Bew: Towards Answering Business-Entity-Related Web Questions

12/10/2020
by   Qingqing Cao, et al.
0

We present BewQA, a system specifically designed to answer a class of questions that we call Bew questions. Bew questions are related to businesses/services such as restaurants, hotels, and movie theaters; for example, "Until what time is happy hour?". These questions are challenging to answer because the answers are found in open-domain Web, are present in short sentences without surrounding context, and are dynamic since the webpage information can be updated frequently. Under these conditions, existing QA systems perform poorly. We present a practical approach, called BewQA, that can answer Bew queries by mining a template of the business-related webpages and using the template to guide the search. We show how we can extract the template automatically by leveraging aggregator websites that aggregate information about business entities in a domain (e.g., restaurants). We answer a given question by identifying the section from the extracted template that is most likely to contain the answer. By doing so we can extract the answers even when the answer span does not have sufficient context. Importantly, BewQA does not require any training. We crowdsource a new dataset of 1066 Bew questions and ground-truth answers in the restaurant domain. Compared to state-of-the-art QA models, BewQA has a 27 percent point improvement in F1 score. Compared to a commercial search engine, BewQA answered correctly 29

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/14/2017

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering

A popular recent approach to answering open-domain questions is to first...
research
07/27/2021

Template-based Chatbot for Agriculture Related FAQs

Agriculture is the fundamental industry of the society, which is the bas...
research
04/18/2021

GooAQ: Open Question Answering with Diverse Answer Types

While day-to-day questions come with a variety of answer types, the curr...
research
09/03/2020

orgFAQ: A New Dataset and Analysis on Organizational FAQs and User Questions

Frequently Asked Questions (FAQ) webpages are created by organizations f...
research
11/02/2017

The Achievement of Higher Flexibility in Multiple Choice-based Tests Using Image Classification Techniques

In spite of the high accuracy of the existing optical mark reading (OMR)...
research
09/13/2021

SituatedQA: Incorporating Extra-Linguistic Contexts into QA

Answers to the same question may change depending on the extra-linguisti...
research
06/12/2018

How effective is your blinding?

This report answers queries about extending the blinding index approach ...

Please sign up or login with your details

Forgot password? Click here to reset