Ensemble approaches are commonly used techniques to improving a system by combining multiple model predictions. Additionally these schemes allow the uncertainty, as well as the source of the uncertainty, to be derived for the prediction. Unfortunately these benefits come at a computational and memory cost. To address this problem ensemble distillation (EnD) and more recently ensemble distribution distillation (EnDD) have been proposed that compress the ensemble into a single model, representing either the ensemble average prediction or prediction distribution respectively. This paper examines the application of both these distillation approaches to a sequence prediction task, grammatical error correction (GEC). This is an important application area for language learning tasks as it can yield highly useful feedback to the learner. It is, however, more challenging than the standard tasks investigated for distillation as the prediction of any grammatical correction to a word will be highly dependent on both the input sequence and the generated output history for the word. The performance of both EnD and EnDD are evaluated on both publicly available GEC tasks as well as a spoken language task.
School of Computer Science and Technology（计算机科学与技术学院）；Soochow University（苏州大学）；Institute of Artificial Intelligence（人工智能研究院）
In view of the poor robustness of existing Chinese grammatical error correction models on attack test sets and large model parameters, this paper uses the method of knowledge distillation to compress model parameters and improve the anti-attack ability of the model. In terms of data, the attack test set is constructed by integrating the disturbance into the standard evaluation data set, and the model robustness is evaluated by the attack test set. The experimental results show that the distilled small model can ensure the performance and improve the training speed under the condition of reduci…
RoLegalGEC: Legal Domain Grammatical Error Detection and Correction Dataset for Romanian
National University of Science and Technology POLITEHNICA Bucharest（波兰亚技术大学布加勒斯特分校）；Paris 1 Panthéon-Sorbonne University（巴黎1大学蓬莎博纳大学）；University of Bucharest（布加勒斯特大学）
University of Cambridge（剑桥大学）；The ALTA Institute（ALTA研究所）；Imperial College London（帝国理工学院）；King’s College London（伦敦国王学院）
We extend a current sequence-tagging approach to Grammatical Error Correction (GEC) by introducing specialised tags for spelling correction and morphological inflection using the SymSpell and LemmInflect algorithms. Our approach improves generalisation: the proposed new tagset allows a smaller number of tags to correct a larger range of errors. Our results show a performance improvement both overall and in the targeted error categories. We further show that ensembles trained with our new tagset outperform those trained with the baseline tagset on the public BEA benchmark.
In this paper, we present a simple and efficient GEC sequence tagger using a Transformer encoder. Our system is pre-trained on synthetic data and then fine-tuned in two stages: first on errorful corpora, and second on a combination of errorful and error-free parallel corpora. We design custom token-level transformations to map input tokens to target corrections. Our best single-model/ensemble GEC tagger achieves an $F_{0.5}$ of 65.3/66.5 on CoNLL-2014 (test) and $F_{0.5}$ of 72.4/73.6 on BEA-2019 (test). Its inference speed is up to 10 times as fast as a Transformer-based seq2seq GEC system. T…
In this paper, we investigate improvements to the GEC sequence tagging architecture with a focus on ensembling of recent cutting-edge Transformer-based encoders in Large configurations. We encourage ensembling models by majority votes on span-level edits because this approach is tolerant to the model architecture and vocabulary size. Our best ensemble achieves a new SOTA result with an $F_{0.5}$ score of 76.05 on BEA-2019 (test), even without pre-training on synthetic datasets. In addition, we perform knowledge distillation with a trained ensemble to generate new synthetic training datasets, "…
LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction
Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology（哈尔滨工业大学社会计算与信息检索研究中心）；State Key Laboratory of Cognitive Intelligence, iFLYTEK Research（讯飞研究院认知智能国家重点实验室）
Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study
Computational Approaches to Modeling Language Lab（语言建模计算方法实验室）；New York University Abu Dhabi（纽约大学阿布扎克分校）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Multi-head Sequence Tagging Model for Grammatical Error Correction
University of Technology and Applied Sciences（科技与应用科学大学）；National University of Defense Technology（国防科技大学）；CVTE Research（视源股份研究院）；Dalian University of Technology（大连理工大学）
This paper contributes a new State Of The Art (SOTA) for Semantic Textual Similarity (STS). We compare and combine a number of recently proposed sentence embedding methods for STS, and propose a novel and simple ensemble knowledge distillation scheme that improves on previous approaches. Our experiments demonstrate that a model trained to learn the average embedding space from multiple ensemble students outperforms all the other individual models with high robustness. Utilizing our distillation method in combination with previous methods, we significantly improve on the SOTA unsupervised STS, …
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are usually learned on the same labeled data, and their predictions have high correlations with groudtruth labels. Thus, they cannot provide sufficient knowledge complementary to task labels for student teaching. Distilling on unseen unlabeled data has the potential to enhance the knowledge transfer from the teachers to the student. In this paper, we propose a uni…
Ensemble Distillation for Unsupervised Constituency Parsing
University of Alberta（阿尔伯塔大学）；Borealis AI；Ingenuity Labs Research Institute, Queen’s University（英吉利蒂实验室研究所（女王大学））；McGill University（麦吉尔大学）；Quebec Artificial Intelligence Institute (MILA)（魁北克人工智能研究所（MILA））
