CAESAR: Context Awareness Enabled Summary-Attentive Reader

TL;DR

This paper introduces CAESAR, a summary-attentive reader model that emulates human reading, incorporating a dictionary-based approach for OOV words, achieving near-human performance on the SQuAD dataset.

Contribution

It presents a novel model combining summary-attention with dictionary-based OOV handling, improving machine comprehension performance.

Findings

Achieved results close to human performance on SQuAD.

Enhanced models with summary-attention and OOV handling.

Demonstrated effectiveness with Match LSTM and Coattention models.

Abstract

Comprehending meaning from natural language is a primary objective of Natural Language Processing (NLP), and text comprehension is the cornerstone for achieving this objective upon which all other problems like chat bots, language translation and others can be achieved. We report a Summary-Attentive Reader we designed to better emulate the human reading process, along with a dictiontary-based solution regarding out-of-vocabulary (OOV) words in the data, to generate answer based on machine comprehension of reading passages and question from the SQuAD benchmark. Our implementation of these features with two popular models (Match LSTM and Dynamic Coattention) was able to reach close to matching the results obtained from humans.