Related papers: Strategies of Code-switching in Human-Machine Dialogs

Strategies of Code-switching in Human-Machine Dialogs

URL: http://arxiv.org/abs/2508.07325v1
Date: Sun, 10 Aug 2025 12:41:46 GMT
Title: Strategies of Code-switching in Human-Machine Dialogs
Authors: Dean Geckt, Melinda Fricke, Shuly Wintner,
Abstract summary: Most people are multilingual, and most multilinguals code-switch.<n>We developed a bot capable of completing a Map Task with human participants using code-switched Spanish and English.
Score: 3.417612970260323
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Most people are multilingual, and most multilinguals code-switch, yet the characteristics of code-switched language are not fully understood. We developed a chatbot capable of completing a Map Task with human participants using code-switched Spanish and English. In two experiments, we prompted the bot to code-switch according to different strategies, examining (1) the feasibility of such experiments for investigating bilingual language use, and (2) whether participants would be sensitive to variations in discourse and grammatical patterns. Participants generally enjoyed code-switching with our bot as long as it produced predictable code-switching behavior; when code-switching was random or ungrammatical (as when producing unattested incongruent mixed-language noun phrases, such as `la fork'), participants enjoyed the task less and were less successful at completing it. These results underscore the potential downsides of deploying insufficiently developed multilingual language technology, while also illustrating the promise of such technology for conducting research on bilingual language use.

Related papers

Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training [58.696660064190475]
We find that the existence of code-switching, alternating between different languages within a context, is key to multilingual capabilities.<n>To better explore the power of code-switching for language alignment during pre-training, we investigate the strategy of synthetic code-switching.
arXiv Detail & Related papers (2025-04-02T15:09:58Z)
Code-switching in text and speech reveals information-theoretic audience design [5.3329709073809095]
We use language modeling to investigate the factors that influence code-switching. Code-switching occurs when a speaker alternates between one language variety (the primary language) and another (the secondary language)
arXiv Detail & Related papers (2024-08-08T17:14:12Z)
Measuring Entrainment in Spontaneous Code-switched Speech [3.9736028502700527]
We study patterns of written and spoken entrainment in code-switched spontaneous speech between humans. Our findings give rise to important implications for the potentially "universal" nature of entrainment as a communication phenomenon.
arXiv Detail & Related papers (2023-11-13T19:41:34Z)
Language Agnostic Code Embeddings [61.84835551549612]
We focus on the cross-lingual capabilities of code embeddings across different programming languages. Code embeddings comprise two distinct components: one deeply tied to the nuances and syntax of a specific language, and the other remaining agnostic to these details. We show that when we isolate and eliminate this language-specific component, we witness significant improvements in downstream code retrieval tasks.
arXiv Detail & Related papers (2023-10-25T17:34:52Z)
LAE: Language-Aware Encoder for Monolingual and Multilingual ASR [87.74794847245536]
A novel language-aware encoder (LAE) architecture is proposed to handle both situations by disentangling language-specific information. Experiments conducted on Mandarin-English code-switched speech suggest that the proposed LAE is capable of discriminating different languages in frame-level.
arXiv Detail & Related papers (2022-06-05T04:03:12Z)
Reducing language context confusion for end-to-end code-switching automatic speech recognition [50.89821865949395]
We propose a language-related attention mechanism to reduce multilingual context confusion for the E2E code-switching ASR model. By calculating the respective attention of multiple languages, our method can efficiently transfer language knowledge from rich monolingual data.
arXiv Detail & Related papers (2022-01-28T14:39:29Z)
Are Multilingual Models Effective in Code-Switching? [57.78477547424949]
We study the effectiveness of multilingual language models to understand their capability and adaptability to the mixed-language setting. Our findings suggest that pre-trained multilingual models do not necessarily guarantee high-quality representations on code-switching.
arXiv Detail & Related papers (2021-03-24T16:20:02Z)
Transformer-Transducers for Code-Switched Speech Recognition [23.281314397784346]
We present an end-to-end ASR system using a transformer-transducer model architecture for code-switched speech recognition. First, we introduce two auxiliary loss functions to handle the low-resource scenario of code-switching. Second, we propose a novel mask-based training strategy with language ID information to improve the label encoder training towards intra-sentential code-switching.
arXiv Detail & Related papers (2020-11-30T17:27:41Z)
Towards Code-switched Classification Exploiting Constituent Language Resources [3.655021726150369]
We convert code-switched data into constituent languages for exploiting both monolingual and cross-lingual settings. We perform experiments for two downstream tasks, sarcasm detection and hate speech detection, in the English-Hindi code-switched setting.
arXiv Detail & Related papers (2020-11-03T18:43:19Z)
Phonological Features for 0-shot Multilingual Speech Synthesis [50.591267188664666]
We show that code-switching is possible for languages unseen during training, even within monolingual models. We generate intelligible, code-switched speech in a new language at test time, including the approximation of sounds never seen in training.
arXiv Detail & Related papers (2020-08-06T18:25:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.