This paper describes our system at NLPTEA-2020 Task: Chinese Grammatical Error Diagnosis (CGED). The goal of CGED is to diagnose four types of grammatical errors: word selection (S), redundant words (R), missing words (M), and disordered words (W). The automatic CGED system contains two parts including error detection and error correction and our system is designed to solve the error detection problem. Our system is built on three models: 1) a BERT-based model leveraging syntactic information; 2) a BERT-based model leveraging contextual embeddings; 3) a lexicon-based graph neural network lever…
Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks. Recent studies on adapting BERT to new tasks mainly focus on modifying the model structure, re-designing the pre-train tasks, and leveraging external data and knowledge. The fine-tuning strategy itself has yet to be fully explored. In this paper, we improve the fine-tuning of BERT with two effective mechanisms: self-ensemble and self-distillation. The experiments on text classification and natural language inference tasks show our proposed methods c…
University of Maryland（马里兰大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Modern neural networks do not always produce well-calibrated predictions, even when trained with a proper scoring function such as cross-entropy. In classification settings, simple methods such as isotonic regression or temperature scaling may be used in conjunction with a held-out dataset to calibrate model outputs. However, extending these methods to structured prediction is not always straightforward or effective; furthermore, a held-out calibration set may not always be available. In this paper, we study ensemble distillation as a general framework for producing well-calibrated structured …
IBM Research AI（IBM研究院人工智能部门）；IBM Research - Ireland（IBM研究院爱尔兰分院）
AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning. Self-learning techniques have also played a role in pushing performance forward. However, for most recent high performant parsers, the effect of self-learning and silver data augmentation seems to be fading. In this paper we propose to overcome this diminishing returns of silver data by combining Smatch-based ensembling techniques with ensemble distillation. In an extensive experimental setup, we push single model …
IBM T.J. Watson Research Center（IBM T.J. Watson 研究中心）
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 smaller model speeds up this process. We demonstrate how to transfer the translation quality of an ensemble and an oracle BLEU teacher network into a single NMT system. Further, we present translation improvements from a teacher network that has the same architecture and dimensions of the student network. As the training of the student model is still expensive…
Carnegie Mellon University（卡内基梅隆大学）；Pompeu Fabra University（庞培法布拉大学）；University of Washington（华盛顿大学）；Google DeepMind（谷歌DeepMind）
We introduce two first-order graph-based dependency parsers achieving a new state of the art. The first is a consensus parser built from an ensemble of independently trained greedy LSTM transition-based parsers with different random initializations. We cast this approach as minimum Bayes risk decoding (under the Hamming cost) and argue that weaker consensus within the ensemble is a useful signal of difficulty or ambiguity. The second parser is a "distillation" of the ensemble into a single model. We train the distillation parser using a structured hinge loss objective with a novel cost that in…
National University of Defense Technology（中国人民解放军国防科技大学）；Microsoft Research Asia（微软亚洲研究院）
Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also vulnerable to adversarial attacks. This paper tackles these problems by leveraging knowledge distillation, which aims to transfer knowledge from an ensemble model to a single model. We first demonstrate that vanilla knowledge distillation applied to answer span prediction is effective for reading comprehension systems. We then propose two novel approaches that not on…
Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty
Niels Bohr Institute（尼尔斯·玻尔研究所）；University of Copenhagen（哥本哈根大学）；Departamento de Física Teórica（理论物理系）；Instituto de Física Teórica UAM/CSIC（马德里自治大学/西班牙国家研究委员会理论物理研究所）；Universidad Autónoma de Madrid（马德里自治大学）
Grapheme-to-phoneme (G2P) conversion is an important task in automatic speech recognition and text-to-speech systems. Recently, G2P conversion is viewed as a sequence to sequence task and modeled by RNN or CNN based encoder-decoder framework. However, previous works do not consider the practical issues when deploying G2P model in the production system, such as how to leverage additional unlabeled data to boost the accuracy, as well as reduce model size for online deployment. In this work, we propose token-level ensemble distillation for G2P conversion, which can (1) boost the accuracy by disti…
Microsoft Research（微软研究院）；Microsoft Dynamics 365 AI（微软 Dynamics 365 AI）
This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning can improve model performance, serving an ensemble of large DNNs such as MT-DNN can be prohibitively expensive. Here we apply the knowledge distillation method (Hinton et al., 2015) in the multi-task learning setting. For each task, we train an ensemble of different MT-DNNs (teacher) that outperforms any single model, and then train a single MT-DNN (student…
National Taiwan University（台湾大学）；ASUS Intelligent Cloud Services（华硕智能云服务）
Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble Knowledge Distillation (EKD) on various self-supervised speech models such as HuBERT, RobustHuBERT, and WavLM. We tried two different aggregation techniques, layerwise-average and layerwise-concatenation, to the representations of different teacher models and found that the former was more effective. On top of that, we proposed a multiple prediction head method …
South China University of Technology（华南理工大学）；VoiceAI Technologies Co. Ltd.（声智科技有限公司）
It is well known that a speech recognition system that combines multiple acoustic models trained on the same data significantly outperforms a single-model system. Unfortunately, real time speech recognition using a whole ensemble of models is too computationally expensive. In this paper, we propose to distill the knowledge of essence in an ensemble of models (i.e. the teacher model) to a single model (i.e. the student model) that needs much less computation to deploy. Previously, all the soften outputs of the teacher model are used to optimize the student model. We argue that not all the outpu…
