Joint Learning of Sentence Embeddings for Relevance and Entailment
This work addresses the challenge of integrating evidence for entailment in IR contexts, which is incremental as it builds on existing neural methods for sentence embeddings.
The paper tackles the problem of Recognizing Textual Entailment in Information Retrieval by jointly learning sentence embeddings for relevance and entailment to answer binary natural language questions, achieving improvements such as advancing the state-of-the-art on the MCTest dataset.
We consider the problem of Recognizing Textual Entailment within an Information Retrieval context, where we must simultaneously determine the relevancy as well as degree of entailment for individual pieces of evidence to determine a yes/no answer to a binary natural language question. We compare several variants of neural networks for sentence embeddings in a setting of decision-making based on evidence of varying relevance. We propose a basic model to integrate evidence for entailment, show that joint training of the sentence embeddings to model relevance and entailment is feasible even with no explicit per-evidence supervision, and show the importance of evaluating strong baselines. We also demonstrate the benefit of carrying over text comprehension model trained on an unrelated task for our small datasets. Our research is motivated primarily by a new open dataset we introduce, consisting of binary questions and news-based evidence snippets. We also apply the proposed relevance-entailment model on a similar task of ranking multiple-choice test answers, evaluating it on a preliminary dataset of school test questions as well as the standard MCTest dataset, where we improve the neural model state-of-art.