Translation and extension of concepts across languages

Davidov, Dmitry; Rappoport, Ari

doi:10.3115/1609067.1609086

Cited by 15 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consider, for example, recent hashtag trends such as #deletefacebook, which sent Facebook stock plummeting in 2018, or current political races in which candidates win or lose based on their ability to use, or intentionally opt out of, social media. As a result, much of the work around this discursive function focuses on ways to build and measure public sentiment through the automated analysis of hashtags (Cunha et al, 2011; Davidov, Tsur, & Rappoport, 2010; Lu & Thomas, 2015; Ma, Sun, Yuan, & Cong, 2014; Mohammad & Kiritchenko, 2015; Qadir & Riloff, 2014; Weston, Chopra, & Adams, 2014).…”

Section: Hashtagsmentioning

confidence: 99%

Emergent Digital Discourses: What Can We Learn From Hashtags and Digital Games to Expand Learners’ Second Language Repertoire?

Sykes

2019

Ann Rev Appl Linguist

View full text Add to dashboard Cite

In recent years, digital technologies have expanded the possibilities for human interactions in ways that were never before imagined, further complicating the teaching and learning of languages (Taguchi & Sykes, 2013; Thorne, Sauro, & Smith, 2015). Despite this complexity, when approached as meaningful, high-stakes practices, discourses in digital contexts can be highly useful for language learning and teaching. This article synthesizes work related to two digital discourse contexts, specifically hashtags and digital games. Moving away from technology as the vehicle to deliver “important content,” the analysis to follow examines digital discourses as both the content and context to be examined as part of learners’ multilingual experiences. The article begins by situating the discussion focused on digital discourses, reviewing relevant work addressing interactional patterns in each context, and then applying findings to second language teaching and learning. Drawing on empirical work, the article then describes a framework with specific examples for learner exploration of digital discourses as part of their language learning experience. The article concludes with implications for future research and teaching.

show abstract

Section: Hashtagsmentioning

confidence: 99%

Emergent Digital Discourses: What Can We Learn From Hashtags and Digital Games to Expand Learners’ Second Language Repertoire?

Sykes

2019

Ann Rev Appl Linguist

View full text Add to dashboard Cite

show abstract

“…For oral language text or network parlance processing, other features such as using environment and text source also need to be considered, e.g. Twitter hashtags and smileys and user behavior .…”

Section: Related Workmentioning

confidence: 99%

Sentiment analysis method based on an improved modifying‐matrix language model

Zhi-gang

Ren

Miao

2018

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

In this paper, a sentence-level sentiment analysis method is proposed to deal with sentiment measurement and classification problems. It is developed from a model called the synthetic and computational language model (SCLM), which represents modifying and modified information, respectively, using matrices and vectors. In the proposed method, a global modifying matrix of a sentence is constructed, the determinant value of this matrix is calculated and adjusted, and then the final value is used as the sentiment value of the sentence. Regression experiment shows that the deviation between the output sentiment and the target sentiment does not exceed a class distance of five classes. The classification experiment shows that the proposed method has improved most of the performance compared to the simplified SCLM and in some cases, such as in 'very positive' class and 'very negative' class, reaches higher precision performance than the baseline method.

show abstract

“…Stages 1-3 of the algorithm have been described in (Davidov and Rappoport, 2009), where the goal was to translate a concept given in one language to other languages. The framework presented here includes the new stages 4-5, and its goal and evaluation methods are completely different.…”

Section: The Algorithmmentioning

confidence: 99%

Enhancement of lexical concepts using cross-lingual web mining

Davidov

Rappoport

2009

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing Volume 2 - EMNLP '09

Self Cite

View full text Add to dashboard Cite

Sets of lexical items sharing a significant aspect of their meaning (concepts) are fundamental in linguistics and NLP. Manual concept compilation is labor intensive, error prone and subjective. We present a web-based concept extension algorithm. Given a set of terms specifying a concept in some language, we translate them to a wide range of intermediate languages, disambiguate the translations using web counts, and discover additional concept terms using symmetric patterns. We then translate the discovered terms back into the original language, score them, and extend the original concept by adding backtranslations having high scores. We evaluate our method in 3 source languages and 45 intermediate languages, using both human judgments and WordNet. In all cases, our cross-lingual algorithm significantly improves high quality concept extension.

show abstract

Translation and extension of concepts across languages

Cited by 15 publications

References 18 publications

Emergent Digital Discourses: What Can We Learn From Hashtags and Digital Games to Expand Learners’ Second Language Repertoire?

Emergent Digital Discourses: What Can We Learn From Hashtags and Digital Games to Expand Learners’ Second Language Repertoire?

Sentiment analysis method based on an improved modifying‐matrix language model

Enhancement of lexical concepts using cross-lingual web mining

Contact Info

Product

Resources

About