The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding

The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding


We present MT-DNN1, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models. Built upon PyTorch and Transformers, MT-DNN is designed to facilitate rapid customization for a broad spectrum of NLU tasks, using a variety of objectives (classification, regression, structured prediction) and text encoders (e.g., RNNs, BERT, RoBERTa, UniLM). A unique feature of MT-DNN is its built-in support for robust and transferable learning using the adversarial multi-task learning paradigm. To enable efficient production deployment, MT-DNN supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop. We demonstrate the effectiveness of MT-DNN on a wide range of NLU applications across general and biomedical domains. The software and pre-trained models will be publicly available at


1 Introduction

NLP model development has observed a paradigm shift in recent years, due to the success in using pretrained language models to improve a wide range of NLP tasks Peters et al. (2018); Devlin et al. (2018). Unlike the traditional pipeline approach that conducts annotation in stages using primarily supervised learning, the new paradigm features a universal pretraining stage that trains a large neural language model via self-supervision on a large unlabeled text corpus, followed by a fine-tuning step that starts from the pretrained contextual representations and conducts supervised learning for individual tasks. The pretrained language models can effectively model textual variations and distributional similarity. Therefore, they can make subsequent task-specific training more sample efficient and often significantly boost performance in downstream tasks. However, these models are quite large and pose significant challenges to production deployment that has stringent memory or speed requirements. As a result, knowledge distillation has become another key feature in this new learning paradigm. An effective distillation step can often substantially compress a large model for efficient deployment Clark et al. (2019); Tang et al. (2019); Liu et al. (2019a).

In the NLP community, there are several well designed frameworks for research and commercial purposes, including toolkits for providing conventional layered linguistic annotations Manning et al. (2014), platforms for developing novel neural models Gardner et al. (2018) and systems for neural machine translation Ott et al. (2019). However, it is hard to find an existing tool that supports all features in the new paradigm and can be easily customized for new tasks. For example, Wolf et al. (2019) provides a number of popular Transformer-based Vaswani et al. (2017) text encoders in a nice unified interface, but does not offer multi-task learning or adversarial training, state-of-the-art techniques that have been shown to significantly improve performance. Additionally, most public frameworks do not offer knowledge distillation. A notable exception is DistillBERT Sanh et al. (2019), but it provides a standalone compressed model and does not support task-specific model compression that can further improve performance.

We introduce MT-DNN, a comprehensive and easily-configurable open-source toolkit for building robust and transferable natural language understanding models. MT-DNN is built upon PyTorch Paszke et al. (2019) and the popular Transformer-based text-encoder interface Wolf et al. (2019). It supports a large inventory of pretrained models, neural architectures, and NLU tasks, and can be easily customized for new tasks.

A key distinct feature for MT-DNN is that it provides out-of-box adversarial training, multi-task learning, and knowledge distillation. Users can train a set of related tasks jointly to amplify each other. They can also invoke adversarial training Miyato et al. (2018); Jiang et al. (2019), which helps improve model robustness and generalizability. For production deployment where large model size becomes a practical obstacle, users can use MT-DNN to compress the original models into substantially smaller ones, even using a completely different architecture (e.g., compressed BERT or other Transformer-based text encoders into LSTMs Hochreiter and Schmidhuber (1997)). The distillation step can similarly leverage multi-task learning and adversarial training. Users can also conduct pretraining from scratch using the masked language model objective in MT-DNN. Moreover, in the fine-tuning step, users can incorporate this as an auxiliary task on the training text, which has been shown to improve performance. MT-DNN provides a comprehensive list of state-of-the-art pre-trained NLU models, together with step-by-step tutorials for using such models in general and biomedical applications.

