Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher’s soft label as in conventional KD, researchers find that the rich information contained in the hidden layers of BERT is conducive to the student’s performance. To better exploit the hidden knowledge, a common practice is to force the student to deeply mimic the teacher’s hidden states of all the tokens in a layer-wise manner. In this paper, however, we observe that although distilling the teacher’s hidden state knowledge (HSK) is helpful, the performance gain (marginal utility) diminishes quickly as more HSK is distilled. To understand this effect, we conduct a series of analysis. Specifically, we divide the HSK of BERT into three dimensions, namely depth, length and width. We first investigate a variety of strategies to extract crucial knowledge for each single dimension and then jointly compress the three dimensions. In this way, we show that 1) the student’s performance can be improved by extracting and distilling the crucial HSK, and 2) using a tiny fraction of HSK can achieve the same performance as extensive HSK distillation. Based on the second finding, we further propose an efficient KD paradigm to compress BERT, which does not require loading the teacher during the training of student. For two kinds of student models and computing devices, the proposed KD paradigm gives rise to training speedup of 2.7x 3.4x.

The Neural Machine Translation (NMT) model is essentially a joint language model conditioned on both the source sentence and partial translation. Therefore, the NMT model naturally involves the mechanism of the Language Model (LM) that predicts the next token only based on partial translation. Despite its success, NMT still suffers from the hallucination problem, generating fluent but inadequate translations. The main reason is that NMT pays excessive attention to the partial translation while neglecting the source sentence to some extent, namely overconfidence of the LM. Accordingly, we define the Margin between the NMT and the LM, calculated by subtracting the predicted probability of the LM from that of the NMT model for each token. The Margin is negatively correlated to the overconfidence degree of the LM. Based on the property, we propose a Margin-based Token-level Objective (MTO) and a Margin-based Sentence-level Objective (MSO) to maximize the Margin for preventing the LM from being overconfident. Experiments on WMT14 English-to-German, WMT19 Chinese-to-English, and WMT14 English-to-French translation tasks demonstrate the effectiveness of our approach, with 1.36, 1.50, and 0.63 BLEU improvements, respectively, compared to the Transformer baseline. The human evaluation further verifies that our approaches improve translation adequacy as well as fluency.

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model’s performance by transferring teacher model’s knowledge on each training sample. However, previous work rarely discusses the different impacts and connections among these samples, which serve as the medium for transferring teacher knowledge. In this paper, we design a novel protocol that can effectively analyze the different impacts of samples by comparing various samples’ partitions. Based on above protocol, we conduct extensive experiments and find that the teacher’s knowledge is not the more, the better. Knowledge over specific samples may even hurt the whole performance of knowledge distillation. Finally, to address these issues, we propose two simple yet effective strategies, i.e., batch-level and global-level selections, to pick suitable samples for distillation. We evaluate our approaches on two large-scale machine translation tasks, WMT’14 English-German and WMT’19 Chinese-English. Experimental results show that our approaches yield up to +1.28 and +0.89 BLEU points improvements over the Transformer baseline, respectively.

We propose UPSA, a novel approach that accomplishes Unsupervised Paraphrasing by Simulated Annealing. We model paraphrase generation as an optimization problem and propose a sophisticated objective function, involving semantic similarity, expression diversity, and language fluency of paraphrases. UPSA searches the sentence space towards this objective by performing a sequence of local editing. We evaluate our approach on various datasets, namely, Quora, Wikianswers, MSCOCO, and Twitter. Extensive results show that UPSA achieves the state-of-the-art performance compared with previous unsupervised methods in terms of both automatic and human evaluations. Further, our approach outperforms most existing domain-adapted supervised models, showing the generalizability of UPSA.

Generating a vivid, novel, and diverse essay with only several given topic words is a promising task of natural language generation. Previous work in this task exists two challenging problems : neglect of sentiment beneath the text and insufficient utilization of topic-related knowledge. Therefore, we propose a novel Sentiment Controllable topic-to- essay generator with a Topic Knowledge Graph enhanced decoder, named SCTKG, which is based on the conditional variational auto-encoder (CVAE) framework. We firstly inject the sentiment information into the generator for controlling sentiment for each sentence, which leads to various generated essays. Then we design a Topic Knowledge Graph enhanced decoder. Unlike existing models that use knowledge entities separately, our model treats knowledge graph as a whole and encodes more structured, connected semantic information in the graph to generate a more relevant essay. Experimental results show that our SCTKG can generate sentiment controllable essays and outperform the state-of-the-art approach in terms of topic relevance, fluency, and diversity on both automatic and human evaluation.

Document Grounded Conversations is a task to generate dialogue responses when chatting about the content of a given document. Obviously, document knowledge plays a critical role in Document Grounded Conversations, while existing dialogue models do not exploit this kind of knowledge effectively enough. In this paper, we propose a novel Transformer-based architecture for multi-turn document grounded conversations. In particular, we devise an Incremental Transformer to encode multi-turn utterances along with knowledge in related documents. Motivated by the human cognitive process, we design a two-pass decoder (Deliberation Decoder) to improve context coherence and knowledge correctness. Our empirical study on a real-world Document Grounded Dataset proves that responses generated by our model significantly outperform competitive baselines on both context coherence and knowledge relevance.

Small perturbations in the input can severely distort intermediate representations and thus impact translation quality of neural machine translation (NMT) models. In this paper, we propose to improve the robustness of NMT models with adversarial stability training. The basic idea is to make both the encoder and decoder in NMT models robust against input perturbations by enabling them to behave similarly for the original input and its perturbed counterpart. Experimental results on Chinese-English, English-German and English-French translation tasks show that our approaches can not only achieve significant improvements over strong NMT systems but also improve the robustness of NMT models.