A Free Format Legal Question Answering System
2021-11-01EMNLP (NLLP) 2021Unverified0· sign in to hype
Soha Khazaeli, Janardhana Punuru, Chad Morris, Sanjay Sharma, Bert Staub, Michael Cole, Sunny Chiu-Webster, Dhruv Sakalley
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
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.