2 Design


trim=0.080pt 0.180pt 0.020pt 0.10pt,clip

Figure 1: The workflow of MT-DNN: train a neural language model on a large amount of unlabeled raw text to obtain general contextual representations; then fine-tune the learned contextual representation on downstream tasks, e.g. GLUE Wang et al. (2018); lastly, distill this large model to a lighter one for online deployment. In the later two phrases, we can leverage powerful multi-task learning and adversarial training to further improve performance.

trim=0.00pt 0.010pt 0.0pt 0.0pt,clip

Figure 2: Process of knowledge distillation for MTL. A set of tasks where there is task-specific labeled training data are picked. Then, for each task, an ensemble of different neural nets (teacher) is trained. The teacher is used to generate for each task-specific training sample a set of soft targets. Given the soft targets of the training datasets across multiple tasks, a single MT-DNN (student) shown in Figure 3 is trained using multi-task learning and back propagation, except that if task has a teacher, the task-specific loss is the average of two objective functions, one for the correct targets and the other for the soft targets assigned by the teacher.
Figure 3: Overall System Architecture: The lower layers are shared across all tasks while the top layers are task-specific. The input (either a sentence or a set of sentences) is first represented as a sequence of embedding vectors, one for each word, in . Then the encoder, e.g a Transformer or recurrent neural network (LSTM) model, captures the contextual information for each word and generates the shared contextual embedding vectors in . Finally, for each task, additional task-specific layers generate task-specific representations, followed by operations necessary for classification, similarity scoring, or relevance ranking. In case of adversarial training, we perturb embeddings from the lexicon encoder and then add an extra loss term during the training. Note that for the inference phrase, it does not require perturbations.

MT-DNN is designed for modularity, flexibility, and ease of use. These modules are built upon PyTorch Paszke et al. (2019) and Transformers Wolf et al. (2019), allowing the use of the SOTA pre-trained models, e.g., BERT Devlin et al. (2018), RoBERTa Liu et al. (2019b) and UniLM Dong et al. (2019). The unique attribute of this package is a flexible interface for adversarial multi-task fine-tuning and knowledge distillation, so that researchers and developers can build large SOTA NLU models and then compress them to small ones for online deployment.The overall workflow and system architecture are shown in Figure 1 and Figure 3 respectively.

2.1 Workflow

As shown in Figure 1, starting from the neural language model pre-training, there are three different training configurations by following the directed arrows:

  • Single-task configuration: single-task fine-tuning and single-task knowledge distillation;

  • Multi-task configuration: multi-task fine-tuning and multi-task knowledge distillation;

  • Multi-stage configuration: multi-task fine-tuning, single-task fine tuning and single-task knowledge distillation.

Moreover, all configurations can be additionally equipped with the adversarial training. Each stage of the workflow is described in details as follows.

Neural Language Model Pre-Training Due to the great success of deep contextual representations, such as ELMo Peters et al. (2018), GPT Radford et al. (2018) and BERT Devlin et al. (2018), it is common practice of developing NLU models by first pre-training the underlying neural text representations (text encoders) through massive language modeling which results in superior text representations transferable across multiple NLP tasks. Because of this, there has been an increasing effort to develop better pre-trained text encoders by multiplying either the scale of data Liu et al. (2019b) or the size of model Raffel et al. (2019). Similar to existing codebases Devlin et al. (2018), MT-DNN supports the LM pre-training from scratch with multiple types of objectives, such as masked LM Devlin et al. (2018) and next sentence prediction Devlin et al. (2018).

Moreover, users can leverage the LM pre-training, such as masked LM used by BERT, as an auxiliary task for fine-tuning under the multi-task learning (MTL) framework Sun et al. (2019); Liu et al. (2019).

Fine-tuning Once the text encoder is trained in the pre-training stage, an additional task-specific layer is usually added for fine-tuning based on the downstream task. Besides the existing typical single-task fine-tuning, MT-DNN facilitates a joint fine-tuning with a configurable list of related tasks in a MTL fashion. By encoding task-relatedness and sharing underlying text representations, MTL is a powerful training paradigm that promotes the model generalization ability and results in improved performance Caruana (1997); Liu et al. (2019); Luong et al. (2015); Liu et al. (2015); Ruder (2017); Collobert et al. (2011). Additionally, a two-step fine-tuning stage is also supported to utilize datasets from related tasks, i.e. a single-task fine-tuning following a multi-task fine-tuning. It also supports two popular sampling strategies in MTL training: 1) sampling tasks uniformly Caruana (1997); Liu et al. (2015); 2) sampling tasks based on the size of the dataset Liu et al. (2019). This makes it easy to explore various ways to feed training data to MTL training. Finally, to further improve the model robustness, MT-DNN also offers a recipe to apply adversarial training Madry et al. (2017); Zhu et al. (2019); Jiang et al. (2019) in the fine-tuning stage.

