Question Answering from Unstructured Text by Retrieval and Comprehension

03/26/2017
by   Yusuke Watanabe, et al.
0

Open domain Question Answering (QA) systems must interact with external knowledge sources, such as web pages, to find relevant information. Information sources like Wikipedia, however, are not well structured and difficult to utilize in comparison with Knowledge Bases (KBs). In this work we present a two-step approach to question answering from unstructured text, consisting of a retrieval step and a comprehension step. For comprehension, we present an RNN based attention model with a novel mixture mechanism for selecting answers from either retrieved articles or a fixed vocabulary. For retrieval we introduce a hand-crafted model and a neural model for ranking relevant articles. We achieve state-of-the-art performance on W IKI M OVIES dataset, reducing the error by 40 introduced components.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/29/2020

Unified Open-Domain Question Answering with Structured and Unstructured Knowledge

We study open-domain question answering (ODQA) with structured, unstruct...
research
09/29/2017

A Neural Comprehensive Ranker (NCR) for Open-Domain Question Answering

This paper proposes a novel neural machine reading model for open-domain...
research
10/20/2020

Open Question Answering over Tables and Text

In open question answering (QA), the answer to a question is produced by...
research
03/31/2017

Reading Wikipedia to Answer Open-Domain Questions

This paper proposes to tackle open- domain question answering using Wiki...
research
06/07/2019

RankQA: Neural Question Answering with Answer Re-Ranking

The conventional paradigm in neural question answering (QA) for narrativ...
research
06/14/2019

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

This paper describes our system for The Microsoft AI Challenge India 201...
research
08/06/2023

Embedding-based Retrieval with LLM for Effective Agriculture Information Extracting from Unstructured Data

Pest identification is a crucial aspect of pest control in agriculture. ...

Please sign up or login with your details

Forgot password? Click here to reset