Natural Language Inference with Monotonicity

Hai Hu; Qi Chen; Lawrence S. Moss

doi:10.18653/v1/W19-0502

Natural Language Inference with Monotonicity

Hai Hu
, Qi Chen
, Lawrence S. Moss

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

11 Citations (Scopus)

Abstract

This paper describes a working system which performs natural language inference using polarity-marked parse trees. The system handles all of the instances of monotonicity inference in the FraCaS data set. Except for the initial parse, it is entirely deterministic. It handles multi-premise arguments, and the kind of inference performed is essentially “logical”, but it goes beyond what is representable in first-order logic. In any case, the system works on surface forms rather than on representations of any kind.

Original language	English
Title of host publication	Proceedings of the 13th International Conference on Computational Semantics - Short Papers
Editors	Simon Dobnik, Stergios Chatzikyriakidis, Vera Demberg
Publisher	Association for Computational Linguistics (ACL)
Pages	8-15
ISBN (Electronic)	9781950737208
DOIs	https://doi.org/10.18653/v1/W19-0502
Publication status	Published - May 2019
Externally published	Yes
Event	The 13th International Conference on Computational Semantics - Gothenburg, Sweden Duration: 23 May 2019 → 27 May 2019

Competition

Competition	The 13th International Conference on Computational Semantics
Country/Territory	Sweden
City	Gothenburg
Period	23/05/19 → 27/05/19

More information

10.18653/v1/W19-0502

Cite this

@inproceedings{e12db8e3fb57414590d6bc95ae82af7a,

title = "Natural Language Inference with Monotonicity",

abstract = "This paper describes a working system which performs natural language inference using polarity-marked parse trees. The system handles all of the instances of monotonicity inference in the FraCaS data set. Except for the initial parse, it is entirely deterministic. It handles multi-premise arguments, and the kind of inference performed is essentially {\textquotedblleft}logical{\textquotedblright}, but it goes beyond what is representable in first-order logic. In any case, the system works on surface forms rather than on representations of any kind.",

author = "Hai Hu and Qi Chen and Moss, \{Lawrence S.\}",

year = "2019",

month = may,

doi = "10.18653/v1/W19-0502",

language = "English",

pages = "8--15",

editor = "Simon Dobnik and Stergios Chatzikyriakidis and Vera Demberg",

booktitle = "Proceedings of the 13th International Conference on Computational Semantics - Short Papers",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

note = "The 13th International Conference on Computational Semantics ; Conference date: 23-05-2019 Through 27-05-2019",

}

Hu, H, Chen, Q & Moss, LS 2019, Natural Language Inference with Monotonicity. in S Dobnik, S Chatzikyriakidis & V Demberg (eds), Proceedings of the 13th International Conference on Computational Semantics - Short Papers. Association for Computational Linguistics (ACL), pp. 8-15, The 13th International Conference on Computational Semantics, Gothenburg, Sweden, 23/05/19. https://doi.org/10.18653/v1/W19-0502

Natural Language Inference with Monotonicity. / Hu, Hai; Chen, Qi; Moss, Lawrence S.
Proceedings of the 13th International Conference on Computational Semantics - Short Papers. ed. / Simon Dobnik; Stergios Chatzikyriakidis; Vera Demberg. Association for Computational Linguistics (ACL), 2019. p. 8-15.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Natural Language Inference with Monotonicity

AU - Hu, Hai

AU - Chen, Qi

AU - Moss, Lawrence S.

PY - 2019/5

Y1 - 2019/5

N2 - This paper describes a working system which performs natural language inference using polarity-marked parse trees. The system handles all of the instances of monotonicity inference in the FraCaS data set. Except for the initial parse, it is entirely deterministic. It handles multi-premise arguments, and the kind of inference performed is essentially “logical”, but it goes beyond what is representable in first-order logic. In any case, the system works on surface forms rather than on representations of any kind.

AB - This paper describes a working system which performs natural language inference using polarity-marked parse trees. The system handles all of the instances of monotonicity inference in the FraCaS data set. Except for the initial parse, it is entirely deterministic. It handles multi-premise arguments, and the kind of inference performed is essentially “logical”, but it goes beyond what is representable in first-order logic. In any case, the system works on surface forms rather than on representations of any kind.

U2 - 10.18653/v1/W19-0502

DO - 10.18653/v1/W19-0502

M3 - Conference article published in proceeding or book

SP - 8

EP - 15

BT - Proceedings of the 13th International Conference on Computational Semantics - Short Papers

A2 - Dobnik, Simon

A2 - Chatzikyriakidis, Stergios

A2 - Demberg, Vera

PB - Association for Computational Linguistics (ACL)

T2 - The 13th International Conference on Computational Semantics

Y2 - 23 May 2019 through 27 May 2019

ER -

Natural Language Inference with Monotonicity

Abstract

Competition

More information

Fingerprint

Cite this