The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dalam makalah ini, kami mencadangkan model kebarangkalian baharu pelabelan peranan semantik, yang menggunakan rangka set predikat sebagai pengetahuan linguistik eksplisit untuk menyediakan maklumat global tentang struktur hujah-predikat yang pengelas tempatan tidak dapat menangkap. Model yang dicadangkan terdiri daripada tiga sub-model: model penjanaan urutan peranan, model penjanaan set rangka dan model padanan. Model penjanaan jujukan peranan menjana calon jujukan peranan semantik bagi predikat tertentu dengan menggunakan pendekatan klasifikasi tempatan, yang merupakan pendekatan yang digunakan secara meluas dalam penyelidikan terdahulu. Model penjanaan set rangka menganggarkan kebarangkalian setiap set rangka yang boleh diambil oleh predikat. Model padanan direka bentuk untuk mengukur tahap padanan antara urutan peranan yang dijana dan set rangka dengan menggunakan beberapa ciri. Ciri-ciri ini dibangunkan untuk mewakili maklumat struktur predikat-hujah yang diterangkan dalam set rangka. Dalam eksperimen, model kami menunjukkan bahawa penggunaan pengetahuan tentang struktur predikat-hujah adalah berkesan untuk memilih urutan peranan semantik yang lebih sesuai.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Joo-Young LEE, Young-In SONG, Hae-Chang RIM, Kyoung-Soo HAN, "Incorporating Frame Information to Semantic Role Labeling" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 1, pp. 201-204, January 2010, doi: 10.1587/transinf.E93.D.201.
Abstract: In this paper, we suggest a new probabilistic model of semantic role labeling, which uses the frameset of the predicate as explicit linguistic knowledge for providing global information on the predicate-argument structure that local classifier is unable to catch. The proposed model consists of three sub-models: role sequence generation model, frameset generation model, and matching model. The role sequence generation model generates the semantic role sequence candidates of a given predicate by using the local classification approach, which is a widely used approach in previous research. The frameset generation model estimates the probability of each frameset that the predicate can take. The matching model is designed to measure the degree of the matching between the generated role sequence and the frameset by using several features. These features are developed to represent the predicate-argument structure information described in the frameset. In the experiments, our model shows that the use of knowledge about the predicate-argument structure is effective for selecting a more appropriate semantic role sequence.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.201/_p
Salinan
@ARTICLE{e93-d_1_201,
author={Joo-Young LEE, Young-In SONG, Hae-Chang RIM, Kyoung-Soo HAN, },
journal={IEICE TRANSACTIONS on Information},
title={Incorporating Frame Information to Semantic Role Labeling},
year={2010},
volume={E93-D},
number={1},
pages={201-204},
abstract={In this paper, we suggest a new probabilistic model of semantic role labeling, which uses the frameset of the predicate as explicit linguistic knowledge for providing global information on the predicate-argument structure that local classifier is unable to catch. The proposed model consists of three sub-models: role sequence generation model, frameset generation model, and matching model. The role sequence generation model generates the semantic role sequence candidates of a given predicate by using the local classification approach, which is a widely used approach in previous research. The frameset generation model estimates the probability of each frameset that the predicate can take. The matching model is designed to measure the degree of the matching between the generated role sequence and the frameset by using several features. These features are developed to represent the predicate-argument structure information described in the frameset. In the experiments, our model shows that the use of knowledge about the predicate-argument structure is effective for selecting a more appropriate semantic role sequence.},
keywords={},
doi={10.1587/transinf.E93.D.201},
ISSN={1745-1361},
month={January},}
Salinan
TY - JOUR
TI - Incorporating Frame Information to Semantic Role Labeling
T2 - IEICE TRANSACTIONS on Information
SP - 201
EP - 204
AU - Joo-Young LEE
AU - Young-In SONG
AU - Hae-Chang RIM
AU - Kyoung-Soo HAN
PY - 2010
DO - 10.1587/transinf.E93.D.201
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2010
AB - In this paper, we suggest a new probabilistic model of semantic role labeling, which uses the frameset of the predicate as explicit linguistic knowledge for providing global information on the predicate-argument structure that local classifier is unable to catch. The proposed model consists of three sub-models: role sequence generation model, frameset generation model, and matching model. The role sequence generation model generates the semantic role sequence candidates of a given predicate by using the local classification approach, which is a widely used approach in previous research. The frameset generation model estimates the probability of each frameset that the predicate can take. The matching model is designed to measure the degree of the matching between the generated role sequence and the frameset by using several features. These features are developed to represent the predicate-argument structure information described in the frameset. In the experiments, our model shows that the use of knowledge about the predicate-argument structure is effective for selecting a more appropriate semantic role sequence.
ER -