Span detection for kinematics word problems

Savitha Sam Abraham, Deepak P., Sowmya S. Sundaram

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Downloads (Pure)

Abstract

Solving kinematics word problems is a specialized task which is best addressed through bespoke logical reasoners. Reasoners, however, require structured input in the form of kinematics parameter values, and translating textual word problems to such structured inputs is a key step in enabling end-to-end automated word problem solving. Span detection for a kinematics parameter is the process of identifying the smallest span of text from a kinematics word problem that has the information to estimate the value of that parameter. A key aspect differentiating kinematics span detection from other span detection tasks is the presence of multiple inter-related parameters for which separate spans need to be identified. State-of-the-art span detection methods are not capable of leveraging the existence of a plurality of inter-dependent span identification tasks. We propose a novel neural architecture that is designed to exploit the inter-relatedness between the separate span detection tasks using a single joint model. This allows us to train the same network for span detection over multiple kinematics parameters, implicitly and automatically transferring knowledge across the kinematics parameters. We show that such a joint training delivers an improvement of accuracies over real-world datasets against state-of-the-art methods for span detection.

Original languageEnglish
Title of host publicationNeural Information Processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part VI: Proceedings
EditorsMohammad Tanveer, Sonali Agarwal, Seiichi Ozawa, Asif Ekbal, Adam Jatowt
PublisherSpringer
Pages276–288
ISBN (Electronic)9789819916450
ISBN (Print)9789819916443
Publication statusPublished - 14 Apr 2023
EventThe 29th International Conference on Neural Information Processing (ICONIP 2022) - IIT Indore, Indore, India
Duration: 22 Nov 202226 Nov 2022
https://iconip2022.apnns.org/index.php

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer
Volume1793
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceThe 29th International Conference on Neural Information Processing (ICONIP 2022)
Abbreviated titleICONIP 2022
Country/TerritoryIndia
CityIndore
Period22/11/202226/11/2022
Internet address

Fingerprint

Dive into the research topics of 'Span detection for kinematics word problems'. Together they form a unique fingerprint.

Cite this