paper-with-me

Papers

Multi-teacher Distillation for Multilingual Spelling Correction

2023-11-20 · Jingfen Zhang, Xuan Guo, Sravan Bodapati, Christopher Potts

Accurate spelling correction is a critical step in modern search interfaces, especially in an era of mobile devices and speech-to-text interfaces. For services that are deployed around the world, this poses a significant challenge for multilingual NLP: spelling errors need to be caught and corrected in all languages, and even in queries that use multiple languages. In this paper, we tackle this challenge using multi-teacher distillation. On our approach, a monolingual teacher model is trained for each language/locale, and these individual models are distilled into a single multilingual student model intended to serve all languages/locales. In experiments using open-source data as well as user data from a worldwide search service, we show that this leads to highly effective spelling correction models that can meet the tight latency requirements of deployed services.

📄 PDF Abstract BibTeX arXiv:2311.11518

Code (0)

등록된 구현이 없습니다.

Tasks

Multilingual NLPSpeech-to-TextSpelling Correction

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Similar Papers 제목 키워드 기반

GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors

2019-11-28 · LREC 2020 5 · Masato Hagiwara, Masato Mita

The lack of large-scale datasets has been a major hindrance to the development of NLP tasks such as spelling correction and grammatical error correction (GEC). As a complementary new resource for these tasks, we present …

Grammatical Error CorrectionSpelling Correction

Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR

2026-08-04 · Yuan Xie, Jiaqi Song, Xianliang Wang, Ming Lei 외 arxiv

Modern LLM-based ASR systems have established multilingual capability as a standard feature, leveraging large-scale multilingual corpora and LLMs' cross-lingual knowledge to achieve competitive performance across multili…

Reinforcement Learning

The Privileged Students: On the Value of Initialization in Multilingual Knowledge Distillation

2024-06-24 · Haryo Akbarianto Wibowo, Thamar Solorio, Alham Fikri Aji

Knowledge distillation (KD) has proven to be a successful strategy to improve the performance of smaller models in many NLP tasks. However, most of the work in KD only explores monolingual scenarios. In this paper, we in…

Knowledge Distillation

AMTSS: An Adaptive Multi-Teacher Single-Student Knowledge Distillation Framework For Multilingual Language Inference

2023-05-13 · Qianglong Chen, Feng Ji, Feng-Lin Li, Guohai Xu 외

Knowledge distillation is of key importance to launching multilingual pre-trained language models for real applications. To support cost-effective language inference in multilingual settings, we propose AMTSS, an adaptiv…

Knowledge Distillation

Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition

2025-06-10 · Mehedi Hasan Bijoy, Dejan Porjazovski, Tamás Grósz, Mikko Kurimo

Speech Emotion Recognition (SER) is crucial for improving human-computer interaction. Despite strides in monolingual SER, extending them to build a multilingual system remains challenging. Our goal is to train a single m…

Emotion RecognitionKnowledge DistillationSpeech Emotion Recognition