Disambiguating Japanese compound verbs

Uchiyama, Kiyoko; Baldwin, Timothy; Ishizaki, Shun

doi:10.1016/j.csl.2005.02.001

Cited by 23 publications

(25 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…His approach, however, requires manually-labelled training data. Uchiyama et al (2005) propose a statistical approach to classifying Japanese LVCs (of the form verb-verb). They acknowledge the importance of the semantic properties of the complement for this task; however, they do not explicitly use such information.…”

Section: Discussion and Concluding Remarksmentioning

confidence: 99%

Automatically learning semantic knowledge about multiword predicates

Fazly

Stevenson

North

2007

Lang Resources & Evaluation

View full text Add to dashboard Cite

Highly frequent and highly polysemous verbs, such as give, take, and make, pose a challenge to automatic lexical acquisition methods. These verbs widely participate in multiword predicates (such as light verb constructions, or LVCs), in which they contribute a broad range of figurative meanings that must be recognized. Here we focus on two properties that are key to the computational treatment of LVCs. First, we consider the degree of figurativeness of the semantic contribution of such a verb to the various LVCs it participates in. Second, we explore the patterns of acceptability of LVCs, and their productivity over semantically related combinations. To assess these properties, we develop statistical measures of figurativeness and acceptability that draw on linguistic properties of LVCs. We demonstrate that these corpus-based measures correlate well with human judgments of the relevant property. We also use the acceptability measure to estimate the degree to which a semantic class of nouns can productively form LVCs with a given verb. The linguistically-motivated measures outperform a standard measure for capturing the strength of collocation of these multiword expressions.

show abstract

Section: Discussion and Concluding Remarksmentioning

confidence: 99%

Automatically learning semantic knowledge about multiword predicates

Fazly

Stevenson

North

2007

Lang Resources & Evaluation

View full text Add to dashboard Cite

show abstract

“…Nonetheless, systematically choosing the most frequent sense is a surprisingly good baseline, not always easy to beat (McCarthy et al, 2007;Navigli, 2009). This was also verified for MWE disambiguation (Uchiyama et al, 2005). Thus, in this work, we implemented a simple supervised predominant-sense heuristic and will investigate more sophisticated WSD techniques as future work.…”

Section: Related Workmentioning

confidence: 99%

UFRGSandLIF at SemEval-2016 Task 10: Rule-Based MWE Identification and Predominant-Supersense Tagging

Cordeiro

Ramisch

Villavicencio

2016

Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

View full text Add to dashboard Cite

This paper presents our approach towards the SemEval-2016 Task 10 -Detecting Minimal Semantic Units and their Meanings. Systems are expected to provide a representation of lexical semantics by (1) segmenting tokens into words and multiword units and (2) providing a supersense tag for segments that function as nouns or verbs. Our pipeline rule-based system uses no external resources and was implemented using the mwetoolkit. First, we extract and filter known MWEs from the training corpus. Second, we group input tokens of the test corpus based on this lexicon, with special treatment for non-contiguous expressions. Third, we use an MWE-aware predominantsense heuristic for supersense tagging. We obtain an F-score of 51.48% for MWE identification and 49.98% for supersense tagging.

show abstract

“…The challenges posed by MWEs have led to them to be referred to as a "pain in the neck" for NLP (Sag et al, 2002); nevertheless, incorporating knowledge of MWEs into NLP applications can lead to improvements in tasks including machine translation (Carpuat and Diab, 2010), information retrieval (Newman et al, 2012), and opinion mining (Berend, 2011). Recent work on token-level MWE identification has focused on methods that are applicable to the full spectrum of kinds of MWEs (Schneider et al, 2014a), in contrast to earlier work that tended to focus on specific kinds of MWEs (Uchiyama et al, 2005;Fazly et al, 2009;Fothergill and Baldwin, 2012). Deep learning is an emerging class of machine learning models that have recently achieved promising results on a range of NLP tasks such as machine translation (Bahdanau et al, 2015;, named entity recognition (Lample et al, 2016), natural language generation (Li et al, 2015), and sentence classification (Kim, 2014).…”

Section: Introductionmentioning

confidence: 99%

“…Many earlier studies on MWE identification have focused on this type of ambiguity, and treated the problem as one of word sense disambiguation, where literal and idiomatic usages are considered different word senses (Birke and Sarkar, 2006;Katz and Giesbrecht, 2006;Li et al, 2010). Other work has leveraged linguistic knowledge of properties of MWEs in order to make these distinctions (Uchiyama et al, 2005;Fazly et al, 2009;Fothergill and Baldwin, 2012). Crucially, this work has typically focused on specific kinds of MWEs, and has not considered identification of the full spectrum of MWEs.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Models For Multiword Expression Identification

Gharbieh

Bhavsar²,

Cook

2017

Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)

View full text Add to dashboard Cite

Multiword expressions (MWEs) are lexical items that can be decomposed into multiple component words, but have properties that are unpredictable with respect to their component words. In this paper we propose the first deep learning models for token-level identification of MWEs. Specifically, we consider a layered feedforward network, a recurrent neural network, and convolutional neural networks. In experimental results we show that convolutional neural networks are able to outperform the previous state-of-the-art for MWE identification, with a convolutional neural network with three hidden layers giving the best performance.

show abstract

Disambiguating Japanese compound verbs

Cited by 23 publications

References 7 publications

Automatically learning semantic knowledge about multiword predicates

Automatically learning semantic knowledge about multiword predicates

UFRGSandLIF at SemEval-2016 Task 10: Rule-Based MWE Identification and Predominant-Supersense Tagging

Deep Learning Models For Multiword Expression Identification

Contact Info

Product

Resources

About