Generating Code-switched Text for Lexical Learning

Labutov, Igor; Lipson, Hod

doi:10.3115/v1/p14-1053

Cited by 17 publications

(17 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bespalov, Bai, Qi, and Shokoufandeh () showed that an n‐gram model combined with latent representation would produce a more suitable embedding for sentiment classification. Labutov and Lipson () re‐embed existing word embeddings with logistic regression by regarding sentiment supervision of sentences as a regularization term.…”

Section: Sentiment Analysis With Word Embeddingmentioning

confidence: 99%

Deep learning for sentiment analysis: A survey

Zhang

Wang

Liu

2018

WIREs Data Min & Knowl

1,266

622

View full text Add to dashboard Cite

Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state‐of‐the‐art prediction results. Along with the success of deep learning in many application domains, deep learning is also used in sentiment analysis in recent years. This paper gives an overview of deep learning and then provides a comprehensive survey of its current applications in sentiment analysis. This article is categorized under: Fundamental Concepts of Data and Knowledge > Data Concepts Algorithmic Development > Text Mining

show abstract

Section: Sentiment Analysis With Word Embeddingmentioning

confidence: 99%

Deep learning for sentiment analysis: A survey

Zhang

Wang

Liu

2018

WIREs Data Min & Knowl

1,266

622

View full text Add to dashboard Cite

show abstract

“…We use insights from recent works in L2 acquisition from code-switched text as they have focused on learning from context. Labutov and Lipson (2014) carry out experiments to determine the guessability of a word in code switched text. A similar work by Knowles et al (2016) discuss the factors that can potentially affect the guessability of a German word with English context.…”

Section: Related Workmentioning

confidence: 99%

Context Based Approach for Second Language Acquisition

Nayak¹,

Rao²

2018

Proceedings of the Thirteenth Workshop on Innovative Use of NLP For Building Educational Applications

View full text Add to dashboard Cite

SLAM 2018 focuses on predicting a student's mistake while using the Duolingo application. In this paper, we describe the system we developed for this shared task. Our system uses a logistic regression model to predict the likelihood of a student making a mistake while answering an exercise on Duolingo in all three language tracks-English/Spanish (en/es), Spanish/English (es/en) and French/English (fr/en). We conduct an ablation study with several features during the development of this system and discover that context based features play a major role in language acquisition modeling. Our model beats Duolingo's baseline scores in all three language tracks (AUROC scores for en/es = 0.821, es/en = 0.790 and fr/en = 0.812). Our work makes a case for providing favourable textual context for students while learning second language.

show abstract

“…Word embedding learning has received a renewed interest lately due to the impressive performances obtained by the prediction-based word embedding learning methods in a wide range of NLP applications such as sentiment classification [ 6 , 11 , 12 ], named entity recognition [ 13 , 14 ], word sense disambiguation [ 15 , 16 ], relation extraction [ 17 , 18 ], semantic role labeling [ 8 ], and machine translation [ 9 ].…”

Section: Related Workmentioning

confidence: 99%

Learning linear transformations between counting-based and prediction-based word embeddings

2017

View full text Add to dashboard Cite

Despite the growing interest in prediction-based word embedding learning methods, it remains unclear as to how the vector spaces learnt by the prediction-based methods differ from that of the counting-based methods, or whether one can be transformed into the other. To study the relationship between counting-based and prediction-based embeddings, we propose a method for learning a linear transformation between two given sets of word embeddings. Our proposal contributes to the word embedding learning research in three ways: (a) we propose an efficient method to learn a linear transformation between two sets of word embeddings, (b) using the transformation learnt in (a), we empirically show that it is possible to predict distributed word embeddings for novel unseen words, and (c) empirically it is possible to linearly transform counting-based embeddings to prediction-based embeddings, for frequent words, different POS categories, and varying degrees of ambiguities.

show abstract

Generating Code-switched Text for Lexical Learning

Cited by 17 publications

References 19 publications

Deep learning for sentiment analysis: A survey

Deep learning for sentiment analysis: A survey

Context Based Approach for Second Language Acquisition

Learning linear transformations between counting-based and prediction-based word embeddings

Contact Info

Product

Resources

About