Summary of 1-800-shared-tasks at Regnlp: Lexical Reranking Of Semantic Retrieval (leser) For Regulatory Question Answering, by Jebish Purbey et al.
1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering
by Jebish Purbey, Drishti Sharma, Siddhant Gupta, Khawaja Murad, Siddartha Pullakhandam, Ram Mohan Rao Kadiyala
First submitted to arxiv on: 8 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Information Retrieval (cs.IR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents an entry for the COLING 2025 RegNLP RIRAG challenge, leveraging advanced information retrieval and answer generation techniques in regulatory domains. The approach combines embedding models like Stella, BGE, CDE, and Mpnet, with fine-tuning and reranking to retrieve relevant documents. The LeSeR method achieved competitive results for retrievals, with a recall@10 of 0.8201 and map@10 of 0.6655. This work highlights the potential of natural language processing techniques in regulatory applications, offering insights into their capabilities for implementing a retrieval-augmented generation system while identifying areas for future improvement. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using special computer programs to help find important information in laws and regulations. It’s like having a super-smart librarian who can quickly search through lots of documents to find the answers you need. The researchers used different techniques to see what worked best, and they came up with a new approach that did really well. This could be very helpful for people working with laws and regulations, and it shows how computers can make our lives easier. |
Keywords
» Artificial intelligence » Embedding » Fine tuning » Natural language processing » Recall » Retrieval augmented generation
