Xu Tan


2022

pdf bib
A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation
Kexun Zhang | Rui Wang | Xu Tan | Junliang Guo | Yi Ren | Tao Qin | Tie-Yan Liu
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the “multi-modality problem”, including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenges to the standard cross entropy (XE) loss in NAT and is understudied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to using different loss functions for different kinds of syntactic multi-modality.

pdf bib
ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation
Chang Liu | Xu Tan | Chongyang Tao | Zhenxin Fu | Dongyan Zhao | Tie-Yan Liu | Rui Yan
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Typical generative dialogue models utilize the dialogue history to generate the response. However, since one dialogue utterance can often be appropriately answered by multiple distinct responses, generating a desired response solely based on the historical information is not easy. Intuitively, if the chatbot can foresee in advance what the user would talk about (i.e., the dialogue future) after receiving its response, it could possibly provide a more informative response. Accordingly, we propose a novel dialogue generation framework named ProphetChat that utilizes the simulated dialogue futures in the inference phase to enhance response generation. To enable the chatbot to foresee the dialogue future, we design a beam-search-like roll-out strategy for dialogue future simulation using a typical dialogue generation model and a dialogue selector. With the simulated futures, we then utilize the ensemble of a history-to-response generator and a future-to-response generator to jointly generate a more informative response. Experiments on two popular open-domain dialogue datasets demonstrate that ProphetChat can generate better responses over strong baselines, which validates the advantages of incorporating the simulated dialogue futures.

pdf bib
Revisiting Over-Smoothness in Text to Speech
Yi Ren | Xu Tan | Tao Qin | Zhou Zhao | Tie-Yan Liu
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Non-autoregressive text to speech (NAR-TTS) models have attracted much attention from both academia and industry due to their fast generation speed. One limitation of NAR-TTS models is that they ignore the correlation in time and frequency domains while generating speech mel-spectrograms, and thus cause blurry and over-smoothed results. In this work, we revisit this over-smoothing problem from a novel perspective: the degree of over-smoothness is determined by the gap between the complexity of data distributions and the capability of modeling methods. Both simplifying data distributions and improving modeling methods can alleviate the problem. Accordingly, we first study methods reducing the complexity of data distributions. Then we conduct a comprehensive study on NAR-TTS models that use some advanced modeling methods. Based on these studies, we find that 1) methods that provide additional condition inputs reduce the complexity of data distributions to model, thus alleviating the over-smoothing problem and achieving better voice quality. 2) Among advanced modeling methods, Laplacian mixture loss performs well at modeling multimodal distributions and enjoys its simplicity, while GAN and Glow achieve the best voice quality while suffering from increased training or model complexity. 3) The two categories of methods can be combined to further alleviate the over-smoothness and improve the voice quality. 4) Our experiments on the multi-speaker dataset lead to similar conclusions as above and providing more variance information can reduce the difficulty of modeling the target data distribution and alleviate the requirements for model capacity.

pdf bib
Non-Autoregressive Sequence Generation
Jiatao Gu | Xu Tan
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts

Non-autoregressive sequence generation (NAR) attempts to generate the entire or partial output sequences in parallel to speed up the generation process and avoid potential issues (e.g., label bias, exposure bias) in autoregressive generation. While it has received much research attention and has been applied in many sequence generation tasks in natural language and speech, naive NAR models still face many challenges to close the performance gap between state-of-the-art autoregressive models because of a lack of modeling power. In this tutorial, we will provide a thorough introduction and review of non-autoregressive sequence generation, in four sections: 1) Background, which covers the motivation of NAR generation, the problem definition, the evaluation protocol, and the comparison with standard autoregressive generation approaches. 2) Method, which includes different aspects: model architecture, objective function, training data, learning paradigm, and additional inference tricks. 3) Application, which covers different tasks in text and speech generation, and some advanced topics in applications. 4) Conclusion, in which we describe several research challenges and discuss the potential future research directions. We hope this tutorial can serve both academic researchers and industry practitioners working on non-autoregressive sequence generation.