Knowledge Distillation Although contextual text representation models pre-trained with massive text data have led to remarkable progress in NLP, it is computationally prohibitive and inefficient to deploy such models with millions of parameters for real-world applications (e.g. BERT large model has 344 million parameters). Therefore, in order to expedite the NLU model learned in either a single-task or multi-task fashion for deployment, MT-DNN additionally supports the multi-task knowledge distillation Clark et al. (2019); Liu et al. (2019a); Tang et al. (2019); Balan et al. (2015); Ba and Caruana (2014), an extension of Hinton et al. (2015), to compress cumbersome models into lighter ones. The multi-task knowledge distillation process is illustrated in Figure 2. Similar to the fine-tuning stage, adversarial training is available in the knowledge distillation stage.

2.2 Architecture

Lexicon Encoder ():

The input is a sequence of tokens of length . The first token is always a specific token, e.g. [CLS] for BERT Devlin et al. (2018) while <s> for RoBERTa Liu et al. (2019b). If is a pair of sentences , we separate these sentences with special tokens, e.g. [SEP] for BERT and [</s>] for RoBERTa. The lexicon encoder maps into a sequence of input embedding vectors, one for each token, constructed by summing the corresponding word with positional, and optional segment embeddings.

Encoder ():

We support a multi-layer bidirectional Transformer Vaswani et al. (2017) or a LSTM Hochreiter and Schmidhuber (1997) encoder to map the input representation vectors () into a sequence of contextual embedding vectors . This is the shared representation across different tasks. Note that MT-DNN also allows developers to customize their own encoders. For example, one can design an encoder with few Transformer layers (e.g. 3 layers) to distill knowledge from the BERT large model (24 layers), so that they can deploy this small mode online to meet the latency restriction as shown in Figure 2.

Task-Specific Output Layers:

We can incorporate arbitrary natural language tasks, each with its task-specific output layer. For example, we implement the output layers as a neural decoder for a neural ranker for relevance ranking, a logistic regression for text classification, and so on. A multi-step reasoning decoder, SAN Liu et al. (2018a, b) is also provided. Customers can choose from existing task-specific output layer or implement new one by themselves.

3 Application

In this section, we present a comprehensive set of examples to illustrate how to customize MT-DNN for new tasks. We use popular benchmarks from general and biomedical domains, including GLUE Wang et al. (2018), SNLI Bowman et al. (2015), SciTail Khot et al. (2018), SQuAD Rajpurkar et al. (2016), ANLI Nie et al. (2019), and biomedical named entity recognition (NER), relation extraction (RE) and question answering (QA) Lee et al. (2019). To make the experiments reproducible, we make all the configuration files publicly available. We also provide a quick guide for customizing a new task in Jupyter notebooks.

3.1 General Domain Natural Language Understanding Benchmarks

Corpus Task Formulation
 CoLA Acceptability Classification
 SST Sentiment Classification
 MNLI NLI Classification
 RTE NLI Classification
 WNLI NLI Classification
 QQP Paraphrase Classification
 MRPC Paraphrase Classification
 QNLI QA/NLI Classification
 QNLI v1.0 QA/NLI Pairwise Ranking
 STS-B Similarity Regression
 SNLI NLI Classification
 SciTail NLI Classification
 ANLI NLI Classification
 SQuAD MRC Span Classification
Table 1: Summary of the four benchmarks: GLUE, SNLI, SciTail and ANLI.
Acc Acc Acc Acc F1
 BERT 84.5 63.5 91.1 92.9 89.0
 BERT + MTL 85.3 79.1 91.5 93.6 89.2
 BERT + AdvTrain 85.6 71.2 91.6 93.0 91.3
Table 2: Comparison among single task, multi-Task and adversarial training on MNLI, RTE, QNLI, SST and MPRC in GLUE.
Model Dev Test
BERT\textsubscriptLARGE (Nie et al., 2019) 49.3 44.2
RoBERTa\textsubscriptLARGE (Nie et al., 2019) 53.7 49.7
RoBERTa-LARGE + AdvTrain 57.1 57.1
Table 3: Results in terms of accuracy on the ANLI.

