Hao Zhou


2020

pdf bib
Unsupervised Paraphrasing by Simulated Annealing
Xianggen Liu | Lili Mou | Fandong Meng | Hao Zhou | Jie Zhou | Sen Song
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

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.

pdf bib
Do you have the right scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods
Ning Miao | Yuxuan Song | Hao Zhou | Lei Li
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

It has been a common approach to pre-train a language model on a large corpus and fine-tune it on task-specific data. In practice, we observe that fine-tuning a pre-trained model on a small dataset may lead to over- and/or under-estimate problem. In this paper, we propose MC-Tailor, a novel method to alleviate the above issue in text generation tasks by truncating and transferring the probability mass from over-estimated regions to under-estimated ones. Experiments on a variety of text generation datasets show that MC-Tailor consistently and significantly outperforms the fine-tuning approach.

pdf bib
KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
Hao Zhou | Chujie Zheng | Kaili Huang | Minlie Huang | Xiaoyan Zhu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

The research of knowledge-driven conversational systems is largely limited due to the lack of dialog data which consists of multi-turn conversations on multiple topics and with knowledge annotations. In this paper, we propose a Chinese multi-domain knowledge-driven conversation dataset, KdConv, which grounds the topics in multi-turn conversations to knowledge graphs. Our corpus contains 4.5K conversations from three domains (film, music, and travel), and 86K utterances with an average turn number of 19.0. These conversations contain in-depth discussions on related topics and natural transition between multiple topics. To facilitate the following research on this corpus, we provide several benchmark models. Comparative results show that the models can be enhanced by introducing background knowledge, yet there is still a large space for leveraging knowledge to model multi-turn conversations for further research. Results also show that there are obvious performance differences between different domains, indicating that it is worth further explore transfer learning and domain adaptation. The corpus and benchmark models are publicly available.

pdf bib
Xiaomingbot: A Multilingual Robot News Reporter
Runxin Xu | Jun Cao | Mingxuan Wang | Jiaze Chen | Hao Zhou | Ying Zeng | Yuping Wang | Li Chen | Xiang Yin | Xijin Zhang | Songcheng Jiang | Yuxuan Wang | Lei Li
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

This paper proposes the building of Xiaomingbot, an intelligent, multilingual and multimodal software robot equipped with four inte- gral capabilities: news generation, news translation, news reading and avatar animation. Its system summarizes Chinese news that it automatically generates from data tables. Next, it translates the summary or the full article into multiple languages, and reads the multi- lingual rendition through synthesized speech. Notably, Xiaomingbot utilizes a voice cloning technology to synthesize the speech trained from a real person’s voice data in one input language. The proposed system enjoys several merits: it has an animated avatar, and is able to generate and read multilingual news. Since it was put into practice, Xiaomingbot has written over 600,000 articles, and gained over 150,000 followers on social media platforms.

pdf bib
Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space
Dongyu Ru | Jiangtao Feng | Lin Qiu | Hao Zhou | Mingxuan Wang | Weinan Zhang | Yong Yu | Lei Li
Findings of the Association for Computational Linguistics: EMNLP 2020

Active learning for sentence understanding aims at discovering informative unlabeled data for annotation and therefore reducing the demand for labeled data. We argue that the typical uncertainty sampling method for active learning is time-consuming and can hardly work in real-time, which may lead to ineffective sample selection. We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently. AUSDS maps sentences into latent space generated by the popular pre-trained language models, and discover informative unlabeled text samples for annotation via adversarial attack. The proposed approach is extremely efficient compared with traditional uncertainty sampling with more than 10x speedup. Experimental results on five datasets show that AUSDS outperforms strong baselines on effectiveness.

pdf bib
Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information
Zehui Lin | Xiao Pan | Mingxuan Wang | Xipeng Qiu | Jiangtao Feng | Hao Zhou | Lei Li
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