2021

pdf bib
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
Mingliang Zeng | Xu Tan | Rui Wang | Zeqian Ju | Tao Qin | Tie-Yan Liu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf bib
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
Yichong Leng | Xu Tan | Rui Wang | Linchen Zhu | Jin Xu | Wenjie Liu | Linquan Liu | Xiang-Yang Li | Tao Qin | Edward Lin | Tie-Yan Liu
Findings of the Association for Computational Linguistics: EMNLP 2021

Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple candidates are generated by an ASR system through beam search, current error correction approaches can only correct one sentence at a time, failing to leverage the voting effect from multiple candidates to better detect and correct error tokens. In this work, we propose FastCorrect 2, an error correction model that takes multiple ASR candidates as input for better correction accuracy. FastCorrect 2 adopts non-autoregressive generation for fast inference, which consists of an encoder that processes multiple source sentences and a decoder that generates the target sentence in parallel from the adjusted source sentence, where the adjustment is based on the predicted duration of each source token. However, there are some issues when handling multiple source sentences. First, it is non-trivial to leverage the voting effect from multiple source sentences since they usually vary in length. Thus, we propose a novel alignment algorithm to maximize the degree of token alignment among multiple sentences in terms of token and pronunciation similarity. Second, the decoder can only take one adjusted source sentence as input, while there are multiple source sentences. Thus, we develop a candidate predictor to detect the most suitable candidate for the decoder. Experiments on our inhouse dataset and AISHELL-1 show that FastCorrect 2 can further reduce the WER over the previous correction model with single candidate by 3.2% and 2.6%, demonstrating the effectiveness of leveraging multiple candidates in ASR error correction. FastCorrect 2 achieves better performance than the cascaded re-scoring and correction pipeline and can serve as a unified post-processing module for ASR.

pdf bib
DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling
Lanqing Xue | Kaitao Song | Duocai Wu | Xu Tan | Nevin L. Zhang | Tao Qin | Wei-Qiang Zhang | Tie-Yan Liu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Rap generation, which aims to produce lyrics and corresponding singing beats, needs to model both rhymes and rhythms. Previous works for rap generation focused on rhyming lyrics, but ignored rhythmic beats, which are important for rap performance. In this paper, we develop DeepRapper, a Transformer-based rap generation system that can model both rhymes and rhythms. Since there is no available rap datasets with rhythmic beats, we develop a data mining pipeline to collect a large-scale rap dataset, which includes a large number of rap songs with aligned lyrics and rhythmic beats. Second, we design a Transformer-based autoregressive language model which carefully models rhymes and rhythms. Specifically, we generate lyrics in the reverse order with rhyme representation and constraint for rhyme enhancement, and insert a beat symbol into lyrics for rhythm/beat modeling. To our knowledge, DeepRapper is the first system to generate rap with both rhymes and rhythms. Both objective and subjective evaluations demonstrate that DeepRapper generates creative and high-quality raps with rhymes and rhythms.

2020

pdf bib
A Study of Non-autoregressive Model for Sequence Generation
Yi Ren | Jinglin Liu | Xu Tan | Zhou Zhao | Sheng Zhao | Tie-Yan Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Non-autoregressive (NAR) models generate all the tokens of a sequence in parallel, resulting in faster generation speed compared to their autoregressive (AR) counterparts but at the cost of lower accuracy. Different techniques including knowledge distillation and source-target alignment have been proposed to bridge the gap between AR and NAR models in various tasks such as neural machine translation (NMT), automatic speech recognition (ASR), and text to speech (TTS). With the help of those techniques, NAR models can catch up with the accuracy of AR models in some tasks but not in some others. In this work, we conduct a study to understand the difficulty of NAR sequence generation and try to answer: (1) Why NAR models can catch up with AR models in some tasks but not all? (2) Why techniques like knowledge distillation and source-target alignment can help NAR models. Since the main difference between AR and NAR models is that NAR models do not use dependency among target tokens while AR models do, intuitively the difficulty of NAR sequence generation heavily depends on the strongness of dependency among target tokens. To quantify such dependency, we propose an analysis model called CoMMA to characterize the difficulty of different NAR sequence generation tasks. We have several interesting findings: 1) Among the NMT, ASR and TTS tasks, ASR has the most target-token dependency while TTS has the least. 2) Knowledge distillation reduces the target-token dependency in target sequence and thus improves the accuracy of NAR models. 3) Source-target alignment constraint encourages dependency of a target token on source tokens and thus eases the training of NAR models.

