BioAMA: Towards an End to End BioMedical Question Answering System

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 (Balikas et al., 2015). We focus on a wide variety of question types including factoid, list based, summary and yes/no type questions that generate both exact and wellformed 'ideal' answers. For summarytype questions, we combine effective IRbased 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 Natural Language Inference (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 and unsupervised techniques.

MSIT_SRIB at MEDIQA 2019: Knowledge Directed Multi-task Framework for Natural Language Inference in Clinical Domain.

“…For external knowledge integration, the required medical concepts in SNOMED-CT were identified in the premise and hypothesis sentences using MetaMap by Aronson and Lang 1 https://github.com/chantera/bicnn-mi 2 https://github.com/namisan/mt-dnn (2010). We used glove and PubMed word embeddings and used DNN (Sharma et al, 2018) for nonlinear projection. In all experiments we report the average result (on the dev set) of 5 different runs, with the same hyperparameters and different random seeds.…”

“…However, these embeddings are not specific to the clinical domain and may result in many tokens being mapped to the embedding of the unknown (UNK) token. To alleviate this issue, we learned a non-linear transformation (Sharma et al, 2018) that maps words from PubMed (Pyysalo et al, 2013) to GloVe subspace. We train the DNN using the common words in both the embeddings.…”

“…We use publicly available implementations for Bi-CNN-Mi 1 and MT-DNN 2 . For external knowledge integration, the required medical concepts in SNOMED-CT were identified in the premise and hypothesis sentences using MetaMap by Aronson and Lang (Sharma et al, 2018) for nonlinear projection. In all experiments we report the average result (on the dev set) of 5 different runs, with the same hyperparameters and different random seeds.…”

Text Mining In Healthcare

“…AskHERMES uses structural clustering to identify multiple answer topics, LCS-based ranking to identify best answer [28]. BioAMA: "Biomedical Ask Me Anything" focus on summary type questions.…”

A Neural Named Entity Recognition and Multi-Type Normalization Tool for Biomedical Text Mining

“…Fast and precise text mining tools can reduce the amount of effort and time it takes researchers to find and extract useful information from the vast amount of biomedical literature. Researchers have used named entity recognition (NER) and named entity normalization (NEN) models to develop effective biomedical text mining tools for information retrieval [1], question answering [2], relation extraction [3], and so on.…”