• W2952013107 creator A5051889115 @default.
• W2952013107 creator A5077472653 @default.
• W2952013107 creator A5087009911 @default.
• W2952013107 date "2015-08-07" @default.
• W2952013107 modified "2023-10-01" @default.
• W2952013107 title "Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems" @default.
• W2952013107 cites W1492935830 @default.
• W2952013107 cites W1521413921 @default.
• W2952013107 cites W1552182777 @default.
• W2952013107 cites W1591801644 @default.
• W2952013107 cites W1606347560 @default.
• W2952013107 cites W1810943226 @default.
• W2952013107 cites W196214544 @default.
• W2952013107 cites W1970207841 @default.
• W2952013107 cites W1980340273 @default.
• W2952013107 cites W1999965501 @default.
• W2952013107 cites W2004637830 @default.
• W2952013107 cites W2024632416 @default.
• W2952013107 cites W2045738181 @default.
• W2952013107 cites W2055537935 @default.
• W2952013107 cites W2095705004 @default.
• W2952013107 cites W2099542783 @default.
• W2952013107 cites W2101105183 @default.
• W2952013107 cites W2104368104 @default.
• W2952013107 cites W2108239140 @default.
• W2952013107 cites W2110313598 @default.
• W2952013107 cites W2115221470 @default.
• W2952013107 cites W2117130368 @default.
• W2952013107 cites W2122585011 @default.
• W2952013107 cites W2131774270 @default.
• W2952013107 cites W2136016850 @default.
• W2952013107 cites W2139079654 @default.
• W2952013107 cites W2143612262 @default.
• W2952013107 cites W2150355110 @default.
• W2952013107 cites W2160815625 @default.
• W2952013107 cites W2161181481 @default.
• W2952013107 cites W2250539671 @default.
• W2952013107 cites W225503657 @default.
• W2952013107 cites W2257626115 @default.
• W2952013107 cites W2949888546 @default.
• W2952013107 cites W2950527759 @default.
• W2952013107 cites W2951176429 @default.
• W2952013107 cites W2951805548 @default.
• W2952013107 cites W1534317862 @default.
• W2952013107 cites W1917215959 @default.
• W2952013107 doi "https://doi.org/10.48550/arxiv.1508.01745" @default.
• W2952013107 hasPublicationYear "2015" @default.
• W2952013107 type Work @default.
• W2952013107 sameAs 2952013107 @default.
• W2952013107 citedByCount "94" @default.
• W2952013107 countsByYear W29520131072015 @default.
• W2952013107 countsByYear W29520131072016 @default.
• W2952013107 countsByYear W29520131072017 @default.
• W2952013107 countsByYear W29520131072018 @default.
• W2952013107 countsByYear W29520131072019 @default.
• W2952013107 countsByYear W29520131072020 @default.
• W2952013107 countsByYear W29520131072021 @default.
• W2952013107 crossrefType "posted-content" @default.
• W2952013107 hasAuthorship W2952013107A5019913562 @default.
• W2952013107 hasAuthorship W2952013107A5030147577 @default.
• W2952013107 hasAuthorship W2952013107A5040922365 @default.
• W2952013107 hasAuthorship W2952013107A5051889115 @default.
• W2952013107 hasAuthorship W2952013107A5077472653 @default.
• W2952013107 hasAuthorship W2952013107A5087009911 @default.
• W2952013107 hasBestOaLocation W29520131071 @default.
• W2952013107 hasConcept C107457646 @default.
• W2952013107 hasConcept C111919701 @default.
• W2952013107 hasConcept C121332964 @default.
• W2952013107 hasConcept C127705205 @default.
• W2952013107 hasConcept C134537474 @default.
• W2952013107 hasConcept C154945302 @default.
• W2952013107 hasConcept C163258240 @default.
• W2952013107 hasConcept C168167062 @default.
• W2952013107 hasConcept C170130773 @default.
• W2952013107 hasConcept C195324797 @default.
• W2952013107 hasConcept C204321447 @default.
• W2952013107 hasConcept C2776187449 @default.
• W2952013107 hasConcept C2776230583 @default.
• W2952013107 hasConcept C2777530160 @default.
• W2952013107 hasConcept C2779439875 @default.
• W2952013107 hasConcept C2779462738 @default.
• W2952013107 hasConcept C2780992000 @default.
• W2952013107 hasConcept C41008148 @default.
• W2952013107 hasConcept C62520636 @default.
• W2952013107 hasConcept C97355855 @default.
• W2952013107 hasConceptScore W2952013107C107457646 @default.
• W2952013107 hasConceptScore W2952013107C111919701 @default.
• W2952013107 hasConceptScore W2952013107C121332964 @default.
• W2952013107 hasConceptScore W2952013107C127705205 @default.
• W2952013107 hasConceptScore W2952013107C134537474 @default.
• W2952013107 hasConceptScore W2952013107C154945302 @default.
• W2952013107 hasConceptScore W2952013107C163258240 @default.
• W2952013107 hasConceptScore W2952013107C168167062 @default.
• W2952013107 hasConceptScore W2952013107C170130773 @default.
• W2952013107 hasConceptScore W2952013107C195324797 @default.

• next