Papers by Ashish Chouhan

2 papers
EUR-Lex-Sum: A Multi- and Cross-lingual Dataset for Long-form Summarization in the Legal Domain (2022.emnlp-main)

Copied to clipboard

Challenge: Existing summarization datasets focus on overly exposed domains and are primarily monolingual with few multilingual datasets.
Approach: They propose a new summarization dataset based on manually curated document summaries from the European Union law platform EUR-Lex.
Outcome: The proposed dataset is based on document summaries of legal acts from the European Union law platform (EUR-Lex).
LexDrafter: Terminology Drafting for Legislative Documents Using Retrieval Augmented Generation (2024.lrec-main)

Copied to clipboard

Challenge: With the increase in legislative documents, the number of new terms and their definitions is increasing as well.
Approach: They propose a framework that helps in drafting Definitions articles for legislative documents using retrieval augmented generation and existing term definitions present in different legislative documents.
Outcome: The proposed framework can be used to draft Definitions articles for legislative documents using retrieval augmented generation and existing term definitions present in different legislative documents.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations