Which distributional cues help the most? Unsupervised context selection for lexical category acquisition

Giovanni Cassani; Robert Grimm; Walter Daelemans; Steven Gillis

Which distributional cues help the most? Unsupervised context selection for lexical category acquisition

Giovanni Cassani^*
, Robert Grimm
, Walter Daelemans
, Steven Gillis

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Abstract

Starting from the distributional bootstrapping hypothesis, we propose an unsupervised model that selects the most useful distributional information according to its salience in the input, incorporating psycholinguistic evidence. With a supervised Parts-of-Speech tagging experiment, we provide preliminary results suggesting that the distributional contexts extracted by our model yield similar performances as compared to current approaches from the literature, with a gain in psychological plausibility. We also introduce a more principled way to evaluate the effectiveness of distributional contexts in helping learners to group words in syntactic categories.

Original language	English
Title of host publication	Proceedings of the 6th Workshop on Cognitive Aspects of Computational Language Learning (CogACLL)
Publisher	Association for Computational Linguistics (ACL)
Pages	33-39
Number of pages	7
Publication status	Published - Sept 2015
Externally published	Yes

Cite this

@inproceedings{0649b1bd7b6f4e809a28a619f4c1e6f8,

title = "Which distributional cues help the most? Unsupervised context selection for lexical category acquisition",

abstract = "Starting from the distributional bootstrapping hypothesis, we propose an unsupervised model that selects the most useful distributional information according to its salience in the input, incorporating psycholinguistic evidence. With a supervised Parts-of-Speech tagging experiment, we provide preliminary results suggesting that the distributional contexts extracted by our model yield similar performances as compared to current approaches from the literature, with a gain in psychological plausibility. We also introduce a more principled way to evaluate the effectiveness of distributional contexts in helping learners to group words in syntactic categories.",

author = "Giovanni Cassani and Robert Grimm and Walter Daelemans and Steven Gillis",

year = "2015",

month = sep,

language = "English",

pages = "33--39",

booktitle = "Proceedings of the 6th Workshop on Cognitive Aspects of Computational Language Learning (CogACLL)",

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

}

Which distributional cues help the most? Unsupervised context selection for lexical category acquisition. / Cassani, Giovanni; Grimm, Robert; Daelemans, Walter et al.
Proceedings of the 6th Workshop on Cognitive Aspects of Computational Language Learning (CogACLL). Association for Computational Linguistics (ACL), 2015. p. 33-39.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Which distributional cues help the most? Unsupervised context selection for lexical category acquisition

AU - Cassani, Giovanni

AU - Grimm, Robert

AU - Daelemans, Walter

AU - Gillis, Steven

PY - 2015/9

Y1 - 2015/9

N2 - Starting from the distributional bootstrapping hypothesis, we propose an unsupervised model that selects the most useful distributional information according to its salience in the input, incorporating psycholinguistic evidence. With a supervised Parts-of-Speech tagging experiment, we provide preliminary results suggesting that the distributional contexts extracted by our model yield similar performances as compared to current approaches from the literature, with a gain in psychological plausibility. We also introduce a more principled way to evaluate the effectiveness of distributional contexts in helping learners to group words in syntactic categories.

AB - Starting from the distributional bootstrapping hypothesis, we propose an unsupervised model that selects the most useful distributional information according to its salience in the input, incorporating psycholinguistic evidence. With a supervised Parts-of-Speech tagging experiment, we provide preliminary results suggesting that the distributional contexts extracted by our model yield similar performances as compared to current approaches from the literature, with a gain in psychological plausibility. We also introduce a more principled way to evaluate the effectiveness of distributional contexts in helping learners to group words in syntactic categories.

M3 - Conference contribution

SP - 33

EP - 39

BT - Proceedings of the 6th Workshop on Cognitive Aspects of Computational Language Learning (CogACLL)

PB - Association for Computational Linguistics (ACL)

ER -

Which distributional cues help the most? Unsupervised context selection for lexical category acquisition

Abstract

Fingerprint

Cite this