We investigate the following question for machine translation (MT): can we develop a single universal MT model to serve as the common seed and obtain derivative and improved models on arbitrary language pairs? We propose mRASP, an approach to pre-train a universal multilingual neural machine translation model. Our key idea in mRASP is its novel technique of random aligned substitution, which brings words and phrases with similar meanings across multiple languages closer in the representation space. We pre-train a mRASP model on 32 language pairs jointly with only public datasets. The model is then fine-tuned on downstream language pairs to obtain specialized MT models. We carry out extensive experiments on 42 translation directions across a diverse settings, including low, medium, rich resource, and as well as transferring to exotic language pairs. Experimental results demonstrate that mRASP achieves significant performance improvement compared to directly training on those target pairs. It is the first time to verify that multiple lowresource language pairs can be utilized to improve rich resource MT. Surprisingly, mRASP is even able to improve the translation quality on exotic languages that never occur in the pretraining corpus. Code, data, and pre-trained models are available at https://github. com/linzehui/mRASP.

pdf bib
On the Sentence Embeddings from Pre-trained Language Models
Bohan Li | Hao Zhou | Junxian He | Mingxuan Wang | Yiming Yang | Lei Li
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture semantic meaning of sentences. In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We first reveal the theoretical connection between the masked language model pre-training objective and the semantic similarity task theoretically, and then analyze the BERT sentence embeddings empirically. We find that BERT always induces a non-smooth anisotropic semantic space of sentences, which harms its performance of semantic similarity. To address this issue, we propose to transform the anisotropic sentence embedding distribution to a smooth and isotropic Gaussian distribution through normalizing flows that are learned with an unsupervised objective. Experimental results show that our proposed BERT-flow method obtains significant performance gains over the state-of-the-art sentence embeddings on a variety of semantic textual similarity tasks. The code is available at https://github.com/bohanli/BERT-flow.

2019

bib
Discreteness in Neural Natural Language Processing
Lili Mou | Hao Zhou | Lei Li
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): Tutorial Abstracts

This tutorial provides a comprehensive guide to the process of discreteness in neural NLP.As a gentle start, we will briefly introduce the background of deep learning based NLP, where we point out the ubiquitous discreteness of natural language and its challenges in neural information processing. Particularly, we will focus on how such discreteness plays a role in the input space, the latent space, and the output space of a neural network. In each part, we will provide examples, discuss machine learning techniques, as well as demonstrate NLP applications.

pdf bib
Imitation Learning for Non-Autoregressive Neural Machine Translation
Bingzhen Wei | Mingxuan Wang | Hao Zhou | Junyang Lin | Xu Sun
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Non-autoregressive translation models (NAT) have achieved impressive inference speedup. A potential issue of the existing NAT algorithms, however, is that the decoding is conducted in parallel, without directly considering previous context. In this paper, we propose an imitation learning framework for non-autoregressive machine translation, which still enjoys the fast translation speed but gives comparable translation performance compared to its auto-regressive counterpart. We conduct experiments on the IWSLT16, WMT14 and WMT16 datasets. Our proposed model achieves a significant speedup over the autoregressive models, while keeping the translation quality comparable to the autoregressive models. By sampling sentence length in parallel at inference time, we achieve the performance of 31.85 BLEU on WMT16 RoEn and 30.68 BLEU on IWSLT16 EnDe.

pdf bib
Generating Fluent Adversarial Examples for Natural Languages
Huangzhao Zhang | Hao Zhou | Ning Miao | Lei Li
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge. Firstly, as the sentence space is discrete, it is difficult to make small perturbations along the direction of gradients. Secondly, the fluency of the generated examples cannot be guaranteed. In this paper, we propose MHA, which addresses both problems by performing Metropolis-Hastings sampling, whose proposal is designed with the guidance of gradients. Experiments on IMDB and SNLI show that our proposed MHAoutperforms the baseline model on attacking capability. Adversarial training with MHA also leads to better robustness and performance.

pdf bib
Generating Sentences from Disentangled Syntactic and Semantic Spaces
Yu Bao | Hao Zhou | Shujian Huang | Lei Li | Lili Mou | Olga Vechtomova | Xin-yu Dai | Jiajun Chen
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic information. In this paper, we propose to generate sentences from disentangled syntactic and semantic spaces. Our proposed method explicitly models syntactic information in the VAE’s latent space by using the linearized tree sequence, leading to better performance of language generation. Additionally, the advantage of sampling in the disentangled syntactic and semantic latent spaces enables us to perform novel applications, such as the unsupervised paraphrase generation and syntax transfer generation. Experimental results show that our proposed model achieves similar or better performance in various tasks, compared with state-of-the-art related work.

