BioAMA: Towards an End to End BioMedical Question Answering System

Vasu Sharma, Nitish Kulkarni, Srividya Pranavi, Gabriel Bayomi, Eric Nyberg, Teruko Mitamura


Abstract
In this paper, we present a novel Biomedical Question Answering system, BioAMA: “Biomedical Ask Me Anything” on task 5b of the annual BioASQ challenge. In this work, we focus on a wide variety of question types including factoid, list based, summary and yes/no type questions that generate both exact and well-formed ‘ideal’ answers. For summary-type questions, we combine effective IR-based techniques for retrieval and diversification of relevant snippets for a question to create an end-to-end system which achieves a ROUGE-2 score of 0.72 and a ROUGE-SU4 score of 0.71 on ideal answer questions (7% improvement over the previous best model). Additionally, we propose a novel NLI-based framework to answer the yes/no questions. To train the NLI model, we also devise a transfer-learning technique by cross-domain projection of word embeddings. Finally, we present a two-stage approach to address the factoid and list type questions by first generating a candidate set using NER taggers and ranking them using both supervised or unsupervised techniques.
Anthology ID:
W18-2312
Volume:
Proceedings of the BioNLP 2018 workshop
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venues:
ACL | BioNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
109–117
Language:
URL:
https://aclanthology.org/W18-2312
DOI:
10.18653/v1/W18-2312
Bibkey:
Cite (ACL):
Vasu Sharma, Nitish Kulkarni, Srividya Pranavi, Gabriel Bayomi, Eric Nyberg, and Teruko Mitamura. 2018. BioAMA: Towards an End to End BioMedical Question Answering System. In Proceedings of the BioNLP 2018 workshop, pages 109–117, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
BioAMA: Towards an End to End BioMedical Question Answering System (Sharma et al., 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-2312.pdf
Data
SNLI