| dc.contributor.author | Nakwijit, P | en_US |
| dc.contributor.author | Purver, M | en_US |
| dc.contributor.author | The International Conference on Language Resources and Evaluation 2022 | en_US |
| dc.date.accessioned | 2022-08-30T10:35:12Z | |
| dc.date.available | 2022-04-05 | en_US |
| dc.date.issued | 2022-06-22 | en_US |
| dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/80210 | |
| dc.description.abstract | User-generated content is full of misspellings. Rather than being just random noise, we hypothesise that many misspellings contain hidden semantics that can be leveraged for language understanding tasks. This paper presents a fine-grained annotated corpus of misspelling in Thai, together with an analysis of misspelling intention and its possible semantics to get a better understanding of the misspelling patterns observed in the corpus. In addition, we introduce two approaches to incorporate the semantics of misspelling: Misspelling Average Embedding (MAE) and Misspelling Semantic Tokens (MST). Experiments on a sentiment analysis task confirm our overall hypothesis: additional semantics from misspelling can boost the micro F1 score up to 0.4-2%, while blindly normalising misspelling is harmful and suboptimal. | en_US |
| dc.title | Misspelling Semantics In Thai | en_US |
| dc.type | Conference Proceeding | |
| dc.rights.holder | © 2022 The Author(s). Published by The International Conference on Language Resources and Evaluation | |
| pubs.notes | Not known | en_US |
| pubs.publication-status | Published | en_US |
| dcterms.dateAccepted | 2022-04-05 | en_US |
| rioxxterms.funder | Default funder | en_US |
| rioxxterms.identifier.project | Default project | en_US |