pdf bib
Dynamically Fused Graph Network for Multi-hop Reasoning
Lin Qiu | Yunxuan Xiao | Yanru Qu | Hao Zhou | Lei Li | Weinan Zhang | Yong Yu
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Text-based question answering (TBQA) has been studied extensively in recent years. Most existing approaches focus on finding the answer to a question within a single paragraph. However, many difficult questions require multiple supporting evidence from scattered text among two or more documents. In this paper, we propose Dynamically Fused Graph Network (DFGN), a novel method to answer those questions requiring multiple scattered evidence and reasoning over them. Inspired by human’s step-by-step reasoning behavior, DFGN includes a dynamic fusion layer that starts from the entities mentioned in the given query, explores along the entity graph dynamically built from the text, and gradually finds relevant supporting entities from the given documents. We evaluate DFGN on HotpotQA, a public TBQA dataset requiring multi-hop reasoning. DFGN achieves competitive results on the public board. Furthermore, our analysis shows DFGN produces interpretable reasoning chains.

pdf bib
Rethinking Text Attribute Transfer: A Lexical Analysis
Yao Fu | Hao Zhou | Jiaze Chen | Lei Li
Proceedings of the 12th International Conference on Natural Language Generation

Text attribute transfer is modifying certain linguistic attributes (e.g. sentiment, style, author-ship, etc.) of a sentence and transforming them from one type to another. In this paper, we aim to analyze and interpret what is changed during the transfer process. We start from the observation that in many existing models and datasets, certain words within a sentence play important roles in determining the sentence attribute class. These words are referred as the Pivot Words. Based on these pivot words, we propose a lexical analysis framework, the Pivot Analysis, to quantitatively analyze the effects of these words in text attribute classification and transfer. We apply this framework to existing datasets and models and show that: (1) the pivot words are strong features for the classification of sentence attributes; (2) to change the attribute of a sentence, many datasets only requires to change certain pivot words; (3) consequently, many transfer models only perform the lexical-level modification,while leaving higher-level sentence structures unchanged. Our work provides an in-depth understanding of linguistic attribute transfer and further identifies the future requirements and challenges of this task

pdf bib
Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation
Hareesh Bahuleyan | Lili Mou | Hao Zhou | Olga Vechtomova
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback-Leibler (KL) divergence between the posterior and prior. In NLP, VAEs are extremely difficult to train due to the problem of KL collapsing to zero. One has to implement various heuristics such as KL weight annealing and word dropout in a carefully engineered manner to successfully train a VAE for text. In this paper, we propose to use the Wasserstein autoencoder (WAE) for probabilistic sentence generation, where the encoder could be either stochastic or deterministic. We show theoretically and empirically that, in the original WAE, the stochastically encoded Gaussian distribution tends to become a Dirac-delta function, and we propose a variant of WAE that encourages the stochasticity of the encoder. Experimental results show that the latent space learned by WAE exhibits properties of continuity and smoothness as in VAEs, while simultaneously achieving much higher BLEU scores for sentence reconstruction.

2018

pdf bib
Dynamic Oracle for Neural Machine Translation in Decoding Phase
Zi-Yi Dou | Hao Zhou | Shu-Jian Huang | Xin-Yu Dai | Jia-Jun Chen
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
On Tree-Based Neural Sentence Modeling
Haoyue Shi | Hao Zhou | Jiaze Chen | Lei Li
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of different tree structures, we replace the parsing trees with trivial trees (i.e., binary balanced tree, left-branching tree and right-branching tree) in the encoders. Though trivial trees contain no syntactic information, those encoders get competitive or even better results on all of the ten downstream tasks we investigated. This surprising result indicates that explicit syntax guidance may not be the main contributor to the superior performances of tree-based neural sentence modeling. Further analysis show that tree modeling gives better results when crucial words are closer to the final representation. Additional experiments give more clues on how to design an effective tree-based encoder. Our code is open-source and available at https://github.com/ExplorerFreda/TreeEnc.

pdf bib
Modeling Past and Future for Neural Machine Translation
Zaixiang Zheng | Hao Zhou | Shujian Huang | Lili Mou | Xinyu Dai | Jiajun Chen | Zhaopeng Tu
Transactions of the Association for Computational Linguistics, Volume 6

