Science Question Answering using Instructional Materials

02/13/2016
by   Mrinmaya Sachan, et al.
0

We provide a solution for elementary science test using instructional materials. We posit that there is a hidden structure that explains the correctness of an answer given the question and instructional materials and present a unified max-margin framework that learns to find these hidden structures (given a corpus of question-answer pairs and instructional materials), and uses what it learns to answer novel elementary science questions. Our evaluation shows that our framework outperforms several strong baselines.

READ FULL TEXT
research
02/08/2018

WorldTree: A Corpus of Explanation Graphs for Elementary Science Questions supporting Multi-Hop Inference

Developing methods of automated inference that are able to provide users...
research
11/26/2018

CLEAR: A Dataset for Compositional Language and Elementary Acoustic Reasoning

We introduce the task of acoustic question answering (AQA) in the area o...
research
08/17/2023

MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models

Information extraction and textual comprehension from materials literatu...
research
09/15/2018

Answering Science Exam Questions Using Query Rewriting with Background Knowledge

Open-domain question answering (QA) is an important problem in AI and NL...
research
06/05/2017

A Joint Model for Question Answering and Question Generation

We propose a generative machine comprehension model that learns jointly ...
research
07/10/2015

Markov Logic Networks for Natural Language Question Answering

Our goal is to answer elementary-level science questions using knowledge...
research
03/31/2020

Unification-based Reconstruction of Explanations for Science Questions

The paper presents a framework to reconstruct explanations for multiple ...

Please sign up or login with your details

Forgot password? Click here to reset