Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315588746> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4315588746 abstract "Extraction of sentiment signals from news text, stock message boards, and business reports, for stock movement prediction, has been a rising field of interest in finance. Building upon past literature, the most recent works attempt to better capture sentiment from sentences with complex syntactic structures by introducing aspect-level sentiment classification (ASC). Despite the growing interest, however, fine-grained sentiment analysis has not been fully explored in non-English literature due to the shortage of annotated finance-specific data. Accordingly, it is necessary for non-English languages to leverage datasets and pre-trained language models (PLM) of different domains, languages, and tasks to best their performance. To facilitate finance-specific ASC research in the Korean language, we build KorFinASC, a Korean aspect-level sentiment classification dataset for finance consisting of 12,613 human-annotated samples, and explore methods of intermediate transfer learning. Our experiments indicate that past research has been ignorant towards the potentially wrong knowledge of financial entities encoded during the training phase, which has overestimated the predictive power of PLMs. In our work, we use the term non-stationary knowledge'' to refer to information that was previously correct but is likely to change, and present TGT-Masking'', a novel masking pattern to restrict PLMs from speculating knowledge of the kind. Finally, through a series of transfer learning with TGT-Masking applied we improve 22.63% of classification accuracy compared to standalone models on KorFinASC." @default.
- W4315588746 created "2023-01-11" @default.
- W4315588746 creator A5028962243 @default.
- W4315588746 creator A5048172321 @default.
- W4315588746 creator A5064294386 @default.
- W4315588746 creator A5072440755 @default.
- W4315588746 date "2023-01-08" @default.
- W4315588746 modified "2023-09-30" @default.
- W4315588746 title "Removing Non-Stationary Knowledge From Pre-Trained Language Models for Entity-Level Sentiment Classification in Finance" @default.
- W4315588746 doi "https://doi.org/10.48550/arxiv.2301.03136" @default.
- W4315588746 hasPublicationYear "2023" @default.
- W4315588746 type Work @default.
- W4315588746 citedByCount "0" @default.
- W4315588746 crossrefType "posted-content" @default.
- W4315588746 hasAuthorship W4315588746A5028962243 @default.
- W4315588746 hasAuthorship W4315588746A5048172321 @default.
- W4315588746 hasAuthorship W4315588746A5064294386 @default.
- W4315588746 hasAuthorship W4315588746A5072440755 @default.
- W4315588746 hasBestOaLocation W43155887461 @default.
- W4315588746 hasConcept C10138342 @default.
- W4315588746 hasConcept C119857082 @default.
- W4315588746 hasConcept C150899416 @default.
- W4315588746 hasConcept C153083717 @default.
- W4315588746 hasConcept C154945302 @default.
- W4315588746 hasConcept C162324750 @default.
- W4315588746 hasConcept C204321447 @default.
- W4315588746 hasConcept C41008148 @default.
- W4315588746 hasConcept C66402592 @default.
- W4315588746 hasConceptScore W4315588746C10138342 @default.
- W4315588746 hasConceptScore W4315588746C119857082 @default.
- W4315588746 hasConceptScore W4315588746C150899416 @default.
- W4315588746 hasConceptScore W4315588746C153083717 @default.
- W4315588746 hasConceptScore W4315588746C154945302 @default.
- W4315588746 hasConceptScore W4315588746C162324750 @default.
- W4315588746 hasConceptScore W4315588746C204321447 @default.
- W4315588746 hasConceptScore W4315588746C41008148 @default.
- W4315588746 hasConceptScore W4315588746C66402592 @default.
- W4315588746 hasLocation W43155887461 @default.
- W4315588746 hasOpenAccess W4315588746 @default.
- W4315588746 hasPrimaryLocation W43155887461 @default.
- W4315588746 hasRelatedWork W2960456850 @default.
- W4315588746 hasRelatedWork W3021430260 @default.
- W4315588746 hasRelatedWork W3107474891 @default.
- W4315588746 hasRelatedWork W3192503984 @default.
- W4315588746 hasRelatedWork W3192794374 @default.
- W4315588746 hasRelatedWork W4200526184 @default.
- W4315588746 hasRelatedWork W4281382123 @default.
- W4315588746 hasRelatedWork W4281645081 @default.
- W4315588746 hasRelatedWork W4285815787 @default.
- W4315588746 hasRelatedWork W4308262314 @default.
- W4315588746 isParatext "false" @default.
- W4315588746 isRetracted "false" @default.
- W4315588746 workType "article" @default.