Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042754229> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W3042754229 abstract "Emojis are a succinct form of language which can express concrete meanings, emotions, and intentions. Emojis also carry signals that can be used to better understand communicative intent. They have become a ubiquitous part of our daily lives, making them an important part of understanding user-generated content. The emoji prediction task aims at predicting the proper set of emojis associated with a piece of text. Through emoji prediction, models can learn rich representations of the communicative intent of the written text. While existing research on the emoji prediction task focus on a small subset of emoji types closely related to certain emotions, this setting oversimplifies the task and wastes the expressive power of emojis. In this paper, we extend the existing setting of the emoji prediction task to include a richer set of emojis and to allow multi-label classification on the task. We propose novel models for multi-class and multi-label emoji prediction based on Transformer networks. We also construct multiple emoji prediction datasets from Twitter using heuristics. The BERT models achieve state-of-the-art performances on all our datasets under all the settings, with relative improvements of 27.21% to 236.36% in accuracy, 2.01% to 88.28% in top-5 accuracy and 65.19% to 346.79% in F-1 score, compared to the prior state-of-the-art. Our results demonstrate the efficacy of deep Transformer-based models on the emoji prediction task. We also release our datasets at https://github.com/hikari-NYU/Emoji_Prediction_Datasets_MMS for future researchers." @default.
- W3042754229 created "2020-07-23" @default.
- W3042754229 creator A5023339675 @default.
- W3042754229 creator A5035399743 @default.
- W3042754229 creator A5043402333 @default.
- W3042754229 creator A5061058262 @default.
- W3042754229 date "2020-07-14" @default.
- W3042754229 modified "2023-10-16" @default.
- W3042754229 title "Emoji Prediction: Extensions and Benchmarking" @default.
- W3042754229 cites W2740654653 @default.
- W3042754229 cites W2807333695 @default.
- W3042754229 cites W2896457183 @default.
- W3042754229 cites W2899435814 @default.
- W3042754229 cites W2916132663 @default.
- W3042754229 cites W2945387691 @default.
- W3042754229 cites W2950349567 @default.
- W3042754229 cites W2963468968 @default.
- W3042754229 cites W3037848111 @default.
- W3042754229 doi "https://doi.org/10.48550/arxiv.2007.07389" @default.
- W3042754229 hasPublicationYear "2020" @default.
- W3042754229 type Work @default.
- W3042754229 sameAs 3042754229 @default.
- W3042754229 citedByCount "2" @default.
- W3042754229 countsByYear W30427542292020 @default.
- W3042754229 countsByYear W30427542292021 @default.
- W3042754229 crossrefType "posted-content" @default.
- W3042754229 hasAuthorship W3042754229A5023339675 @default.
- W3042754229 hasAuthorship W3042754229A5035399743 @default.
- W3042754229 hasAuthorship W3042754229A5043402333 @default.
- W3042754229 hasAuthorship W3042754229A5061058262 @default.
- W3042754229 hasBestOaLocation W30427542291 @default.
- W3042754229 hasConcept C111472728 @default.
- W3042754229 hasConcept C111919701 @default.
- W3042754229 hasConcept C119857082 @default.
- W3042754229 hasConcept C127705205 @default.
- W3042754229 hasConcept C136764020 @default.
- W3042754229 hasConcept C138885662 @default.
- W3042754229 hasConcept C144133560 @default.
- W3042754229 hasConcept C154945302 @default.
- W3042754229 hasConcept C162324750 @default.
- W3042754229 hasConcept C162853370 @default.
- W3042754229 hasConcept C177264268 @default.
- W3042754229 hasConcept C187736073 @default.
- W3042754229 hasConcept C199360897 @default.
- W3042754229 hasConcept C204321447 @default.
- W3042754229 hasConcept C2778136018 @default.
- W3042754229 hasConcept C2779247141 @default.
- W3042754229 hasConcept C2780451532 @default.
- W3042754229 hasConcept C2780801425 @default.
- W3042754229 hasConcept C41008148 @default.
- W3042754229 hasConcept C518677369 @default.
- W3042754229 hasConcept C86251818 @default.
- W3042754229 hasConceptScore W3042754229C111472728 @default.
- W3042754229 hasConceptScore W3042754229C111919701 @default.
- W3042754229 hasConceptScore W3042754229C119857082 @default.
- W3042754229 hasConceptScore W3042754229C127705205 @default.
- W3042754229 hasConceptScore W3042754229C136764020 @default.
- W3042754229 hasConceptScore W3042754229C138885662 @default.
- W3042754229 hasConceptScore W3042754229C144133560 @default.
- W3042754229 hasConceptScore W3042754229C154945302 @default.
- W3042754229 hasConceptScore W3042754229C162324750 @default.
- W3042754229 hasConceptScore W3042754229C162853370 @default.
- W3042754229 hasConceptScore W3042754229C177264268 @default.
- W3042754229 hasConceptScore W3042754229C187736073 @default.
- W3042754229 hasConceptScore W3042754229C199360897 @default.
- W3042754229 hasConceptScore W3042754229C204321447 @default.
- W3042754229 hasConceptScore W3042754229C2778136018 @default.
- W3042754229 hasConceptScore W3042754229C2779247141 @default.
- W3042754229 hasConceptScore W3042754229C2780451532 @default.
- W3042754229 hasConceptScore W3042754229C2780801425 @default.
- W3042754229 hasConceptScore W3042754229C41008148 @default.
- W3042754229 hasConceptScore W3042754229C518677369 @default.
- W3042754229 hasConceptScore W3042754229C86251818 @default.
- W3042754229 hasLocation W30427542291 @default.
- W3042754229 hasOpenAccess W3042754229 @default.
- W3042754229 hasPrimaryLocation W30427542291 @default.
- W3042754229 hasRelatedWork W1848359393 @default.
- W3042754229 hasRelatedWork W2081647779 @default.
- W3042754229 hasRelatedWork W2127025027 @default.
- W3042754229 hasRelatedWork W2961085424 @default.
- W3042754229 hasRelatedWork W2999063186 @default.
- W3042754229 hasRelatedWork W3009603553 @default.
- W3042754229 hasRelatedWork W3040620603 @default.
- W3042754229 hasRelatedWork W3119715496 @default.
- W3042754229 hasRelatedWork W3185852197 @default.
- W3042754229 hasRelatedWork W4283702175 @default.
- W3042754229 isParatext "false" @default.
- W3042754229 isRetracted "false" @default.
- W3042754229 magId "3042754229" @default.
- W3042754229 workType "article" @default.