GLUE. The General Language Understanding Evaluation (GLUE) benchmark is a collection of nine natural language understanding (NLU) tasks. As shown in Table 1, it includes question answering Rajpurkar et al. (2016), linguistic acceptability Warstadt et al. (2018), sentiment analysis Socher et al. (2013), text similarity Cer et al. (2017), paraphrase detection Dolan and Brockett (2005), and natural language inference (NLI) Dagan et al. (2006); Bar-Haim et al. (2006); Giampiccolo et al. (2007); Bentivogli et al. (2009); Levesque et al. (2012); Williams et al. (2018). The diversity of the tasks makes GLUE very suitable for evaluating the generalization and robustness of NLU models.

SNLI. The Stanford Natural Language Inference (SNLI) dataset contains 570k human annotated sentence pairs, in which the premises are drawn from the captions of the Flickr30 corpus and hypotheses are manually annotated Bowman et al. (2015). This is the most widely used entailment dataset for NLI.

SciTail This is a textual entailment dataset derived from a science question answering (SciQ) dataset Khot et al. (2018). In contrast to other entailment datasets mentioned previously, the hypotheses in SciTail are created from science questions while the corresponding answer candidates and premises come from relevant web sentences retrieved from a large corpus.

ANLI. The Adversarial Natural Language Inference (ANLI, Nie et al. (2019)) is a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure. Particular, the data is selected to be difficult to the state-of-the-art models, including BERT and RoBERTa.

SQuAD. The Stanford Question Answering Dataset (SQuAD) Rajpurkar et al. (2016) contains about 23K passages and 100K questions. The passages come from approximately 500 Wikipedia articles and the questions and answers are obtained by crowdsourcing.

Following Devlin et al. (2018), table 2 compares different training algorithm: 1) BERT denotes a single task fine-tuning; 2) BERT + MTL indicates that it is trained jointly via MTL; at last 3), BERT + AdvTrain represents that a single task fine-tuning with adversarial training. It is obvious that the both MLT and adversarial training helps to obtain a better result. We further test our model on an adversarial natural language inference (ANLI) dataset Nie et al. (2019). Table 3 summarizes the results on ANLI. As Nie et al. (2019), all the dataset of ANLI Nie et al. (2019), MNLI Williams et al. (2018), SNLI Bowman et al. (2015) and FEVER Thorne et al. (2018) are combined as training. RoBERTa-LARGE+AdvTrain obtains the best performance compared with all the strong baselines, demonstrating the advantage of adversarial training.

3.2 Biomedical Natural Language Understating Benchmarks

There has been rising interest in exploring natural language understanding tasks in high-value domains other than newswire and the Web. In our release, we provide MT-DNN customization for three representative biomedical natural language understanding tasks:

Named entity recognition (NER): In biomedical natural language understanding, NER has received greater attention than other tasks and datasets are available for recognizing various biomedical entities such as disease, gene, drug (chemical).

Relation extraction (RE): Relation extraction is more closely related to end applications, but annotation effort is significantly higher compared to NER. Most existing RE tasks focus on binary relations within a short text span such as a sentence of an abstract. Examples include gene-disease or protein-chemical relations.

Question answering (QA): Inspired by interest in QA for the general domain, there has been some effort to create question-answering datasets in biomedicine. Annotation requires domain expertise, so it is significantly harder than in general domain, where it is to produce large-scale datasets by crowdsourcing.

The MT-DNN customization can work with standard or biomedicine-specific pretraining models such as BioBERT, and can be directly applied to biomedical benchmarks Lee et al. (2019).

3.3 Extension


trim=0.00pt 0.010pt 0.0pt 0.00pt,clip

Figure 4: The configuration of SNLI.

We will go though a typical Natural Language Inference task, e.g. SNLI, which is one of the most popular benchmark, showing how to apply our toolkit to a new task. MT-DNN is driven by configuration and command line arguments. Firstly, the SNLI configuration is shown in Figure 4. The configuration defines tasks, model architecture as well as loss functions. We briefly introduce these attributes as follows:

  1. data_format is a required attribute and it denotes that each sample includes two sentences (premise and hypothesis). Please refer the tutorial and API for supported formats.