Existing neural machine translation systems do not explicitly model what has been translated and what has not during the decoding phase. To address this problem, we propose a novel mechanism that separates the source information into two parts: translated Past contents and untranslated Future contents, which are modeled by two additional recurrent layers. The Past and Future contents are fed to both the attention model and the decoder states, which provides Neural Machine Translation (NMT) systems with the knowledge of translated and untranslated contents. Experimental results show that the proposed approach significantly improves the performance in Chinese-English, German-English, and English-German translation tasks. Specifically, the proposed model outperforms the conventional coverage model in terms of both the translation quality and the alignment error rate.

2017

pdf bib
Chunk-Based Bi-Scale Decoder for Neural Machine Translation
Hao Zhou | Zhaopeng Tu | Shujian Huang | Xiaohua Liu | Hang Li | Jiajun Chen
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

In typical neural machine translation (NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we propose a new type of decoder for NMT, which splits the decode state into two parts and updates them in two different time-scales. Specifically, we first predict a chunk time-scale state for phrasal modeling, on top of which multiple word time-scale states are generated. In this way, the target sentence is translated hierarchically from chunks to words, with information in different granularities being leveraged. Experiments show that our proposed model significantly improves the translation performance over the state-of-the-art NMT model.

pdf bib
Word-Context Character Embeddings for Chinese Word Segmentation
Hao Zhou | Zhenting Yu | Yue Zhang | Shujian Huang | Xinyu Dai | Jiajun Chen
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Neural parsers have benefited from automatically labeled data via dependency-context word embeddings. We investigate training character embeddings on a word-based context in a similar way, showing that the simple method improves state-of-the-art neural word segmentation models significantly, beating tri-training baselines for leveraging auto-segmented data.

2016

pdf bib
Evaluating a Deterministic Shift-Reduce Neural Parser for Constituent Parsing
Hao Zhou | Yue Zhang | Shujian Huang | Xin-Yu Dai | Jiajun Chen
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

Greedy transition-based parsers are appealing for their very fast speed, with reasonably high accuracies. In this paper, we build a fast shift-reduce neural constituent parser by using a neural network to make local decisions. One challenge to the parsing speed is the large hidden and output layer sizes caused by the number of constituent labels and branching options. We speed up the parser by using a hierarchical output layer, inspired by the hierarchical log-bilinear neural language model. In standard WSJ experiments, the neural parser achieves an almost 2.4 time speed up (320 sen/sec) compared to a non-hierarchical baseline without significant accuracy loss (89.06 vs 89.13 F-score).

pdf bib
Context-aware Natural Language Generation for Spoken Dialogue Systems
Hao Zhou | Minlie Huang | Xiaoyan Zhu
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers

Natural language generation (NLG) is an important component of question answering(QA) systems which has a significant impact on system quality. Most tranditional QA systems based on templates or rules tend to generate rigid and stylised responses without the natural variation of human language. Furthermore, such methods need an amount of work to generate the templates or rules. To address this problem, we propose a Context-Aware LSTM model for NLG. The model is completely driven by data without manual designed templates or rules. In addition, the context information, including the question to be answered, semantic values to be addressed in the response, and the dialogue act type during interaction, are well approached in the neural network model, which enables the model to produce variant and informative responses. The quantitative evaluation and human evaluation show that CA-LSTM obtains state-of-the-art performance.

pdf bib
A Search-Based Dynamic Reranking Model for Dependency Parsing
Hao Zhou | Yue Zhang | Shujian Huang | Junsheng Zhou | Xin-Yu Dai | Jiajun Chen
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2015

pdf bib
A Neural Probabilistic Structured-Prediction Model for Transition-Based Dependency Parsing
Hao Zhou | Yue Zhang | Shujian Huang | Jiajun Chen
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2012

pdf bib
Adapting Conventional Chinese Word Segmenter for Segmenting Micro-blog Text: Combining Rule-based and Statistic-based Approaches
Ning Xi | Bin Li | Guangchao Tang | Shujian Huang | Yinggong Zhao | Hao Zhou | Xinyu Dai | Jiajun Chen
Proceedings of the Second CIPS-SIGHAN Joint Conference on Chinese Language Processing