Challenge: a multilingual spelling correction model is needed to meet the tight latency requirements of multilingual NLP . a monolingual teacher model is trained for each language/locale, and individual models are distilled into a single student model .
Approach: They propose a multilingual approach to spelling correction using multi-teacher distillation . they train a monolingual teacher model for each language and distill them into a single model .
Outcome: The proposed model can meet the tight latency requirements of deployed services.

Similar Papers

Distilling Multilingual Transformers into CNNs for Scalable Intent Classification (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing multilingual models for voice assistants are limited by their prohibitive inference time and limited performance.
Approach: They propose to distill and deploy multilingual Transformer models for voice assistants using a teacher-student framework that uses teacher-trained models to supervise student model training.
Outcome: The proposed model outperforms a teacher model trained on unlabelled data and achieves equivalent performance.
LeSpell - A Multi-Lingual Benchmark Corpus of Spelling Errors to Develop Spellchecking Methods for Learner Language (2022.lrec-1)

Copied to clipboard

Challenge: Existing spellcheckers do not work well with learner data.
Approach: They propose a multi-lingual evaluation data set of spelling mistakes in context that is highly customizable for the DKPro architecture.
Outcome: The proposed spellchecker improves performance in many settings and can be customized to meet learners' needs.
Training a Better Chinese Spelling Correction Model via Prior-knowledge Guided Teacher (2024.findings-acl)

Copied to clipboard

Challenge: Chinese Spelling Correction models are prone to over-correct and poor generalization for error patterns outside the standard distribution.
Approach: They propose a teacher network guided by prior knowledge for distillation learning of CSC models.
Outcome: The proposed method significantly enhances the CSC model’s language modeling capabilities, crucial for minimizing over-correction.
XtremeDistil: Multi-stage Distillation for Massive Multilingual Models (2020.acl-main)

Copied to clipboard

Challenge: Existing work on pre-trained language models focuses on reducing the size of these models into shallow ones.
Approach: They propose a knowledge distillation technique that leverages teacher internal representations to reduce the size of pre-trained language models.
Outcome: The proposed method outperforms previous methods in multilingual Named Entity Recognition (NER) it reduces the size of teacher models by 35x while retaining 95% of its F1 score.
Multilingual Arbitration: Optimizing Data Pools to Accelerate Multilingual Progress (2025.acl-long)

Copied to clipboard

Challenge: Synthetic data generation relies on a single oracle teacher model, which can lead to model collapse and bias propagation.
Approach: They propose a multilingual arbitration approach that exploits performance variations among multiple models for each language.
Outcome: The proposed approach surpasses single-teacher distillation with 80% win rates over proprietary and open-weight models with the largest improvements in low-resource languages.
Multilingual AMR Parsing with Noisy Knowledge Distillation (2021.findings-emnlp)

Copied to clipboard

Challenge: Abstract Meaning Representation (AMR) parsing is a broad-coverage semantic formalism that encodes the meaning of a sentence as a rooted, directed, and labeled graph.
Approach: They propose to use existing English parser to learn and improve multilingual AMR parsers . their results show that noisy input and precise output are key to successful distillation .
Outcome: The proposed model outperforms the current state-of-the-art English-only parser on four different languages.
BAM! Born-Again Multi-Task Networks for Natural Language Understanding (P19-1)

Copied to clipboard

Challenge: Existing methods to train multi-task neural networks outperform or even match their single-task counterparts are difficult to implement.
Approach: They propose a method that uses knowledge distillation to train multi-task neural networks that outperform or even match their single-task counterparts.
Outcome: The proposed method outperforms or matches single-task neural networks on the GLUE benchmark.
One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification (2022.coling-1)

Copied to clipboard

Challenge: Existing knowledge distillation models require large computing resources and long inference time to perform.
Approach: They propose a one-teacher and multiple-student knowledge distillation approach to distill a deep pre-trained teacher model into multiple shallow student models with ensemble learning.
Outcome: The proposed method achieves better results with fewer parameters and extremely high speedup ratios on three sentiment classification tasks.
Beyond the Mode: Sequence-Level Distillation of Multilingual Translation Models for Low-Resource Language Pairs (2025.findings-naacl)

Copied to clipboard

Challenge: Existing multilingual pre-trained models for low-resource languages have outperformed those trained from scratch for low resources due to high hardware requirements.
Approach: They propose to use beam search to decode the whole output distribution of the teacher to improve student learning.
Outcome: The proposed methods improve student model performance and reduce gender bias amplification common to beam search based methods.
Improving Zero-Shot Multilingual Text Generation via Iterative Distillation (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to generalize multilingual dialogue systems to multilingual settings often make assumptions about data availability.
Approach: They propose to transfer inductive biases for target languages learned by pretrained teacher models to student models via sequence-level knowledge distillation.
Outcome: The proposed method performs well on the multiATIS++ benchmark, and is comparable to human annotations in both slot F1 and intent accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations