A Word Embedding Approach to Identifying Verb-Noun Idiomatic Combinations

Gharbieh, Waseem; Bhavsar, Virendrakumar C.; Cook, Paul F.

doi:10.18653/v1/w16-1817

Cited by 19 publications

(23 citation statements)

References 15 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future work we therefore also intend to consider approaches such as context2vec (Melamud et al, 2016) which explicitly encode the context in which a token occurs. Finally, one known challenge of VNC token classification is to develop models that are able to generalize to VNC types that were not seen during training (Gharbieh et al, 2016). In future work we plan to explore this experimental setup.…”

Section: Discussionmentioning

confidence: 99%

“…Work on MWE identification has leveraged rich linguistic knowledge of the constructions under consideration (e.g., Fazly et al, 2009;Fothergill and Baldwin, 2012), treated literal and idiomatic as two senses of an expression and applied approaches similar to word-sense disambiguation (e.g., Birke and Sarkar, 2006;Hashimoto and Kawahara, 2008), incorporated topic models (e.g., Li et al, 2010), and made use of distributed representations of words (Gharbieh et al, 2016).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Leveraging distributed representations and lexico-syntactic fixedness for token-level prediction of the idiomaticity of English verb-noun combinations

King

Cook

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Self Cite

View full text Add to dashboard Cite

Verb-noun combinations (VNCs)-e.g., blow the whistle, hit the roof, and see stars-are a common type of English idiom that are ambiguous with literal usages. In this paper we propose and evaluate models for classifying VNC usages as idiomatic or literal, based on a variety of approaches to forming distributed representations. Our results show that a model based on averaging word embeddings performs on par with, or better than, a previously-proposed approach based on skip-thoughts. Idiomatic usages of VNCs are known to exhibit lexico-syntactic fixedness. We further incorporate this information into our models, demonstrating that this rich linguistic knowledge is complementary to the information carried by distributed representations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Leveraging distributed representations and lexico-syntactic fixedness for token-level prediction of the idiomaticity of English verb-noun combinations

King

Cook

2018

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Self Cite

View full text Add to dashboard Cite

show abstract

“…, which is a similar framework to that of previous work (Neelakantan et al, 2014;Gharbieh et al, 2016). We then tested a method based on the positive pointwise mutual information (PPMI) (Levy et al, 2015;Hamilton et al, 2016).…”

Section: Methods For Comparative Evaluationmentioning

confidence: 99%

Distinguishing Japanese Non-standard Usages from Standard Ones

Aoki

Sasano

Takamura

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

We focus on non-standard usages of common words on social media. In the context of social media, words sometimes have other usages that are totally different from their original. In this study, we attempt to distinguish non-standard usages on social media from standard ones in an unsupervised manner. Our basic idea is that nonstandardness can be measured by the inconsistency between the expected meaning of the target word and the given context. For this purpose, we use context embeddings derived from word embeddings. Our experimental results show that the model leveraging the context embedding outperforms other methods and provide us with findings, for example, on how to construct context embeddings and which corpus to use.

show abstract

“…Skip-gram (Mikolov et al 2013) Skip-gram IN Mitra, Nalisnick, Craswell, and Caruana (2016) Press and Wolf (2017) (Neelakantan, Shankar, Passos, and McCallum 2014;Gharbieh, Virendra, and Cook 2016 (Levy et al 2015;Hamilton, Clark, Leskovec, and…”

Section: Skip-gram With Negative Sampling (Sgns)mentioning

confidence: 99%

Detecting Nonstandard Word Usages on Social Media

Aoki

Sasano

Takamura

et al. 2019

Journal of Natural Language Processing

View full text Add to dashboard Cite

We focus on nonstandard usages of common words on social media, where words, sometimes, are used in a totally different manner from that of their original or standard usage. In this work, we attempt to distinguish nonstandard usages on social media from standard ones in an unsupervised manner. We also constructed new Twitter dataset consisting of 40 words with nonstandard usages and then used the dataset for evaluation in an experiment. For this task, our basic idea is that nonstandard usage can be measured by the inconsistency between the target word's expected meaning and the given context. For this purpose, we use context embeddings derived from word embeddings. Our experimental results show that the model leveraging the context embedding outperforms other methods and also provide us with findings, for example, on how to construct context embeddings, and which corpus to use.

show abstract

A Word Embedding Approach to Identifying Verb-Noun Idiomatic Combinations

Cited by 19 publications

References 15 publications

Leveraging distributed representations and lexico-syntactic fixedness for token-level prediction of the idiomaticity of English verb-noun combinations

Leveraging distributed representations and lexico-syntactic fixedness for token-level prediction of the idiomaticity of English verb-noun combinations

Distinguishing Japanese Non-standard Usages from Standard Ones

Detecting Nonstandard Word Usages on Social Media

Contact Info

Product

Resources

About