pdf bib
SimulSpeech: End-to-End Simultaneous Speech to Text Translation
Yi Ren | Jinglin Liu | Xu Tan | Chen Zhang | Tao Qin | Zhou Zhao | Tie-Yan Liu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

In this work, we develop SimulSpeech, an end-to-end simultaneous speech to text translation system which translates speech in source language to text in target language concurrently. SimulSpeech consists of a speech encoder, a speech segmenter and a text decoder, where 1) the segmenter builds upon the encoder and leverages a connectionist temporal classification (CTC) loss to split the input streaming speech in real time, 2) the encoder-decoder attention adopts a wait-k strategy for simultaneous translation. SimulSpeech is more challenging than previous cascaded systems (with simultaneous automatic speech recognition (ASR) and simultaneous neural machine translation (NMT)). We introduce two novel knowledge distillation methods to ensure the performance: 1) Attention-level knowledge distillation transfers the knowledge from the multiplication of the attention matrices of simultaneous NMT and ASR models to help the training of the attention mechanism in SimulSpeech; 2) Data-level knowledge distillation transfers the knowledge from the full-sentence NMT model and also reduces the complexity of data distribution to help on the optimization of SimulSpeech. Experiments on MuST-C English-Spanish and English-German spoken language translation datasets show that SimulSpeech achieves reasonable BLEU scores and lower delay compared to full-sentence end-to-end speech to text translation (without simultaneous translation), and better performance than the two-stage cascaded simultaneous translation model in terms of BLEU scores and translation delay.

2019

pdf bib
Multilingual Neural Machine Translation with Language Clustering
Xu Tan | Jiale Chen | Di He | Yingce Xia | Tao Qin | Tie-Yan Liu
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Multilingual neural machine translation (NMT), which translates multiple languages using a single model, is of great practical importance due to its advantages in simplifying the training process, reducing online maintenance costs, and enhancing low-resource and zero-shot translation. Given there are thousands of languages in the world and some of them are very different, it is extremely burdensome to handle them all in a single model or use a separate model for each language pair. Therefore, given a fixed resource budget, e.g., the number of models, how to determine which languages should be supported by one model is critical to multilingual NMT, which, unfortunately, has been ignored by previous work. In this work, we develop a framework that clusters languages into different groups and trains one multilingual model for each cluster. We study two methods for language clustering: (1) using prior knowledge, where we cluster languages according to language family, and (2) using language embedding, in which we represent each language by an embedding vector and cluster them in the embedding space. In particular, we obtain the embedding vectors of all the languages by training a universal neural machine translation model. Our experiments on 23 languages show that the first clustering method is simple and easy to understand but leading to suboptimal translation accuracy, while the second method sufficiently captures the relationship among languages well and improves the translation accuracy for almost all the languages over baseline methods.

pdf bib
Microsoft Research Asia’s Systems for WMT19
Yingce Xia | Xu Tan | Fei Tian | Fei Gao | Di He | Weicong Chen | Yang Fan | Linyuan Gong | Yichong Leng | Renqian Luo | Yiren Wang | Lijun Wu | Jinhua Zhu | Tao Qin | Tie-Yan Liu
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place for the other three. Our basic systems are built on Transformer, back translation and knowledge distillation. We integrate several of our rececent techniques to enhance the baseline systems: multi-agent dual learning (MADL), masked sequence-to-sequence pre-training (MASS), neural architecture optimization (NAO), and soft contextual data augmentation (SCA).

