Vector relation acquisition and scene knowledge for solving arithmetic word problems
This paper presents a vector relation-centric algorithm for solving arithmetic word problems (AWPs), which uses vector relation acquisition and scene knowledge to ensure the performances of problem understanding and symbolic solver correspondingly. The vector relation acquisition procedure builds on...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157823002276 |
| _version_ | 1797663864929648640 |
|---|---|
| author | Xiaopan Lyu Xinguo Yu Rao Peng |
| author_facet | Xiaopan Lyu Xinguo Yu Rao Peng |
| author_sort | Xiaopan Lyu |
| collection | DOAJ |
| description | This paper presents a vector relation-centric algorithm for solving arithmetic word problems (AWPs), which uses vector relation acquisition and scene knowledge to ensure the performances of problem understanding and symbolic solver correspondingly. The vector relation acquisition procedure builds on the synergy of the vector syntax-semantics method and the deep neural miner. Compared with the syntax-semantics method, the vector syntax-semantics method decreases not only the number of models but also semantic ambiguities and computational costs. For the scene knowledge, this paper proposes a scene-aware symbolic solver which infers relations obeying scene rules to decrease the occurrences of unwanted operations. Experimental results show that the proposed algorithm is superior to the high-performance baseline algorithm in both accuracy and computational cost. In accuracy, the proposed algorithm increased the accuracy by 3.9% on the sum of the three scene subsets due to the use of the scene knowledge and vector computing; as a result, it increased the accuracy by 0.5% on the sum of six authoritative datasets. In computational cost, the proposed algorithm decreased the computing cost by more than 50%. Thus, this paper makes a significant contribution to developing instruments for solving AWPs. |
| first_indexed | 2024-03-11T19:20:57Z |
| format | Article |
| id | doaj.art-501a7afea5c04e31b41c5b4e4b0690bc |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-11T19:20:57Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-501a7afea5c04e31b41c5b4e4b0690bc2023-10-07T04:34:02ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-09-01358101673Vector relation acquisition and scene knowledge for solving arithmetic word problemsXiaopan Lyu0Xinguo Yu1Rao Peng2Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaCorresponding author.; Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, ChinaThis paper presents a vector relation-centric algorithm for solving arithmetic word problems (AWPs), which uses vector relation acquisition and scene knowledge to ensure the performances of problem understanding and symbolic solver correspondingly. The vector relation acquisition procedure builds on the synergy of the vector syntax-semantics method and the deep neural miner. Compared with the syntax-semantics method, the vector syntax-semantics method decreases not only the number of models but also semantic ambiguities and computational costs. For the scene knowledge, this paper proposes a scene-aware symbolic solver which infers relations obeying scene rules to decrease the occurrences of unwanted operations. Experimental results show that the proposed algorithm is superior to the high-performance baseline algorithm in both accuracy and computational cost. In accuracy, the proposed algorithm increased the accuracy by 3.9% on the sum of the three scene subsets due to the use of the scene knowledge and vector computing; as a result, it increased the accuracy by 0.5% on the sum of six authoritative datasets. In computational cost, the proposed algorithm decreased the computing cost by more than 50%. Thus, this paper makes a significant contribution to developing instruments for solving AWPs.http://www.sciencedirect.com/science/article/pii/S1319157823002276Problem-solvingRelation-centricVector computingScene knowledgeVector syntax-semantics model |
| spellingShingle | Xiaopan Lyu Xinguo Yu Rao Peng Vector relation acquisition and scene knowledge for solving arithmetic word problems Journal of King Saud University: Computer and Information Sciences Problem-solving Relation-centric Vector computing Scene knowledge Vector syntax-semantics model |
| title | Vector relation acquisition and scene knowledge for solving arithmetic word problems |
| title_full | Vector relation acquisition and scene knowledge for solving arithmetic word problems |
| title_fullStr | Vector relation acquisition and scene knowledge for solving arithmetic word problems |
| title_full_unstemmed | Vector relation acquisition and scene knowledge for solving arithmetic word problems |
| title_short | Vector relation acquisition and scene knowledge for solving arithmetic word problems |
| title_sort | vector relation acquisition and scene knowledge for solving arithmetic word problems |
| topic | Problem-solving Relation-centric Vector computing Scene knowledge Vector syntax-semantics model |
| url | http://www.sciencedirect.com/science/article/pii/S1319157823002276 |
| work_keys_str_mv | AT xiaopanlyu vectorrelationacquisitionandsceneknowledgeforsolvingarithmeticwordproblems AT xinguoyu vectorrelationacquisitionandsceneknowledgeforsolvingarithmeticwordproblems AT raopeng vectorrelationacquisitionandsceneknowledgeforsolvingarithmeticwordproblems |