English
Related papers

Related papers: Ensembling and Knowledge Distilling of Large Seque…

200 papers

Model ensembling is a technique to combine the predicted distributions of two or more models, often leading to improved robustness and performance. For ensembling in text generation, the next token's probability distribution is derived from…

Computation and Language · Computer Science 2025-03-03 Rachel Wicks , Kartik Ravisankar , Xinchen Yang , Philipp Koehn , Matt Post

Driven by encouraging results on a wide range of tasks, the field of NLP is experiencing an accelerated race to develop bigger language models. This race for bigger models has also underscored the need to continue the pursuit of practical…

Computation and Language · Computer Science 2023-02-14 Marco Farina , Duccio Pappadopulo , Anant Gupta , Leslie Huang , Ozan İrsoy , Thamar Solorio

An increasing number of datasets sharing similar domains for semantic segmentation have been published over the past few years. But despite the growing amount of overall data, it is still difficult to train bigger and better models due to…

Computer Vision and Pattern Recognition · Computer Science 2025-02-27 Anton Backhaus , Thorsten Luettel , Mirko Maehlisch

Augmentation and knowledge distillation (KD) are well-established techniques employed in audio classification tasks, aimed at enhancing performance and reducing model sizes on the widely recognized Audioset (AS) benchmark. Although both…

Sound · Computer Science 2023-09-11 Heinrich Dinkel , Yongqing Wang , Zhiyong Yan , Junbo Zhang , Yujun Wang

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language understanding tasks. However, the size and memory footprint…

Computation and Language · Computer Science 2020-02-04 Luke Melas-Kyriazi , George Han , Celine Liang

Edit-based approaches have recently shown promising results on multiple monolingual sequence transduction tasks. In contrast to conventional sequence-to-sequence (Seq2Seq) models, which learn to generate text from scratch as they are…

Computation and Language · Computer Science 2022-05-11 Kostiantyn Omelianchuk , Vipul Raheja , Oleksandr Skurzhanskyi

Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a…

Computation and Language · Computer Science 2017-08-09 Markus Freitag , Yaser Al-Onaizan , Baskaran Sankaran

Synthetic data generation is widely known to boost the accuracy of neural grammatical error correction (GEC) systems, but existing methods often lack diversity or are too simplistic to generate the broad range of grammatical errors made by…

Computation and Language · Computer Science 2021-05-28 Felix Stahlberg , Shankar Kumar

Large-scale language-agnostic sentence embedding models such as LaBSE (Feng et al., 2022) obtain state-of-the-art performance for parallel sentence alignment. However, these large-scale models can suffer from inference speed and computation…

Computation and Language · Computer Science 2023-12-27 Zhuoyuan Mao , Tetsuji Nakagawa

This paper introduces a new methodology for using LLM-based systems for accurate and efficient semantic tagging of UN Security Council resolutions. The main goal is to leverage LLM performance variability to build ensemble systems for data…

Computation and Language · Computer Science 2026-03-09 Hussein Ghaly

The recent studies of knowledge distillation have discovered that ensembling the "dark knowledge" from multiple teachers or students contributes to creating better soft targets for training, but at the cost of significantly more…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Yixiao Ge , Xiao Zhang , Ching Lam Choi , Ka Chun Cheung , Peipei Zhao , Feng Zhu , Xiaogang Wang , Rui Zhao , Hongsheng Li

We describe an approach to Grammatical Error Correction (GEC) that is effective at making use of models trained on large amounts of weakly supervised bitext. We train the Transformer sequence-to-sequence model on 4B tokens of Wikipedia…

Computation and Language · Computer Science 2018-11-06 Jared Lichtarge , Christopher Alberti , Shankar Kumar , Noam Shazeer , Niki Parmar

Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate cross-lingual transfer of multilingual pretrained models…

Computation and Language · Computer Science 2021-09-13 Xinyi Wang , Yulia Tsvetkov , Sebastian Ruder , Graham Neubig

Quality estimation models have been developed to assess the corrections made by grammatical error correction (GEC) models when the reference or gold-standard corrections are not available. An ideal quality estimator can be utilized to…

Computation and Language · Computer Science 2023-10-24 Muhammad Reza Qorib , Hwee Tou Ng

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Computation and Language · Computer Science 2025-09-09 Manuel Frank , Haithem Afli

Grammatical error correction (GEC) is one of the areas in natural language processing in which purely neural models have not yet superseded more traditional symbolic models. Hybrid systems combining phrase-based statistical machine…

Computation and Language · Computer Science 2019-04-08 Felix Stahlberg , Christopher Bryant , Bill Byrne

Most contemporary music tagging systems rely on large volumes of annotated data. As an alternative, we investigate the extent to which synthetically generated music excerpts can improve tagging systems when only small annotated collections…

Sound · Computer Science 2024-07-03 Nadine Kroher , Steven Manangu , Aggelos Pikrakis

Test-Time adaptation (TTA) aims to enhance model robustness against distribution shifts through rapid model adaptation during inference. While existing TTA methods often rely on entropy-based unsupervised training and achieve promising…

Computer Vision and Pattern Recognition · Computer Science 2025-05-08 Zixuan Hu , Yichun Hu , Ling-Yu Duan

The pre-trained speech encoder wav2vec 2.0 performs very well on various spoken language understanding (SLU) tasks. However, on many tasks, it trails behind text encoders with textual input. To improve the understanding capability of SLU…

Computation and Language · Computer Science 2023-05-23 Yi Xuan Tan , Navonil Majumder , Soujanya Poria

General-purpose Large Language Models (LLMs) are frequently fine-tuned through supervised fine-tuning (SFT) to enhance performance in specific domains. Better results can be achieved by distilling the chain-of-thought of a larger model at…

Machine Learning · Computer Science 2026-03-24 Andrey Goncharov , Daniil Vyazhev , Petr Sychev , Edvard Khalafyan , Alexey Zaytsev