A Method for Extraction of Future Reference Sentences Based on Semantic Role Labeling

Yoko NAKAJIMA; Michal PTASZYNSKI; Hirotoshi HONMA; Fumito MASUI

doi:10.1587/transinf.2015EDP7115

A Method for Extraction of Future Reference Sentences Based on Semantic Role Labeling

Yoko NAKAJIMA, Michal PTASZYNSKI, Hirotoshi HONMA, Fumito MASUI

Full Text Views

0

Share
Cite this

Summary :

In everyday life, people use past events and their own knowledge in predicting probable unfolding of events. To obtain the necessary knowledge for such predictions, newspapers and the Internet provide a general source of information. Newspapers contain various expressions describing past events, but also current and future events, and opinions. In our research we focused on automatically obtaining sentences that make reference to the future. Such sentences can contain expressions that not only explicitly refer to future events, but could also refer to past or current events. For example, if people read a news article that states “In the near future, there will be an upward trend in the price of gasoline,” they may be likely to buy gasoline now. However, if the article says “The cost of gasoline has just risen 10 yen per liter,” people will not rush to buy gasoline, because they accept this as reality and may expect the cost to decrease in the future. In the following study we firstly investigate future reference sentences in newspapers and Web news. Next, we propose a method for automatic extraction of such sentences by using semantic role labels, without typical approaches (temporal expressions, etc.). In a series of experiments, we extract semantic role patterns from future reference sentences and examine the validity of the extracted patterns in classification of future reference sentences.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.2 pp.514-524

Publication Date: 2016/02/01

Publicized: 2015/11/18

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDP7115

Type of Manuscript: PAPER

Category: Natural Language Processing

Authors

Yoko NAKAJIMA
  Kitami Institute of Technology
Michal PTASZYNSKI
  Kitami Institute of Technology
Hirotoshi HONMA
  Kushiro College
Fumito MASUI
  Kitami Institute of Technology

Keyword

natural language processing, future reference expressions, future prediction, information extraction

Cite this

Copy

Yoko NAKAJIMA, Michal PTASZYNSKI, Hirotoshi HONMA, Fumito MASUI, "A Method for Extraction of Future Reference Sentences Based on Semantic Role Labeling" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 2, pp. 514-524, February 2016, doi: 10.1587/transinf.2015EDP7115.
Abstract: In everyday life, people use past events and their own knowledge in predicting probable unfolding of events. To obtain the necessary knowledge for such predictions, newspapers and the Internet provide a general source of information. Newspapers contain various expressions describing past events, but also current and future events, and opinions. In our research we focused on automatically obtaining sentences that make reference to the future. Such sentences can contain expressions that not only explicitly refer to future events, but could also refer to past or current events. For example, if people read a news article that states “In the near future, there will be an upward trend in the price of gasoline,” they may be likely to buy gasoline now. However, if the article says “The cost of gasoline has just risen 10 yen per liter,” people will not rush to buy gasoline, because they accept this as reality and may expect the cost to decrease in the future. In the following study we firstly investigate future reference sentences in newspapers and Web news. Next, we propose a method for automatic extraction of such sentences by using semantic role labels, without typical approaches (temporal expressions, etc.). In a series of experiments, we extract semantic role patterns from future reference sentences and examine the validity of the extracted patterns in classification of future reference sentences.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7115/_p

Copy

@ARTICLE{e99-d_2_514,
author={Yoko NAKAJIMA, Michal PTASZYNSKI, Hirotoshi HONMA, Fumito MASUI, },
journal={IEICE TRANSACTIONS on Information},
title={A Method for Extraction of Future Reference Sentences Based on Semantic Role Labeling},
year={2016},
volume={E99-D},
number={2},
pages={514-524},
abstract={In everyday life, people use past events and their own knowledge in predicting probable unfolding of events. To obtain the necessary knowledge for such predictions, newspapers and the Internet provide a general source of information. Newspapers contain various expressions describing past events, but also current and future events, and opinions. In our research we focused on automatically obtaining sentences that make reference to the future. Such sentences can contain expressions that not only explicitly refer to future events, but could also refer to past or current events. For example, if people read a news article that states “In the near future, there will be an upward trend in the price of gasoline,” they may be likely to buy gasoline now. However, if the article says “The cost of gasoline has just risen 10 yen per liter,” people will not rush to buy gasoline, because they accept this as reality and may expect the cost to decrease in the future. In the following study we firstly investigate future reference sentences in newspapers and Web news. Next, we propose a method for automatic extraction of such sentences by using semantic role labels, without typical approaches (temporal expressions, etc.). In a series of experiments, we extract semantic role patterns from future reference sentences and examine the validity of the extracted patterns in classification of future reference sentences.},
keywords={},
doi={10.1587/transinf.2015EDP7115},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - A Method for Extraction of Future Reference Sentences Based on Semantic Role Labeling
T2 - IEICE TRANSACTIONS on Information
SP - 514
EP - 524
AU - Yoko NAKAJIMA
AU - Michal PTASZYNSKI
AU - Hirotoshi HONMA
AU - Fumito MASUI
PY - 2016
DO - 10.1587/transinf.2015EDP7115
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2016
AB - In everyday life, people use past events and their own knowledge in predicting probable unfolding of events. To obtain the necessary knowledge for such predictions, newspapers and the Internet provide a general source of information. Newspapers contain various expressions describing past events, but also current and future events, and opinions. In our research we focused on automatically obtaining sentences that make reference to the future. Such sentences can contain expressions that not only explicitly refer to future events, but could also refer to past or current events. For example, if people read a news article that states “In the near future, there will be an upward trend in the price of gasoline,” they may be likely to buy gasoline now. However, if the article says “The cost of gasoline has just risen 10 yen per liter,” people will not rush to buy gasoline, because they accept this as reality and may expect the cost to decrease in the future. In the following study we firstly investigate future reference sentences in newspapers and Web news. Next, we propose a method for automatic extraction of such sentences by using semantic role labels, without typical approaches (temporal expressions, etc.). In a series of experiments, we extract semantic role patterns from future reference sentences and examine the validity of the extracted patterns in classification of future reference sentences.
ER -