Papers by Parantak Singh
LESA: Linguistic Encapsulation and Semantic Amalgamation Based Generalised Claim Detection from Online Content (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing work on claim detection is built on the basis of a 'segregation' of claims across different domains. |
| Approach: | They propose a generalized generalized model that captures syntactic features through part-of-speech and dependency embeddings, as well as contextual features through a fine-tuned language model. |
| Outcome: | The proposed model outperforms baselines on six claim datasets by an average of 3 claim-F1 points and 2 claim-f1 points on the general-domain experiments. |