Exploration of the Impact of Maximum Entropy in Recurrent Neural Network Language Models for Code-Switching Speech

Vu, Ngoc Thang; Schultz, Tanja

doi:10.3115/v1/w14-3904

Cited by 8 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They showed that their system outperforms the best SVMbased systems reported in the EMNLP'14 Code-Switching Workshop. Vu and Schultz (2014) proposed to adapt the recurrent neural network language model to different code-switching behaviors and even use them to generate artificial code-switching text data. Adel et al (2013) investigated the application of RNN language models and factored language models to the task of identifying code-switching in speech, and reported a significant improvement compared to the traditional n-gram language model.…”

Section: Related Workmentioning

confidence: 99%

Multilingual Code-switching Identification via LSTM Recurrent Neural Networks

Samih¹,

Maharjan²,

Attia³

et al. 2016

Proceedings of the Second Workshop on Computational Approaches to Code Switching

View full text Add to dashboard Cite

This paper describes the HHU-UH-G system submitted to the EMNLP 2016 Second Workshop on Computational Approaches to Code Switching. Our system ranked first place for Arabic (MSA-Egyptian) with an F1-score of 0.83 and second place for Spanish-English with an F1-score of 0.90. The HHU-UH-G system introduces a novel unified neural network architecture for language identification in code-switched tweets for both SpanishEnglish and MSA-Egyptian dialect. The system makes use of word and character level representations to identify code-switching. For the MSA-Egyptian dialect the system does not rely on any kind of language-specific knowledge or linguistic resources such as, Part Of Speech (POS) taggers, morphological analyzers, gazetteers or word lists to obtain state-ofthe-art performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Multilingual Code-switching Identification via LSTM Recurrent Neural Networks

Samih¹,

Maharjan²,

Attia³

et al. 2016

Proceedings of the Second Workshop on Computational Approaches to Code Switching

View full text Add to dashboard Cite

show abstract

“…To alleviate the data sparsity problem, some approaches work by generating artificial CS text based on a CS-aware recurrent neural network decoder (Vu and Schultz, 2014) or a machine translation system to create CS data from monolingual data . Such techniques would benefit from better understanding of the characteristics of codeswitching data.…”

Section: Resultsmentioning

confidence: 99%

Challenges of Computational Processing of Code-Switching

Çetinoğlu¹,

Schulz²,

Vu³

2016

Proceedings of the Second Workshop on Computational Approaches to Code Switching

Self Cite

View full text Add to dashboard Cite

This paper addresses challenges of Natural Language Processing (NLP) on non-canonical multilingual data in which two or more languages are mixed. It refers to code-switching which has become more popular in our daily life and therefore obtains an increasing amount of attention from the research community. We report our experience that covers not only core NLP tasks such as normalisation, language identification, language modelling, part-of-speech tagging and dependency parsing but also more downstream ones such as machine translation and automatic speech recognition. We highlight and discuss the key problems for each of the tasks with supporting examples from different language pairs and relevant previous work.

show abstract

“…The second approach [10,11] leverages recurrent neural network language models trained with CS transcriptions. Because of the small amount of CS transcriptions, the generated texts are often meaningless [10]. The third approach [12] formulates the CS text generation task as a sequence to sequence problem, mapping monolingual text to CS text and solves the task in an end-to-end fashion using sequence-tosequence model [16,17].…”

Section: Introductionmentioning

confidence: 99%

Improving Code-Switching Language Modeling with Artificially Generated Texts Using Cycle-Consistent Adversarial Networks

Li¹,

Vu²

2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

This paper presents our latest effort on improving Codeswitching language models that suffer from data scarcity. We investigate methods to augment Code-switching training text data by artificially generating them. Concretely, we propose a cycle-consistent adversarial networks based framework to transfer monolingual text into Code-switching text, considering Code-switching as a speaking style. Our experimental results on the SEAME corpus show that utilizing artificially generated Code-switching text data improves consistently the language model as well as the automatic speech recognition performance.

show abstract

Exploration of the Impact of Maximum Entropy in Recurrent Neural Network Language Models for Code-Switching Speech

Cited by 8 publications

References 20 publications

Multilingual Code-switching Identification via LSTM Recurrent Neural Networks

Multilingual Code-switching Identification via LSTM Recurrent Neural Networks

Challenges of Computational Processing of Code-Switching

Improving Code-Switching Language Modeling with Artificially Generated Texts Using Cycle-Consistent Adversarial Networks

Contact Info

Product

Resources

About