Creative Commons source reading · Search and retrieval
A Free Format Legal Question Answering System
Soha Khazaeli; Janardhana Punuru; Chad Morris; Sanjay Sharma; Bert Staub; Michael Cole; Sunny Chiu-Webster; Dhruv Sakalley
Originally published in Proceedings of the Natural Legal Language Processing Workshop 2021 · 2021-11
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
We present an information retrieval-based question answer system to answer legal questions. The system is not limited to a predefined set of questions or patterns and uses both sparse vector search and embeddings for input to a BERT-based answer re-ranking system. A combination of general domain and legal domain data is used for training. This natural question answering system is in production and is used commercially.
Editorial reading guide
- Which legal corpus, jurisdiction and evaluation task does the article use?
- What evidence supports the reported performance, and where could the method fail in practice?
