Details
| Original language | English |
|---|---|
| Title of host publication | EMNLP-IJCNLP 2019, Graph-Based Methods for Natural Language Processing |
| Subtitle of host publication | Proceedings of the Thirteenth Workshop, November 4, 2019Hong Kong |
| Place of Publication | Hong Kong |
| Pages | 90-100 |
| Number of pages | 11 |
| ISBN (electronic) | 9781950737864 |
| Publication status | Published - Nov 2019 |
| Externally published | Yes |
| Event | 13th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2019, in conjunction with the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 - Hong Kong, Hong Kong Duration: 4 Nov 2019 → 4 Nov 2019 |
Abstract
The TextGraphs 2019 Shared Task on Multi- Hop Inference for Explanation Regeneration (MIER-19) tackles explanation generation for answers to elementary science questions. It builds on the AI2 Reasoning Challenge 2018 (ARC-18) which was organized as an advanced question answering task on a dataset of elementary science questions. The ARC- 18 questions were shown to be hard to answer with systems focusing on surface-level cues alone, instead requiring far more powerful knowledge and reasoning. To address MIER-19, we adopt a hybrid pipelined architecture comprising a featurerich learning-to-rank (LTR) machine learning model, followed by a rule-based system for reranking the LTR model predictions. Our system was ranked fourth in the official evaluation, scoring close to the second and third ranked teams, achieving 39.4% MAP.
ASJC Scopus subject areas
- Computer Science(all)
- Computational Theory and Mathematics
- Computer Science(all)
- Computer Science Applications
- Computer Science(all)
- Information Systems
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
EMNLP-IJCNLP 2019, Graph-Based Methods for Natural Language Processing: Proceedings of the Thirteenth Workshop, November 4, 2019Hong Kong. Hong Kong, 2019. p. 90-100.
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Team SVMrank
T2 - 13th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2019, in conjunction with the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
AU - D'Souza, Jennifer
AU - Mulang, Isaiah Onando
AU - Auer, Sören
PY - 2019/11
Y1 - 2019/11
N2 - The TextGraphs 2019 Shared Task on Multi- Hop Inference for Explanation Regeneration (MIER-19) tackles explanation generation for answers to elementary science questions. It builds on the AI2 Reasoning Challenge 2018 (ARC-18) which was organized as an advanced question answering task on a dataset of elementary science questions. The ARC- 18 questions were shown to be hard to answer with systems focusing on surface-level cues alone, instead requiring far more powerful knowledge and reasoning. To address MIER-19, we adopt a hybrid pipelined architecture comprising a featurerich learning-to-rank (LTR) machine learning model, followed by a rule-based system for reranking the LTR model predictions. Our system was ranked fourth in the official evaluation, scoring close to the second and third ranked teams, achieving 39.4% MAP.
AB - The TextGraphs 2019 Shared Task on Multi- Hop Inference for Explanation Regeneration (MIER-19) tackles explanation generation for answers to elementary science questions. It builds on the AI2 Reasoning Challenge 2018 (ARC-18) which was organized as an advanced question answering task on a dataset of elementary science questions. The ARC- 18 questions were shown to be hard to answer with systems focusing on surface-level cues alone, instead requiring far more powerful knowledge and reasoning. To address MIER-19, we adopt a hybrid pipelined architecture comprising a featurerich learning-to-rank (LTR) machine learning model, followed by a rule-based system for reranking the LTR model predictions. Our system was ranked fourth in the official evaluation, scoring close to the second and third ranked teams, achieving 39.4% MAP.
UR - http://www.scopus.com/inward/record.url?scp=85085038180&partnerID=8YFLogxK
U2 - 10.18653/v1/d19-5312
DO - 10.18653/v1/d19-5312
M3 - Conference contribution
AN - SCOPUS:85085038180
SP - 90
EP - 100
BT - EMNLP-IJCNLP 2019, Graph-Based Methods for Natural Language Processing
CY - Hong Kong
Y2 - 4 November 2019 through 4 November 2019
ER -