Hyperbolic Representation Learning for Fast and Efficient Neural Question Answering release_jchysshc25acfjk4xgt62nw2gy

by Yi Tay, Luu Anh Tuan, Siu Cheung Hui

Released as a article .

2017  

Abstract

The dominant neural architectures in question answer retrieval are based on recurrent or convolutional encoders configured with complex word matching layers. Given that recent architectural innovations are mostly new word interaction layers or attention-based matching mechanisms, it seems to be a well-established fact that these components are mandatory for good performance. Unfortunately, the memory and computation cost incurred by these complex mechanisms are undesirable for practical applications. As such, this paper tackles the question of whether it is possible to achieve competitive performance with simple neural architectures. We propose a simple but novel deep learning architecture for fast and efficient question-answer ranking and retrieval. More specifically, our proposed model, HyperQA, is a parameter efficient neural network that outperforms other parameter intensive models such as Attentive Pooling BiLSTMs and Multi-Perspective CNNs on multiple QA benchmarks. The novelty behind HyperQA is a pairwise ranking objective that models the relationship between question and answer embeddings in Hyperbolic space instead of Euclidean space. This empowers our model with a self-organizing ability and enables automatic discovery of latent hierarchies while learning embeddings of questions and answers. Our model requires no feature engineering, no similarity matrix matching, no complicated attention mechanisms nor over-parameterized layers and yet outperforms and remains competitive to many models that have these functionalities on multiple benchmarks.
In text/plain format

Archived Files and Locations

application/pdf  1.3 MB
file_smlz27zilvbrvlxj6jyhk5qvyq
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2017-07-25
Version   v1
Language   en ?
arXiv  1707.07847v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: fd721ae9-466e-4634-9237-7932e6952d1c
API URL: JSON