FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949278967> ?p ?o ?g. }

• W2949278967 abstract "Computational models for sarcasm detection have often relied on the content of utterances in isolation. However, the speaker's sarcastic intent is not always apparent without additional context. Focusing on social media discussions, we investigate three issues: (1) does modeling conversation context help in sarcasm detection; (2) can we identify what part of conversation context triggered the sarcastic reply; and (3) given a sarcastic post that contains multiple sentences, can we identify the specific sentence that is sarcastic. To address the first issue, we investigate several types of Long Short-Term Memory (LSTM) networks that can model both the conversation context and the current turn. We show that LSTM networks with sentence-level attention on context and current turn, as well as the conditional LSTM network (Rocktaschel et al. 2016), outperform the LSTM model that reads only the current turn. As conversation context, we consider the prior turn, the succeeding turn or both. Our computational models are tested on two types of social media platforms: Twitter and discussion forums. We discuss several differences between these datasets ranging from their size to the nature of the gold-label annotations. To address the last two issues, we present a qualitative analysis of attention weights produced by the LSTM models (with attention) and discuss the results compared with human performance on the two tasks." @default.
• W2949278967 created "2019-06-27" @default.
• W2949278967 creator A5023648764 @default.
• W2949278967 creator A5043262011 @default.
• W2949278967 creator A5068587810 @default.
• W2949278967 date "2018-08-22" @default.
• W2949278967 modified "2023-09-23" @default.
• W2949278967 title "Sarcasm Analysis using Conversation Context" @default.
• W2949278967 cites W1515671031 @default.
• W2949278967 cites W1591801644 @default.
• W2949278967 cites W1598447808 @default.
• W2949278967 cites W1733704070 @default.
• W2949278967 cites W1842080548 @default.
• W2949278967 cites W19325706 @default.
• W2949278967 cites W2022204871 @default.
• W2949278967 cites W2024011160 @default.
• W2949278967 cites W2039120654 @default.
• W2949278967 cites W2064675550 @default.
• W2949278967 cites W2077018496 @default.
• W2949278967 cites W2093183130 @default.
• W2949278967 cites W2095705004 @default.
• W2949278967 cites W2104246439 @default.
• W2949278967 cites W2114661483 @default.
• W2949278967 cites W2131505766 @default.
• W2949278967 cites W2132210327 @default.
• W2949278967 cites W2142112646 @default.
• W2949278967 cites W2153222072 @default.
• W2949278967 cites W2153635508 @default.
• W2949278967 cites W2157765050 @default.
• W2949278967 cites W2160660844 @default.
• W2949278967 cites W2211192759 @default.
• W2949278967 cites W2223340824 @default.
• W2949278967 cites W2250247764 @default.
• W2949278967 cites W2250480277 @default.
• W2949278967 cites W2250489604 @default.
• W2949278967 cites W2250710744 @default.
• W2949278967 cites W2251210340 @default.
• W2949278967 cites W2251920663 @default.
• W2949278967 cites W2251958472 @default.
• W2949278967 cites W2252381721 @default.
• W2949278967 cites W2263859238 @default.
• W2949278967 cites W2277095315 @default.
• W2949278967 cites W2294058101 @default.
• W2949278967 cites W2404480901 @default.
• W2949278967 cites W2413794162 @default.
• W2949278967 cites W2489370933 @default.
• W2949278967 cites W2510141903 @default.
• W2949278967 cites W2512470422 @default.
• W2949278967 cites W2512532697 @default.
• W2949278967 cites W2576562514 @default.
• W2949278967 cites W2604716683 @default.
• W2949278967 cites W2605659599 @default.
• W2949278967 cites W2754247709 @default.
• W2949278967 cites W2758985501 @default.
• W2949278967 cites W2765736925 @default.
• W2949278967 cites W2949888546 @default.
• W2949278967 cites W2950178297 @default.
• W2949278967 cites W2950577311 @default.
• W2949278967 cites W2952072734 @default.
• W2949278967 cites W2953084091 @default.
• W2949278967 cites W2962809001 @default.
• W2949278967 cites W2963069010 @default.
• W2949278967 cites W2963635943 @default.
• W2949278967 cites W2964066928 @default.
• W2949278967 cites W2964126051 @default.
• W2949278967 hasPublicationYear "2018" @default.
• W2949278967 type Work @default.
• W2949278967 sameAs 2949278967 @default.
• W2949278967 citedByCount "2" @default.
• W2949278967 countsByYear W29492789672019 @default.
• W2949278967 countsByYear W29492789672020 @default.
• W2949278967 crossrefType "posted-content" @default.
• W2949278967 hasAuthorship W2949278967A5023648764 @default.
• W2949278967 hasAuthorship W2949278967A5043262011 @default.
• W2949278967 hasAuthorship W2949278967A5068587810 @default.
• W2949278967 hasConcept C136764020 @default.
• W2949278967 hasConcept C138885662 @default.
• W2949278967 hasConcept C151730666 @default.
• W2949278967 hasConcept C154945302 @default.
• W2949278967 hasConcept C15744967 @default.
• W2949278967 hasConcept C204321447 @default.
• W2949278967 hasConcept C2776207355 @default.
• W2949278967 hasConcept C2777200299 @default.
• W2949278967 hasConcept C2777530160 @default.
• W2949278967 hasConcept C2779343474 @default.
• W2949278967 hasConcept C2779975665 @default.
• W2949278967 hasConcept C41008148 @default.
• W2949278967 hasConcept C41895202 @default.
• W2949278967 hasConcept C46312422 @default.
• W2949278967 hasConcept C518677369 @default.
• W2949278967 hasConcept C66024118 @default.
• W2949278967 hasConcept C86803240 @default.
• W2949278967 hasConceptScore W2949278967C136764020 @default.
• W2949278967 hasConceptScore W2949278967C138885662 @default.
• W2949278967 hasConceptScore W2949278967C151730666 @default.
• W2949278967 hasConceptScore W2949278967C154945302 @default.
• W2949278967 hasConceptScore W2949278967C15744967 @default.
• W2949278967 hasConceptScore W2949278967C204321447 @default.
• W2949278967 hasConceptScore W2949278967C2776207355 @default.
• W2949278967 hasConceptScore W2949278967C2777200299 @default.

• next