Accurate collocation extraction using a multilingual parser

Seretan, Violeta; Wehrli, Eric

doi:10.3115/1220175.1220295

Cited by 45 publications

(34 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiments performed made use of very small text corpora, probably due to the low efficiency of the syntactic techniques available at that time. Similar experiments were performed more recently [16,17,21]. All of them state that syntax-based methods outperform windowing techniques thanks to a drastic reduction of noise.…”

Section: Related Workmentioning

confidence: 49%

Comparing Different Properties Involved in Word Similarity Extraction

Gamallo

2009

Progress in Artificial Intelligence

View full text Add to dashboard Cite

Abstract. In this paper, we will analyze the behavior of several parameters, namely type of contexts, similarity measures, and word space models, in the task of word similarity extraction from large corpora. The main objective of the paper will be to describe experiments comparing different extraction systems based on all possible combinations of these parameters. Special attention will be paid to the comparison between syntax-based contexts and windowing techniques, binary similarity metrics and more elaborate coefficients, as well as baseline word space models and Singular Value Decomposition strategies. The evaluation leads us to conclude that the combination of syntax-based contexts, binary similarity metrics, and a baseline word space model makes the extraction much more precise than other combinations with more elaborate metrics and complex models.

show abstract

Section: Related Workmentioning

confidence: 49%

Comparing Different Properties Involved in Word Similarity Extraction

Gamallo

2009

Progress in Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Concerning the type of context used to represent word distributions, there is a great number of previous studies that evaluate and compare syntactic contexts (usually dependencies) with bagof-words techniques (Grefenstette, 1993;Seretan and Wehrli, 2006;Padó and Lapata, 2007;Peirsman et al, 2007;Gamallo, 2008Gamallo, , 2009Levy and Goldberg, 2014;Gamallo, 2017). The cited papers state that syntax-based methods outperform bagof-words techniques, in particular when the objective is to compute semantic similarity between functional equivalent words, such as detection of co-hyponym/hypernym word relations (i.e.…”

Section: The Methodsmentioning

confidence: 99%

CitiusNLP at SemEval-2018 Task 10: The Use of Transparent Distributional Models and Salient Contexts to Discriminate Word Attributes

Gamallo

2018

Proceedings of the 12th International Workshop on Semantic Evaluation

View full text Add to dashboard Cite

This article describes the unsupervised strategy submitted by the CitiusNLP team to SemEval 2018 Task 10, a task which consists of predicting whether a word is a discriminative attribute between two other words. The proposed strategy relies on the correspondence between discriminative attributes and relevant contexts of a word. More precisely, the method uses transparent distributional models to extract salient contexts of words which are identified as discriminative attributes. The system performance reaches about 70% accuracy when it is applied on the development dataset, but its accuracy goes down (63%) on the official test dataset.

show abstract

“…Other approaches are hybrid in the sense that they benefit from both statistical and linguistic information. For instance (Seretan and Wehrli, 2006;Baldwin and Villavicencio, 2002;Piao and McEnery, 2001;Dias, 2003).…”

Section: Previous Workmentioning

confidence: 99%

A Supervised Model for Extraction of Multiword Expressions, Based on Statistical Context Features

Farahmand¹,

Martins²

2014

Proceedings of the 10th Workshop on Multiword Expressions (MWE)

View full text Add to dashboard Cite

We present a method for extracting Multiword Expressions (MWEs) based on the immediate context they occur in, using a supervised model. We show some of these contextual features can be very discriminant and combining them with MWEspecific features results in a relatively accurate extraction. We define context as a sequential structure and not a bag of words, consequently, it becomes much more informative about MWEs.

show abstract

Accurate collocation extraction using a multilingual parser

Cited by 45 publications

References 10 publications

Comparing Different Properties Involved in Word Similarity Extraction

Comparing Different Properties Involved in Word Similarity Extraction

CitiusNLP at SemEval-2018 Task 10: The Use of Transparent Distributional Models and Salient Contexts to Discriminate Word Attributes

A Supervised Model for Extraction of Multiword Expressions, Based on Statistical Context Features

Contact Info

Product

Resources

About