CLJun 14, 2019

Microsoft AI Challenge India 2018: Learning to Rank Passages for Web Question Answering with Deep Attention Networks

arXiv:1906.06056v11 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the challenge of improving passage retrieval for web-based question answering systems, representing an incremental advancement in the field.

The paper tackled the problem of ranking passages for web question answering by developing a system using biLSTM with co-attention and self-attention mechanisms, achieving a Mean Reciprocal Rank (MRR) of 0.67 on the eval-1 dataset.

This paper describes our system for The Microsoft AI Challenge India 2018: Ranking Passages for Web Question Answering. The system uses the biLSTM network with co-attention mechanism between query and passage representations. Additionally, we use self attention on embeddings to increase the lexical coverage by allowing the system to take union over different embeddings. We also incorporate hand-crafted features to improve the system performance. Our system achieved a Mean Reciprocal Rank (MRR) of 0.67 on eval-1 dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes