A Survey of Code-switched Speech and Language Processing

Abstract

Code-switching, the alternation of languages within a conversation or utterance, is a common communicative phenomenon that occurs in multilingual communities across the world. This survey reviews computational approaches for code-switched Speech and Natural Language Processing. We motivate why processing code-switched text and speech is essential for building intelligent agents and systems that interact with users in multilingual communities. As code-switching data and resources are scarce, we list what is available in various code-switched language pairs with the language processing tasks they can be used for. We review code-switching research in various Speech and NLP applications, including language processing tools and end-to-end systems. We conclude with future directions and open problems in the field.

References in corpus (26)

• A Multi-task Approach for Named Entity Recognition in Social Media Data
• XNLI: Evaluating Cross-lingual Sentence Representations
• Sentiment Analysis of Code-Mixed Indian Languages: An Overview of SAIL_Code-Mixed Shared Task @ICON-2017
• Syntactic and Semantic Features For Code-Switching Factored Language Models
• Towards End-to-End Code-Switching Speech Recognition
• Overview for the Second Shared Task on Language Identification in Code-Switched Data
• Recurrent-Neural-Network for Language Detection on Twitter Code-Switching Corpus
• Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
• Grammatical Constraints on Intra-sentential Code-Switching: From Theories to Working Models
• On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
• Analyzing Roles of Classifiers and Code-Mixed factors for Sentiment Identification
• Creating a Large Multi-Layered Representational Repository of Linguistic Code Switched Arabic Data
• CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP
• Semi-supervised Development of ASR Systems for Multilingual Code-switched Speech in Under-resourced Languages
• Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition
• Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
• Building a Unified Code-Switching ASR System for South African Languages
• Hindi-English Code-Switching Speech Corpus
• Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition
• Multi-Encoder-Decoder Transformer for Code-Switching Speech Recognition
• Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition
• Challenges of Computational Processing of Code-Switching
• Multi-Graph Decoding for Code-Switching ASR
• Crowdsourcing Universal Part-Of-Speech Tags for Code-Switching
• Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognition
• Code-Switching Detection with Data-Augmented Acoustic and Language Models

Cited by in corpus (13)

• QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension
• SJ_AJ@DravidianLangTech-EACL2021: Task-Adaptive Pre-Training of Multilingual BERT models for Offensive Language Identification
• Learning to Recognize Code-switched Speech Without Forgetting Monolingual Speech Recognition
• GupShup: An Annotated Corpus for Abstractive Summarization of Open-Domain Code-Switched Conversations
• Task-Specific Pre-Training and Cross Lingual Transfer for Code-Switched Data
• LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation
• End-to-End Code-Switching ASR for Low-Resourced Language Pairs
• Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots
• Towards Code-switched Classification Exploiting Constituent Language Resources
• Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition
• Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation
• Can You Traducir This? Machine Translation for Code-Switched Input
• Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching