DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval
This work addresses information retrieval for users needing more accurate document ranking by improving neural models, though it appears incremental as it builds on classical visualization methods.
The paper tackled the problem of neural information retrieval by proposing DeepTileBars, a model that handles query-to-document matching at subtopic and higher levels to better capture document discourse structure, resulting in outperforming state-of-the-art models on benchmark datasets like TREC 2010-2012 Web Tracks and LETOR 4.0.
Most neural Information Retrieval (Neu-IR) models derive query-to-document ranking scores based on term-level matching. Inspired by TileBars, a classical term distribution visualization method, in this paper, we propose a novel Neu-IR model that handles query-to-document matching at the subtopic and higher levels. Our system first splits the documents into topical segments, "visualizes" the matchings between the query and the segments, and then feeds an interaction matrix into a Neu-IR model, DeepTileBars, to obtain the final ranking scores. DeepTileBars models the relevance signals occurring at different granularities in a document's topic hierarchy. It better captures the discourse structure of a document and thus the matching patterns. Although its design and implementation are light-weight, DeepTileBars outperforms other state-of-the-art Neu-IR models on benchmark datasets including the Text REtrieval Conference (TREC) 2010-2012 Web Tracks and LETOR 4.0.