  2. task_layer_type specifies architecture of the task specific layer. The default is a ”linear layer”.

  3. labels Users can list unique values of labels. The configuration helps to convert back and forth between text labels and numbers during training and evaluation. Without it, MT-DNN assumes the label of prediction are numbers.

  4. metric_meta is the evaluation metric used for validation.

  5. loss is the loss function for SNLI. It also supports other functions, e.g. MSE for regression.

  6. kd_loss is the loss function in the knowledge distillation setting.

  7. adv_loss is the loss function in the adversarial setting.

  8. n_class denotes the number of categories for SNLI.

  9. task_type specifies whether it is a classification task or a regression task.

Once the configuration is provided, one can train the customized model for the task, using any supported pre-trained models as starting point.

MT-DNN is also highly extensible, as shown in Figure 4, loss and task_layer_type point to existing classes in code. Users can write customized classes and plug into MT-DNN. The customized classes could then be used via configuration.

4 Conclusion

Microsoft MT-DNN is an open-source natural language understanding toolkit which facilitates researchers and developers to build customized deep learning models. Its key features are: 1) support for robust and transferable learning using adversarial multi-task learning paradigm; 2) enable knowledge distillation under the multi-task learning setting which can be leveraged to derive lighter models for efficient online deployment. We will extend MT-DNN to support Natural Language Generation tasks, e.g. Question Generation, and incorporate more pre-trained encoders, e.g. T5 Raffel et al. (2019) in future.


  1. The complete name of our toolkit is -DNN (The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding), but we use MT-DNN for sake of simplicity.


