Artificial fine-tuning tasks for yes/no question answering

Abstract

Current research in yes/no question answering (QA) focuses on transfer learning techniques and transformer-based models. Models trained on large corpora are fine-tuned on tasks similar to yes/no QA, and then the captured knowledge is transferred for solving the yes/no QA task. Most previous studies use existing similar tasks, such as natural language inference or extractive QA, for the fine-tuning step. This paper follows a different perspective, hypothesizing that an artificial yes/no task can transfer useful knowledge for improving the performance of yes/no QA. We introduce three such tasks for this purpose, by adapting three corresponding existing tasks: candidate answer validation, sentiment classification, and lexical simplification. Furthermore, we experimented with three different variations of the BERT model (BERT base, RoBERTa, and ALBERT). The results show that our hypothesis holds true for all artificial tasks, despite the small size of the corresponding datasets that are used for the fine-tuning process, the differences between these tasks, the decisions that we made to adapt the original ones, and the tasks’ simplicity. This gives an alternative perspective on how to deal with the yes/no QA problem, that is more creative, and at the same time more flexible, as it can exploit multiple other existing tasks and corresponding datasets to improve yes/no QA models.

Deep Learning Based Question Answering System (Survey)

“…By changing the model's weights to more accurately suit the particular job, fine-tuning can also aid in enhancing the system's accuracy [62]. By changing the model's weights to better suit the particular job, fine-tuning can also aid in enhancing the system's accuracy [63]. A further drawback is that only small modifications to the language model, primarily to its top layers, may be made during fine-tuning [63].…”

“…By changing the model's weights to better suit the particular job, fine-tuning can also aid in enhancing the system's accuracy [63]. A further drawback is that only small modifications to the language model, primarily to its top layers, may be made during fine-tuning [63]. Furthermore, if the inquiry contains grammar errors, the machine might not locate a match [63].…”

“…A further drawback is that only small modifications to the language model, primarily to its top layers, may be made during fine-tuning [63]. Furthermore, if the inquiry contains grammar errors, the machine might not locate a match [63]. Nevertheless, optimizing a transformer model for QA is a well-liked NLP technique and can result in a high-performing QA model [61,64].…”