Markov Logic Networks for Natural Language Question Answering

07/10/2015
by   Tushar Khot, et al.
0

Our goal is to answer elementary-level science questions using knowledge extracted automatically from science textbooks, expressed in a subset of first-order logic. Given the incomplete and noisy nature of these automatically extracted rules, Markov Logic Networks (MLNs) seem a natural model to use, but the exact way of leveraging MLNs is by no means obvious. We investigate three ways of applying MLNs to our task. In the first, we simply use the extracted science rules directly as MLN clauses. Unlike typical MLN applications, our domain has long and complex rules, leading to an unmanageable number of groundings. We exploit the structure present in hard constraints to improve tractability, but the formulation remains ineffective. In the second approach, we instead interpret science rules as describing prototypical entities, thus mapping rules directly to grounded MLN assertions, whose constants are then clustered using existing entity resolution methods. This drastically simplifies the network, but still suffers from brittleness. Finally, our third approach, called Praline, uses MLNs to align the lexical elements as well as define and control how inference should be performed in this task. Our experiments, demonstrating a 15% accuracy boost and a 10x reduction in runtime, suggest that the flexibility and different inference semantics of Praline are a better fit for the natural language question answering task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/08/2022

Integrating question answering and text-to-SQL in Portuguese

Deep learning transformers have drastically improved systems that automa...
research
01/11/2017

Question Analysis for Arabic Question Answering Systems

The first step of processing a question in Question Answering(QA) System...
research
04/20/2016

Question Answering via Integer Programming over Semi-Structured Knowledge

Answering science questions posed in natural language is an important AI...
research
02/26/2018

AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data

The task of answering natural language questions over RDF data has recei...
research
02/13/2016

Science Question Answering using Instructional Materials

We provide a solution for elementary science test using instructional ma...
research
02/22/2021

A Relational Tsetlin Machine with Applications to Natural Language Understanding

TMs are a pattern recognition approach that uses finite state machines f...
research
12/25/2020

LOREN: Logic Enhanced Neural Reasoning for Fact Verification

Given a natural language statement, how to verify whether it is supporte...

Please sign up or login with your details

Forgot password? Click here to reset