Knowledge transfer can boost neural machine translation (NMT), for example, by finetuning a pretrained masked language model (LM). However, it may suffer from the forgetting problem and the structural inconsistency between pretrained LMs and NMT models. Knowledge distillation (KD) may be a potential solution to alleviate these issues, but few studies have investigated language knowledge transfer from pretrained language models to NMT models through KD. In this paper, we propose Pretrained Bidirectional Distillation (PBD) for NMT, which aims to efficiently transfer bidirectional language knowledge from masked language pretraining to NMT models. Its advantages are reflected in efficiency and effectiveness through a globally defined and bidirectional context-aware distillation objective. Bidirectional language knowledge of the entire sequence is transferred to an NMT model concurrently during translation training. Specifically, we propose self-distilled masked language pretraining to obtain the PBD objective. We also design PBD losses to efficiently distill the language knowledge, in the form of token probabilities, to the encoder and decoder of an NMT model using the PBD objective. Extensive experiments reveal that pretrained bidirectional distillation can significantly improve machine translation performance and achieve competitive or even better results than previous pretrain-finetune or unified multilingual translation methods in supervised, unsupervised, and zero-shot scenarios. Empirically, it is concluded that pretrained bidirectional distillation is an effective and efficient method for transferring language knowledge from pretrained language models to NMT models.

Self-attention mechanism has been shown to be an effective approach for capturing global context dependencies in sequence modeling, but it suffers from quadratic complexity in time and memory usage. Due to the sparsity of the attention matrix, much computation is redundant. Therefore, in this paper, we design an efficient Transformer architecture, named Fourier Sparse Attention for Transformer (FSAT), for fast long-range sequence modeling. We provide a brand-new perspective for constructing sparse attention matrix, i.e. making the sparse attention matrix predictable. Two core sub-modules are: (1) A fast Fourier transform based hidden state cross module, which captures and pools L² semantic combinations in 𝒪(Llog L) time complexity. (2) A sparse attention matrix estimation module, which predicts dominant elements of an attention matrix based on the output of the previous hidden state cross module. By reparameterization and gradient truncation, FSAT successfully learned the index of dominant elements. The overall complexity about the sequence length is reduced from 𝒪(L²) to 𝒪(Llog L). Extensive experiments (natural language, vision, and math) show that FSAT remarkably outperforms the standard multi-head attention and its variants in various long-sequence tasks with low computational costs, and achieves new state-of-the-art results on the Long Range Arena benchmark.

This paper describes our system used in the SemEval-2021 Task4 Reading Comprehension of Abstract Meaning, achieving 1st for subtask 1 and 2nd for subtask 2 on the leaderboard. We propose an ensemble of ELECTRA-based models with task-adaptive pretraining and a multi-head attention multiple-choice classifier on top of the pre-trained model. The main contributions of our system are 1) revealing the performance discrepancy of different transformer-based pretraining models on the downstream task, 2) presentation of an efficient method to generate large task-adaptive corpora for pretraining. We also investigated several pretraining strategies and contrastive learning objectives. Our system achieves a test accuracy of 95.11 and 94.89 on subtask 1 and subtask 2 respectively.

This paper describes the LIT Team’s submission to the IWSLT2020 open domain translation task, focusing primarily on Japanese-to-Chinese translation direction. Our system is based on the organizers’ baseline system, but we do more works on improving the Transform baseline system by elaborate data pre-processing. We manage to obtain significant improvements, and this paper aims to share some data processing experiences in this translation task. Large-scale back-translation on monolingual corpus is also investigated. In addition, we also try shared and exclusive word embeddings, compare different granularity of tokens like sub-word level. Our Japanese-to-Chinese translation system achieves a performance of BLEU=34.0 and ranks 2nd among all participating systems.

Suggestion mining task aims to extract tips, advice, and recommendations from unstructured text. The task includes many challenges, such as class imbalance, figurative expressions, context dependency, and long and complex sentences. This paper gives a detailed system description of our submission in SemEval 2019 Task 9 Subtask A. We transfer Self-Attention Network (SAN), a successful model in machine reading comprehension field, into this task. Our model concentrates on modeling long-term dependency which is indispensable to parse long and complex sentences. Besides, we also adopt techniques, such as contextualized embedding, back-translation, and auxiliary loss, to augment the system. Our model achieves a performance of F1=76.3, and rank 4th among 34 participating systems. Further ablation study shows that the techniques used in our system are beneficial to the performance.

Multi-passage reading comprehension requires the ability to combine cross-passage information and reason over multiple passages to infer the answer. In this paper, we introduce the Dynamic Self-attention Network (DynSAN) for multi-passage reading comprehension task, which processes cross-passage information at token-level and meanwhile avoids substantial computational costs. The core module of the dynamic self-attention is a proposed gated token selection mechanism, which dynamically selects important tokens from a sequence. These chosen tokens will attend to each other via a self-attention mechanism to model long-range dependencies. Besides, convolutional layers are combined with the dynamic self-attention to enhance the model’s capacity of extracting local semantic. The experimental results show that the proposed DynSAN achieves new state-of-the-art performance on the SearchQA, Quasar-T and WikiHop datasets. Further ablation study also validates the effectiveness of our model components.

Most models for learning word embeddings are trained based on the context information of words, more precisely first order co-occurrence relations. In this paper, a metric is designed to estimate second order co-occurrence relations based on context overlap. The estimated values are further used as the augmented data to enhance the learning of word embeddings by joint training with existing neural word embedding models. Experimental results show that better word vectors can be obtained for word similarity tasks and some downstream NLP tasks by the enhanced approach.