Combined Approach for Answer Identification with Small Sized Reading Comprehension Datasets

In the realm of natural language understanding, machine reading and comprehension have emerged as significant areas of interest, requiring machines to extract pertinent information from textual data and understand it. This study proposes a novel method for answer identification in a multiple-choice question answering setup, utilizing science textbook and narrative text data. The proposed methodology integrates lexical semantic features at the word level and sentence-level equivalence. Initially, the strategy exploits lexical features, particularly word overlap, critical for answer identification. It extracts features such as noun phrases, verb phrases, and prepositions, accounting for their grammatical relationships. These features are then enhanced by assessing semantic similarity via a transformer model. Subsequently, answer identification is executed by mapping between answer option sentences and paragraph sentences on a one-to-one basis. The accuracy of correct answer identification was evaluated using both a feature-based approach and a BERT-based approach. Results indicated an accuracy of 66.4% and 57.5% for the science and narrative datasets, respectively, employing the combined approach. The performance evaluation of the proposed method was undertaken with a fine-tuned pre-trained language model. The evaluation analysis revealed certain challenges with the proposed methodology, outlining avenues for future research.