Salient context-based semantic matching for information retrieval

Neural networks provide new possibilities to uncover semantic relationships between words by involving contextual information, and further a way to learn the matching pattern from document-query word contextual similarity matrix, which has brought promising results in IR. However, most neural IR methods rely on the conventional word-word matching framework for finding a relevant document for a query. Its effect is limited due to the wide gap between the lengths of query and document. To address this problem, we propose a salient context-based semantic matching (SCSM) method to build a bridge between query and document. Our method locates the most relevant context in the document using a shifting window with adapted length and then calculates the relevance score within it as the representation of the document. We define the notion of contextual salience and the corresponding measures to calculate the relevance of a context to a given query, in which the interaction between the query and the context is modeled by semantic similarity. Experiments on various collections from TREC show the effectiveness of our model as compared to the state-of-the-art methods.