How much should you ask? On the question structure in QA systems

09/11/2018
by   Dominika Basaj, et al.
0

Datasets that boosted state-of-the-art solutions for Question Answering (QA) systems prove that it is possible to ask questions in natural language manner. However, users are still used to query-like systems where they type in keywords to search for answer. In this study we validate which parts of questions are essential for obtaining valid answer. In order to conclude that, we take advantage of LIME - a framework that explains prediction by local approximation. We find that grammar and natural language is disregarded by QA. State-of-the-art model can answer properly even if 'asked' only with a few words with high coefficients calculated with LIME. According to our knowledge, it is the first time that QA model is being explained by LIME.

READ FULL TEXT

page 1

page 2

page 3

research
11/08/2019

Comparison of Machine Learning Based Methods Used in Bengali Question Classification

This paper work demonstrates phases of assembling a question answer type...
research
11/07/2015

Stacked Attention Networks for Image Question Answering

This paper presents stacked attention networks (SANs) that learn to answ...
research
05/15/2023

MeeQA: Natural Questions in Meeting Transcripts

We present MeeQA, a dataset for natural-language question answering over...
research
05/25/2022

Asking the Right Questions in Low Resource Template Extraction

Information Extraction (IE) researchers are mapping tasks to Question An...
research
05/31/2020

Efficient Deployment ofConversational Natural Language Interfaces over Databases

Many users communicate with chatbots and AI assistants in order to help ...
research
05/30/2023

KEYword based Sampling (KEYS) for Large Language Models

Question answering (Q/A) can be formulated as a generative task (Mitra, ...
research
07/30/2023

Around the GLOBE: Numerical Aggregation Question-Answering on Heterogeneous Genealogical Knowledge Graphs with Deep Neural Networks

One of the key AI tools for textual corpora exploration is natural langu...

Please sign up or login with your details

Forgot password? Click here to reset