Distilling the Knowledge of Romanian BERTs Using Multiple Teachers (2022.lrec-1)
Copied to clipboard
Andrei-Marius Avram, Darius Catrina, Dumitru-Clementin Cercel, Mihai Dascalu, Traian Rebedea, Vasile Pais, Dan Tufis
| Challenge: | Existing approaches to train pre-trained language models focus on the English language, thus widening the gap when considering low-resource languages. |
| Approach: | They propose three versions of distilled BERT models for the Romanian language . they argue that the models offer performance comparable to their teachers . |
| Outcome: | The proposed models perform comparable to their teachers, while being twice as fast on a GPU and 35% smaller. |
Similar Papers
RoBERT – A Romanian BERT Model (2020.coling-main)
Copied to clipboard
| Challenge: | Existing pre-trained language models learn contextualized representations by using unlabeled text data and obtain state of the art results on a multitude of NLP tasks. |
| Approach: | They propose a pre-trained BERT model for Romanian language processing and compare it with multi-lingual models on seven Romanian specific NLP tasks. |
| Outcome: | The proposed model outperforms multi-lingual models on seven Romanian specific NLP tasks on sentiment analysis, dialect and cross-dialect topic identification, and diacritics restoration. |
The birth of Romanian BERT (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale pretrained language models are available in high-resource languages, in particular English, or as multilingual models that compromise performance on individual languages for coverage. |
| Approach: | They propose to use a Romanian transformer-based language model to pretrained a large text corpus to evaluate the model. |
| Outcome: | The proposed model is open-source and can be used in production. |
Patient Knowledge Distillation for BERT Model Compression (D19-1)
Copied to clipboard
| Challenge: | Pre-trained language models such as BERT have proven to be highly effective for natural language processing tasks, but the high demand for computing resources hinders their application in practice. |
| Approach: | They propose to compress an original large model (teacher) into an equally-effective lightweight shallow network (student) Empirically, this translates into improved results on multiple NLP tasks with a significant gain in training efficiency, without sacrificing model accuracy. |
| Outcome: | The proposed model reduces the computational cost of training models using the teacher model into a lightweight shallow network. |
Distilling Knowledge Learned in BERT for Text Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Large-scale pre-trained language models such as BERT have revolutionized the state of the art in many language understanding tasks. |
| Approach: | They propose a conditional masked language modeling approach to fine tune BERT on target generation tasks by imposing global sequence-level supervision on conventional Seq2Seq models. |
| Outcome: | The proposed model outperforms strong Transformer baselines on multiple language generation tasks such as machine translation and text summarization. |
Extremely Small BERT Models from Mixed-Vocabulary Training (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation methods cannot be directly applied to train student models with reduced vocabulary and embedding dimensions. |
| Approach: | They propose a method to align teacher and student embeddings via mixed-vocabulary training. |
| Outcome: | The proposed method compresses BERT-LARGE to a task-agnostic model with smaller vocabulary and hidden dimensions, which is an order of magnitude smaller than other distilled models. |
Enhancing Task-Specific Distillation in Small Data Regimes through Language Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Large-scale pretrained language models have led to significant improvements in Natural Language Processing, but they come at the cost of high computational and storage requirements. |
| Approach: | They propose to distill knowledge from larger models to smaller ones through pseudo-labels on task-specific datasets. |
| Outcome: | The proposed approach improves on the SST-2, MRPC, YELP-2, and TREC-6 datasets. |
TinyBERT: Distilling BERT for Natural Language Understanding (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models are computationally expensive and difficult to efficiently execute on resource-restricted devices. |
| Approach: | They propose a Transformer distillation method that performs Transformer distillations at pre-training and task-specific learning stages. |
| Outcome: | The proposed method accelerates inference and reduces model size while maintaining accuracy. |
Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings (D19-61)
Copied to clipboard
| Challenge: | Recent research points to knowledge distillation as a potential solution for NLU tasks. |
| Approach: | They propose a training approach that distills large finetuned LMs into a small network using unlabeled training examples. |
| Outcome: | The proposed approach outperforms BERT training approaches while using 300 times fewer parameters. |
Natural Language Generation for Effective Knowledge Distillation (D19-61)
Copied to clipboard
| Challenge: | Knowledge distillation can transfer knowledge from deep language representation models to shallow word embedding-based neural networks. |
| Approach: | They propose to build an unlabeled transfer dataset to enable effective knowledge transfer . they hypothesize that this principled, general approach outperforms rule-based techniques . |
| Outcome: | The proposed method outperforms OpenAI GPT on four datasets in sentiment classification, sentence similarity, and linguistic acceptability. |
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have been proposed and applied to many NLP tasks, yielding state-of-the-art performance, but high storage and computational costs obstruct them to be effectively deployed on resource-constrained devices and real-time applications. |
| Approach: | They propose a BERT distillation method which allows each intermediate student layer to learn from any intermediate teacher layers. |
| Outcome: | The proposed method can learn from different teacher layers adaptively for different NLP tasks. |