Inference for Natural Language,Citation formats

  • Authors:
  • A Alshahrani
  • A M Ramsay

Standard

Inference for Natural Language, / Alshahrani, A; Ramsay, A M.

host publication. 2013. p. 60-64.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Alshahrani, A & Ramsay, AM 2013, Inference for Natural Language, in host publication. pp. 60-64, Proceedings of the Joint Symposium on Semantic Processing. Textual Inference and Structures in Corpora, Trento, Italy, 20/11/13.

APA

Alshahrani, A., & Ramsay, A. M. (2013). Inference for Natural Language, In host publication (pp. 60-64)

Vancouver

Alshahrani A, Ramsay AM. Inference for Natural Language, In host publication. 2013. p. 60-64

Author

Alshahrani, A ; Ramsay, A M. / Inference for Natural Language,. host publication. 2013. pp. 60-64

Bibtex

@inproceedings{66ed1f6d492a44a5a4ff09ea63b65798,
title = "Inference for Natural Language,",
abstract = "The main aim of this study is to develop a natural language inference (NLI) engine that is more robust than typical systems that are based on post-Montague approaches to semantics and more accurate than the kinds of shallow approaches usually used for textual entailment, The term robustness is concerned with processing as many inputs as possible successfully, and the term accuracy is concerned with producing correct result. In recent years, several approaches have been proposed for NLI. These approaches range from shallow approaches to deep approaches. However, each­ approach has a number of limitations, which we discuss in this paper. We argue that all approaches to NLI share a common architecture, and that it may be possible to overcome the limitations inherent in the existing approaches by combining elements of both kinds of strategy.",
author = "A Alshahrani and Ramsay, {A M}",
note = "Allan Ramsay's contribution to this work was supported by Qatar National Research Foundation grant NPRP 09-046-6-001. Amal Alshahran is supported by a grant from the government of the Kingdom of Saudi Arabia.",
year = "2013",
month = "11",
day = "21",
language = "English",
pages = "60--64",
booktitle = "host publication",

}

RIS

TY - GEN

T1 - Inference for Natural Language,

AU - Alshahrani, A

AU - Ramsay, A M

N1 - Allan Ramsay's contribution to this work was supported by Qatar National Research Foundation grant NPRP 09-046-6-001. Amal Alshahran is supported by a grant from the government of the Kingdom of Saudi Arabia.

PY - 2013/11/21

Y1 - 2013/11/21

N2 - The main aim of this study is to develop a natural language inference (NLI) engine that is more robust than typical systems that are based on post-Montague approaches to semantics and more accurate than the kinds of shallow approaches usually used for textual entailment, The term robustness is concerned with processing as many inputs as possible successfully, and the term accuracy is concerned with producing correct result. In recent years, several approaches have been proposed for NLI. These approaches range from shallow approaches to deep approaches. However, each­ approach has a number of limitations, which we discuss in this paper. We argue that all approaches to NLI share a common architecture, and that it may be possible to overcome the limitations inherent in the existing approaches by combining elements of both kinds of strategy.

AB - The main aim of this study is to develop a natural language inference (NLI) engine that is more robust than typical systems that are based on post-Montague approaches to semantics and more accurate than the kinds of shallow approaches usually used for textual entailment, The term robustness is concerned with processing as many inputs as possible successfully, and the term accuracy is concerned with producing correct result. In recent years, several approaches have been proposed for NLI. These approaches range from shallow approaches to deep approaches. However, each­ approach has a number of limitations, which we discuss in this paper. We argue that all approaches to NLI share a common architecture, and that it may be possible to overcome the limitations inherent in the existing approaches by combining elements of both kinds of strategy.

M3 - Conference contribution

SP - 60

EP - 64

BT - host publication

ER -