Abstract
This paper describes the Nara Institute of Science and Technology's system for the entrance exam pilot task of CLEF 2013 QA4MRE. The core of the system is a similar to the system for the main task of CLEF 2013 QA4MRE. We use minimum error rate training (MERT) to train the weights of the model and also propose a novel method for MERT with the addition of a threshold that defines the certainty with which we must answer questions. The system received a score of 22% c@1.
| Original language | English |
|---|---|
| Journal | CEUR Workshop Proceedings |
| Volume | 1179 |
| Publication status | Published - 1 Jan 2013 |
| Event | 2013 Cross Language Evaluation Forum Conference, CLEF 2013 - Valencia, Spain Duration: 23 Sep 2013 → 26 Sep 2013 |
Keywords
- Discriminative learning
- Inter-sentence features
- Linear feature model
- Machine reading
- Minimum error rate training
- Question answering
Cite this
}
NAIST at the CLEF 2013 QA4MRE pilot task. / Arthur, Philip; Neubig, Graham; Sakti, Sakriani; Toda, Tomoki; Nakamura, Satoshi.
In: CEUR Workshop Proceedings, Vol. 1179, 01.01.2013.Research output: Contribution to journal › Conference article › Research › peer-review
TY - JOUR
T1 - NAIST at the CLEF 2013 QA4MRE pilot task
AU - Arthur, Philip
AU - Neubig, Graham
AU - Sakti, Sakriani
AU - Toda, Tomoki
AU - Nakamura, Satoshi
PY - 2013/1/1
Y1 - 2013/1/1
N2 - This paper describes the Nara Institute of Science and Technology's system for the entrance exam pilot task of CLEF 2013 QA4MRE. The core of the system is a similar to the system for the main task of CLEF 2013 QA4MRE. We use minimum error rate training (MERT) to train the weights of the model and also propose a novel method for MERT with the addition of a threshold that defines the certainty with which we must answer questions. The system received a score of 22% c@1.
AB - This paper describes the Nara Institute of Science and Technology's system for the entrance exam pilot task of CLEF 2013 QA4MRE. The core of the system is a similar to the system for the main task of CLEF 2013 QA4MRE. We use minimum error rate training (MERT) to train the weights of the model and also propose a novel method for MERT with the addition of a threshold that defines the certainty with which we must answer questions. The system received a score of 22% c@1.
KW - Discriminative learning
KW - Inter-sentence features
KW - Linear feature model
KW - Machine reading
KW - Minimum error rate training
KW - Question answering
UR - http://www.scopus.com/inward/record.url?scp=84922051490&partnerID=8YFLogxK
M3 - Conference article
VL - 1179
JO - CEUR Workshop Proceedings
JF - CEUR Workshop Proceedings
SN - 1613-0073
ER -