Construction of a general-purpose post-recognition error corrector poses a crucial question: how can we most effectively train a model on a large mixture of domain datasets? The answer would lie in learning dataset-specific features and digesting their knowledge in a single model. Previous methods achieve this by having separate correction language models, resulting in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose a Multi-Task Correction MoE, where we train the experts to become an ``expert'' of speech-to-text, language-to-text and vision-to-text datasets by learning to route each dataset's tokens to its mapped expert. Experiments on the Open ASR Leaderboard show that we explore a new state-of-the-art performance by achieving an average relative 5.0% WER reduction and substantial improvements in BLEU scores for speech and translation tasks. On zero-shot evaluation, NeKo outperforms GPT-3.5 and Claude-Opus with 15.5% to 27.6% relative WER reduction in the Hyporadise benchmark. NeKo performs competitively on grammar and post-OCR correction as a multi-task model.
@article{arxiv.2411.05945,
title = {NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model},
author = {Yen-Ting Lin and Zhehuai Chen and Piotr Zelasko and Zhen Wan and Xuesong Yang and Zih-Ching Chen and Krishna C Puvvada and Szu-Wei Fu and Ke Hu and Jun Wei Chiu and Jagadeesh Balam and Boris Ginsburg and Yu-Chiang Frank Wang and Chao-Han Huck Yang},
journal= {arXiv preprint arXiv:2411.05945},
year = {2025}
}
Comments
ACL 2025 Industry Track. NeKo LMs: https://huggingface.co/nvidia/NeKo-v0-post-correction