DeepAI AI Chat
Log In Sign Up

Reasoning in Vector Space: An Exploratory Study of Question Answering

11/19/2015
by   Moontae Lee, et al.
Microsoft
Johns Hopkins University
cornell university
0

Question answering tasks have shown remarkable progress with distributed vector representation. In this paper, we investigate the recently proposed Facebook bAbI tasks which consist of twenty different categories of questions that require complex reasoning. Because the previous work on bAbI are all end-to-end models, errors could come from either an imperfect understanding of semantics or in certain steps of the reasoning. For clearer analysis, we propose two vector space models inspired by Tensor Product Representation (TPR) to perform knowledge encoding and logical reasoning based on common-sense inference. They together achieve near-perfect accuracy on all categories including positional reasoning and path finding that have proved difficult for most of the previous approaches. We hypothesize that the difficulties in these categories are due to the multi-relations in contrast to uni-relational characteristic of other categories. Our exploration sheds light on designing more sophisticated dataset and moving one step toward integrating transparent and interpretable formalism of TPR into existing learning paradigms.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/30/2018

Compositional Attention Networks for Interpretability in Natural Language Question Answering

MAC Net is a compositional attention network designed for Visual Questio...
08/30/2022

Faithful Reasoning Using Large Language Models

Although contemporary large language models (LMs) demonstrate impressive...
04/30/2020

Dynamic Language Binding in Relational Visual Reasoning

We present Language-binding Object Graph Network, the first neural reaso...
04/28/2022

Inferring Implicit Relations with Language Models

A prominent challenge for modern language understanding systems is the a...
04/15/2021

TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph

Multi-hop Question Answering (QA) is a challenging task because it requi...
09/30/2020

TaxiNLI: Taking a Ride up the NLU Hill

Pre-trained Transformer-based neural architectures have consistently ach...
02/23/2018

Semantic Vector Spaces for Broadening Consideration of Consequences

Reasoning systems with too simple a model of the world and human intent ...