Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Neural Information Processing |
| Untertitel | 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part VI |
| Herausgeber/-innen | Mohammad Tanveer, Sonali Agarwal, Seiichi Ozawa, Asif Ekbal, Adam Jatowt |
| Erscheinungsort | Singapore |
| Herausgeber (Verlag) | Springer Science and Business Media Deutschland GmbH |
| Seiten | 276-288 |
| Seitenumfang | 13 |
| ISBN (elektronisch) | 978-981-99-1645-0 |
| ISBN (Print) | 9789819916443 |
| Publikationsstatus | Veröffentlicht - 2023 |
| Veranstaltung | 29th International Conference on Neural Information Processing, ICONIP 2022 - Virtual, Online Dauer: 22 Nov. 2022 → 26 Nov. 2022 |
Publikationsreihe
| Name | Communications in Computer and Information Science |
|---|---|
| Band | 1793 CCIS |
| ISSN (Print) | 1865-0929 |
| ISSN (elektronisch) | 1865-0937 |
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.
ASJC Scopus Sachgebiete
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Neural Information Processing : 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, Proceedings, Part VI. Hrsg. / Mohammad Tanveer; Sonali Agarwal; Seiichi Ozawa; Asif Ekbal; Adam Jatowt. Singapore: Springer Science and Business Media Deutschland GmbH, 2023. S. 276-288 (Communications in Computer and Information Science; Band 1793 CCIS).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Span Detection for Kinematics Word Problems
AU - Abraham, Savitha Sam
AU - P, Deepak
AU - Sundaram, Sowmya S.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85161648745&partnerID=8YFLogxK
U2 - 10.1007/978-981-99-1645-0_23
DO - 10.1007/978-981-99-1645-0_23
M3 - Conference contribution
AN - SCOPUS:85161648745
SN - 9789819916443
T3 - Communications in Computer and Information Science
SP - 276
EP - 288
BT - Neural Information Processing
A2 - Tanveer, Mohammad
A2 - Agarwal, Sonali
A2 - Ozawa, Seiichi
A2 - Ekbal, Asif
A2 - Jatowt, Adam
PB - Springer Science and Business Media Deutschland GmbH
CY - Singapore
T2 - 29th International Conference on Neural Information Processing, ICONIP 2022
Y2 - 22 November 2022 through 26 November 2022
ER -