  1. Do deep nets really need to be deep?. In Advances in neural information processing systems, pp. 2654–2662. Cited by: §2.1.
  2. Bayesian dark knowledge. In Advances in Neural Information Processing Systems, pp. 3438–3446. Cited by: §2.1.
  3. The second PASCAL recognising textual entailment challenge. In Proceedings of the Second PASCAL Challenges Workshop on Recognising Textual Entailment, Cited by: §3.1.
  4. The fifth pascal recognizing textual entailment challenge. In In Proc Text Analysis Conference (TAC’09, Cited by: §3.1.
  5. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), Cited by: §3.1, §3.1, §3.
  6. Multitask learning. Machine learning 28 (1), pp. 41–75. Cited by: §2.1.
  7. SemEval-2017 task 1: semantic textual similarity-multilingual and cross-lingual focused evaluation. arXiv preprint arXiv:1708.00055. Cited by: §3.1.
  8. Bam! born-again multi-task networks for natural language understanding. arXiv preprint arXiv:1907.04829. Cited by: §1, §2.1.
  9. Natural language processing (almost) from scratch. Journal of machine learning research 12 (Aug), pp. 2493–2537. Cited by: §2.1.
  10. The pascal recognising textual entailment challenge. In Proceedings of the First International Conference on Machine Learning Challenges: Evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment, MLCW’05, Berlin, Heidelberg, pp. 177–190. External Links: ISBN 3-540-33427-0, 978-3-540-33427-9, Link, Document Cited by: §3.1.
  11. Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. Cited by: §1, §2.1, §2.2, §2, §3.1.
  12. Automatically constructing a corpus of sentential paraphrases. In Proceedings of the Third International Workshop on Paraphrasing (IWP2005), Cited by: §3.1.
  13. Unified language model pre-training for natural language understanding and generation. arXiv preprint arXiv:1905.03197. Cited by: §2.
  14. Allennlp: a deep semantic natural language processing platform. arXiv preprint arXiv:1803.07640. Cited by: §1.
  15. The third PASCAL recognizing textual entailment challenge. In Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, Prague, pp. 1–9. External Links: Link Cited by: §3.1.
  16. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531. Cited by: §2.1.
  17. Long short-term memory. Neural computation 9 (8), pp. 1735–1780. Cited by: §1, §2.2.
  18. SMART: robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization. arXiv preprint arXiv:1911.03437. Cited by: §1, §2.1.
  19. SciTail: a textual entailment dataset from science question answering. In AAAI, Cited by: §3.1, §3.
  20. Biobert: pre-trained biomedical language representation model for biomedical text mining. arXiv preprint arXiv:1901.08746. Cited by: §3.2, §3.
  21. The winograd schema challenge. In Thirteenth International Conference on the Principles of Knowledge Representation and Reasoning, Cited by: §3.1.
  22. Stochastic answer networks for natural language inference. arXiv preprint arXiv:1804.07888. Cited by: §2.2.
  23. Representation learning using multi-task deep neural networks for semantic classification and information retrieval. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 912–921. Cited by: §2.1.
  24. Multi-task deep neural networks for natural language understanding. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 4487–4496. External Links: Link Cited by: §2.1, §2.1.
  25. Improving multi-task deep neural networks via knowledge distillation for natural language understanding. arXiv preprint arXiv:1904.09482. Cited by: §1, §2.1.
  26. Stochastic answer networks for machine reading comprehension. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Cited by: §2.2.
  27. Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692. Cited by: §2.1, §2.2, §2.
  28. Multi-task sequence to sequence learning. arXiv preprint arXiv:1511.06114. Cited by: §2.1.
  29. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083. Cited by: §2.1.
  30. The stanford corenlp natural language processing toolkit. In Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations, pp. 55–60. Cited by: §1.
  31. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence 41 (8), pp. 1979–1993. Cited by: §1.
  32. Adversarial nli: a new benchmark for natural language understanding. arXiv preprint arXiv:1910.14599. Cited by: §3.1, §3.1, Table 3, §3.
  33. Fairseq: a fast, extensible toolkit for sequence modeling. arXiv preprint arXiv:1904.01038. Cited by: §1.
  34. PyTorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, pp. 8024–8035. Cited by: §1, §2.
  35. Deep contextualized word representations. arXiv preprint arXiv:1802.05365. Cited by: §1, §2.1.
  36. Language models are unsupervised multitask learners. Cited by: §2.1.
  37. Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683. Cited by: §2.1, §4.
  38. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, pp. 2383–2392. External Links: Link, Document Cited by: §3.1, §3.1, §3.
  39. An overview of multi-task learning in deep neural networks. arXiv preprint arXiv:1706.05098. Cited by: §2.1.
  40. DistilBERT, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108. Cited by: §1.
  41. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 conference on empirical methods in natural language processing, pp. 1631–1642. Cited by: §3.1.
  42. Ernie 2.0: a continual pre-training framework for language understanding. arXiv preprint arXiv:1907.12412. Cited by: §2.1.
  43. Distilling task-specific knowledge from bert into simple neural networks. arXiv preprint arXiv:1903.12136. Cited by: §1, §2.1.
  44. FEVER: a large-scale dataset for fact extraction and verification. arXiv preprint arXiv:1803.05355. Cited by: §3.1.
  45. Attention is all you need. In Advances in neural information processing systems, pp. 5998–6008. Cited by: §1, §2.2.
  46. Glue: a multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461. Cited by: Figure 1, §3.
  47. Neural network acceptability judgments. arXiv preprint arXiv:1805.12471. Cited by: §3.1.
  48. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1112–1122. External Links: Link Cited by: §3.1, §3.1.
  49. HuggingFace’s transformers: state-of-the-art natural language processing. ArXiv abs/1910.03771. Cited by: §1, §1, §2.
  50. FreeLB: enhanced adversarial training for language understanding. arXiv preprint arXiv:1909.11764. Cited by: §2.1.
Comments 0
Request Comment
You are adding the first comment!
How to quickly get a good reply:
  • Give credit where it’s due by listing out the positive aspects of a paper before getting into which changes should be made.
  • Be specific in your critique, and provide supporting evidence with appropriate references to substantiate general statements.
  • Your comment should inspire ideas to flow and help the author improves the paper.

The better we are at sharing our knowledge with each other, the faster we move forward.
The feedback must be of minimum 40 characters and the title a minimum of 5 characters
Add comment
Loading ...
This is a comment super asjknd jkasnjk adsnkj
The feedback must be of minumum 40 characters
The feedback must be of minumum 40 characters

You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test description