Multi-Label Question Classification for Factoid and List Type Questions in Biomedical Question Answering

Abstract

Biomedical experts and bio-curators are unable to quickly find short and precise information using typical search engines as the amount of biomedical literature is increasing exponentially. The research community is focusing on biomedical question answering (QA) systems so that anyone can find precise information nuggets from the massive amount of biomedical literature. Generally, the user queries fall under different categories such as factoid, list, yes/no, or summary. The existing state-of-the-art question answering systems deal with most of these question types. However, the research to improve the performance of individual question types is also on the rise. To improve QA system performance, question classification plays a vital role for factoid and list type questions as it allows the answer processing stage to narrow down the candidate answer space and assigns a higher rank to the correct answers. A single biomedical answer or entity may be associated with more than one biomedical category or semantic type, e.g., Coenzyme Q(10) is classified under two categories in Unified Medical Language System (UMLS): organic chemical and biologically active substance. This inherent characteristic of biomedical entities makes question classification in the biomedical domain a multi-label classification problem, where one question might expect answers belonging to more than one semantic type. To the best of our knowledge, several QA systems deal with question classification as a multi-class classification problem and only one state-of-the-art system-OAQA-deals with it as a multi-label classification problem. In this paper, we analyze the pipeline of the OAQA system for factoid and list type questions, emphasizing the multi-label question classification. We use an improved question classification dataset with the copy transformation technique to improve the performance of list type questions. Moreover, we introduce a binary transformation in the pipeline of factoid questions to increase its performance. Our modified methodology enhances the performance of both list and factoid type questions by a margin of 2% and 3% evaluated on standard F 1 and Mean Reciprocal Rank measures, respectively.

Question answering systems for health professionals at the point of care—a systematic review

“…However, several of the included studies arose from the BioASQ 5b 44 and 6b 45 shared tasks, which aimed to answer 4 types of questions (yes/no, factoids, list, and summary questions) and had 2 phases: information retrieval and exact answer production. Three studies arising from BioASQ 53 , 54 , 65 evaluated QA systems with a neural component, while 5 studies 52–54 , 57 , 65 evaluated QA systems that relied only on rule-based or classical ML components (eg, support vector machines). The neural components encoded questions and passages with a recurrent neural network (RNN) that were then used to create intermediate representations before answers were generated with additional layers.…”

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

“…• Question answering: BERN can recognize biomedical named entities in questions and passages in question answering tasks such as BioASQ Task B [63], [64], and help improve performance, especially on ''what'' and ''which'' questions by classifying whether a span in a passage is an entity or not.…”

List-wise learning to rank biomedical question-answer pairs with deep ranking recursive autoencoders

“…Due to some restrictions, however, only definitional questions can be solved. Another research project focused on retrieval of answers from biomedical literature through narrowing down the candidate answer space by question classification and distributing a higher rank to the correct answers [ 10 ]. This research still suffered from some troublesome problems [ 7 , 29 ], such as the need for a clear factoid and list type.…”

“…There have been several investigations concerning improvements of the query processing phase. For example, Cao et al [ 9 ], Wasim et al [ 10 ] and Abacha et al [ 11 ] have employed question classifying approaches, with semantic information obtained from the UMLS resources. However, some researchers have noted that these medical QA approaches have limitations in terms of the types and formats of questions that they can process [ 12 ].…”