Papers by Sudeshna Sarkar
ArgGen: Prompting Text Generation Models for Document-Level Event-Argument Aggregation (2022.findings-aacl)
Copied to clipboard
| Challenge: | Existing discourse-level information extraction tasks are extractive in nature, but extracting information from larger bodies of discourse-like documents requires more natural language understanding and reasoning capabilities. |
| Approach: | They propose a conditional text generation approach which generates consolidated event-arguments at a document-level with minimal loss of information. |
| Outcome: | The proposed approach generates document-level argument spans in a low-resource and zero-shot setting and can be leveraged in other related multilingual text generation tasks. |
PESE: Event Structure Extraction using Pointer Network based Encoder-Decoder Architecture (2022.aacl-main)
Copied to clipboard
| Challenge: | Event extraction (EE) aims to find the events and event-related argument information from the text and represent them in a structured format. |
| Approach: | They propose to represent each event record in a unique tuple format that contains trigger phrase, trigger type, argument phrase, and corresponding role information. |
| Outcome: | The proposed model achieves competitive performance compared to the state-of-the-art methods. |
Does Meta-learning Help mBERT for Few-shot Question Generation in a Cross-lingual Transfer Setting for Indic Languages? (2022.coling-1)
Copied to clipboard
Aniruddha Roy, Rupak Kumar Thakur, Isha Sharma, Ashim Gupta, Amrith Krishna, Sudeshna Sarkar, Pawan Goyal
| Challenge: | Existing approaches to few-shot Question Generation (QG) are limited and require manual annotation. |
| Approach: | They propose to use multilingual BERT to perform few-shot question generation with cross-lingual transfer. |
| Outcome: | The proposed model improves in few-shot QG and human evaluation confirms it. |
Biomedical Relation Classification by single and multiple source domain adaptation (D19-62)
Copied to clipboard
| Challenge: | Existing supervised systems are highly data-driven and require a lot of effort to label data for a new domain. |
| Approach: | They propose to transfer knowledge from one or more related source domains to another domain to improve relation classification. |
| Outcome: | The proposed model outperforms neural-network based models on biomedical datasets and with contextualized embeddings on 3 biomedically-relevant datasets. |