DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models

• URL: http://arxiv.org/abs/2501.16581v1
• Date: Mon, 27 Jan 2025 23:53:04 GMT
• Title: DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models
• Authors: Niyati Bafna, Emily Chang, Nathaniel R. Robinson, David R. Mortensen, Kenton Murray, David Yarowsky, Hale Sirin,
• Abstract summary: Most of the world's languages and dialects are low-resource, and lack support in mainstream machine translation (MT) models. We present DialUp, consisting of a training-time technique for adapting a pretrained model to dialectical data. We show considerable performance gains for several dialects from four language families, and modest gains for two other language families.
• Score: 11.066884521130056
• License:
• Abstract: Most of the world's languages and dialects are low-resource, and lack support in mainstream machine translation (MT) models. However, many of them have a closely-related high-resource language (HRL) neighbor, and differ in linguistically regular ways from it. This underscores the importance of model robustness to dialectical variation and cross-lingual generalization to the HRL dialect continuum. We present DialUp, consisting of a training-time technique for adapting a pretrained model to dialectical data (M->D), and an inference-time intervention adapting dialectical data to the model expertise (D->M). M->D induces model robustness to potentially unseen and unknown dialects by exposure to synthetic data exemplifying linguistic mechanisms of dialectical variation, whereas D->M treats dialectical divergence for known target dialects. These methods show considerable performance gains for several dialects from four language families, and modest gains for two other language families. We also conduct feature and error analyses, which show that language varieties with low baseline MT performance are more likely to benefit from these approaches.

Related papers

• Linguistically Grounded Analysis of Language Models using Shapley Head Values [2.914115079173979]
  We investigate the processing of morphosyntactic phenomena by leveraging a recently proposed method for probing language models via Shapley Head Values (SHVs) Using the English language BLiMP dataset, we test our approach on two widely used models, BERT and RoBERTa, and compare how linguistic constructions are handled. Our results show that SHV-based attributions reveal distinct patterns across both models, providing insights into how language models organize and process linguistic information.
  arXiv  Detail & Related papers  (2024-10-17T09:48:08Z)
• MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting [53.77590764277568]
  We introduce a novel MoE-CT architecture that separates the base model's learning from the multilingual expansion process. Our design freezes the original LLM parameters, thus safeguarding its performance in high-resource languages, while an appended MoE module, trained on diverse language datasets, augments low-resource language proficiency.
  arXiv  Detail & Related papers  (2024-06-25T11:03:45Z)
• Modeling Orthographic Variation in Occitan's Dialects [3.038642416291856]
  Large multilingual models minimize the need for spelling normalization during pre-processing. Our findings suggest that large multilingual models minimize the need for spelling normalization during pre-processing.
  arXiv  Detail & Related papers  (2024-04-30T07:33:51Z)
• Quantifying the Dialect Gap and its Correlates Across Languages [69.18461982439031]
  This work will lay the foundation for furthering the field of dialectal NLP by laying out evident disparities and identifying possible pathways for addressing them through mindful data collection.
  arXiv  Detail & Related papers  (2023-10-23T17:42:01Z)
• Parameter and Data Efficient Continual Pre-training for Robustness to Dialectal Variance in Arabic [9.004920233490642]
  We show that multilingual-BERT (mBERT) incrementally pretrained on Arabic monolingual data takes less training time and yields comparable accuracy when compared to our custom monolingual Arabic model. We then explore two continual pre-training methods-- (1) using small amounts of dialectical data for continual finetuning and (2) parallel Arabic to English data and a Translation Language Modeling loss function.
  arXiv  Detail & Related papers  (2022-11-08T02:51:57Z)
• Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models [28.036233760742125]
  We causally probe multilingual language models (XGLM and multilingual BERT) across various languages. We find significant neuron overlap across languages in autoregressive multilingual language models, but not masked language models.
  arXiv  Detail & Related papers  (2022-10-25T20:43:36Z)
• A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition [80.87085897419982]
  We propose a novel acoustic modeling technique for accurate multi-dialect speech recognition with a single AM. Our proposed AM is dynamically adapted based on both dialect information and its internal representation, which results in a highly adaptive AM for handling multiple dialects simultaneously. The experimental results on large scale speech datasets show that the proposed AM outperforms all the previous ones, reducing word error rates (WERs) by 8.11% relative compared to a single all-dialects AM and by 7.31% relative compared to dialect-specific AMs.
  arXiv  Detail & Related papers  (2022-05-06T06:07:09Z)
• Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units [56.52704348773307]
  We propose a novel LSTM-based generative speech LM based on linguistic units including syllables and phonemes. With a limited dataset, orders of magnitude smaller than that required by contemporary generative models, our model closely approximates babbling speech. We show the effect of training with auxiliary text LMs, multitask learning objectives, and auxiliary articulatory features.
  arXiv  Detail & Related papers  (2021-10-31T22:48:30Z)
• Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation [127.81351683335143]
  Cross-lingual pretraining requires models to align the lexical- and high-level representations of the two languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language model pretraining with lexical-level information by using type-level cross-lingual subword embeddings.
  arXiv  Detail & Related papers  (2021-03-18T21:17:58Z)
• Multi-timescale Representation Learning in LSTM Language Models [69.98840820213937]
  Language models must capture statistical dependencies between words at timescales ranging from very short to very long. We derived a theory for how the memory gating mechanism in long short-term memory language models can capture power law decay. Experiments showed that LSTM language models trained on natural English text learn to approximate this theoretical distribution.
  arXiv  Detail & Related papers  (2020-09-27T02:13:38Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.