pdf bib
Unsupervised Pivot Translation for Distant Languages
Yichong Leng | Xu Tan | Tao Qin | Xiang-Yang Li | Tie-Yan Liu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German translation), they perform poorly between distant languages, because unsupervised alignment does not work well for distant languages. In this work, we introduce unsupervised pivot translation for distant languages, which translates a language to a distant language through multiple hops, and the unsupervised translation on each hop is relatively easier than the original direct translation. We propose a learning to route (LTR) method to choose the translation path between the source and target languages. LTR is trained on language pairs whose best translation path is available and is applied on the unseen language pairs for path selection. Experiments on 20 languages and 294 distant language pairs demonstrate the advantages of the unsupervised pivot translation for distant languages, as well as the effectiveness of the proposed LTR for path selection. Specifically, in the best case, LTR achieves an improvement of 5.58 BLEU points over the conventional direct unsupervised method.

2018

pdf bib
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter
Lijun Wu | Xu Tan | Di He | Fei Tian | Tao Qin | Jianhuang Lai | Tie-Yan Liu
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Neural machine translation usually adopts autoregressive models and suffers from exposure bias as well as the consequent error propagation problem. Many previous works have discussed the relationship between error propagation and the accuracy drop (i.e., the left part of the translated sentence is often better than its right part in left-to-right decoding models) problem. In this paper, we conduct a series of analyses to deeply understand this problem and get several interesting findings. (1) The role of error propagation on accuracy drop is overstated in the literature, although it indeed contributes to the accuracy drop problem. (2) Characteristics of a language play a more important role in causing the accuracy drop: the left part of the translation result in a right-branching language (e.g., English) is more likely to be more accurate than its right part, while the right part is more accurate for a left-branching language (e.g., Japanese). Our discoveries are confirmed on different model structures including Transformer and RNN, and in other sequence generation tasks such as text summarization.

pdf bib
Dense Information Flow for Neural Machine Translation
Yanyao Shen | Xu Tan | Di He | Tao Qin | Tie-Yan Liu
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve learning performance for both encoder and decoder in most of these deep architectures, and advanced attention connections are applied as well. Inspired by the success of the DenseNet model in computer vision problems, in this paper, we propose a densely connected NMT architecture (DenseNMT) that is able to train more efficiently for NMT. The proposed DenseNMT not only allows dense connection in creating new features for both encoder and decoder, but also uses the dense attention structure to improve attention quality. Our experiments on multiple datasets show that DenseNMT structure is more competitive and efficient.

pdf bib
Double Path Networks for Sequence to Sequence Learning
Kaitao Song | Xu Tan | Di He | Jianfeng Lu | Tao Qin | Tie-Yan Liu
Proceedings of the 27th International Conference on Computational Linguistics

Encoder-decoder based Sequence to Sequence learning (S2S) has made remarkable progress in recent years. Different network architectures have been used in the encoder/decoder. Among them, Convolutional Neural Networks (CNN) and Self Attention Networks (SAN) are the prominent ones. The two architectures achieve similar performances but use very different ways to encode and decode context: CNN use convolutional layers to focus on the local connectivity of the sequence, while SAN uses self-attention layers to focus on global semantics. In this work we propose Double Path Networks for Sequence to Sequence learning (DPN-S2S), which leverage the advantages of both models by using double path information fusion. During the encoding step, we develop a double path architecture to maintain the information coming from different paths with convolutional layers and self-attention layers separately. To effectively use the encoded context, we develop a gated attention fusion module and use it to automatically pick up the information needed during the decoding step, which is also a double path network. By deeply integrating the two paths, both types of information are combined and well exploited. Experiments show that our proposed method can significantly improve the performance of sequence to sequence learning over state-of-the-art systems.