Xuancheng Ren


pdf bib
Hierarchical Inductive Transfer for Continual Dialogue Learning
Shaoxiong Feng | Xuancheng Ren | Kan Li | Xu Sun
Findings of the Association for Computational Linguistics: ACL 2022

Pre-trained models have achieved excellent performance on the dialogue task. However, for the continual increase of online chit-chat scenarios, directly fine-tuning these models for each of the new tasks not only explodes the capacity of the dialogue system on the embedded devices but also causes knowledge forgetting on pre-trained models and knowledge interference among diverse dialogue tasks. In this work, we propose a hierarchical inductive transfer framework to learn and deploy the dialogue skills continually and efficiently. First, we introduce the adapter module into pre-trained models for learning new dialogue tasks. As the only trainable module, it is beneficial for the dialogue system on the embedded devices to acquire new dialogue skills with negligible additional parameters. Then, for alleviating knowledge interference between tasks yet benefiting the regularization between them, we further design hierarchical inductive transfer that enables new tasks to use general knowledge in the base adapter without being misled by diverse knowledge in task-specific adapters. Empirical evaluation and analysis indicate that our framework obtains comparable performance under deployment-friendly model capacity.


pdf bib
A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models
Kaiyuan Liao | Yi Zhang | Xuancheng Ren | Qi Su | Xu Sun | Bin He
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Early exit mechanism aims to accelerate the inference speed of large-scale pre-trained language models. The essential idea is to exit early without passing through all the inference layers at the inference stage. To make accurate predictions for downstream tasks, the hierarchical linguistic information embedded in all layers should be jointly considered. However, much of the research up to now has been limited to use local representations of the exit layer. Such treatment inevitably loses information of the unused past layers as well as the high-level features embedded in future layers, leading to sub-optimal performance. To address this issue, we propose a novel Past-Future method to make comprehensive predictions from a global perspective. We first take into consideration all the linguistic information embedded in the past layers and then take a further step to engage the future information which is originally inaccessible for predictions. Extensive experiments demonstrate that our method outperforms previous early exit methods by a large margin, yielding better and robust performance.

pdf bib
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Wenkai Yang | Lei Li | Zhiyuan Zhang | Xuancheng Ren | Xu Sun | Bin He
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific trigger word inserted. Previous backdoor attacking methods usually assume that attackers have a certain degree of data knowledge, either the dataset which users would use or proxy datasets for a similar task, for implementing the data poisoning procedure. However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples. Experimental results on sentiment analysis and sentence-pair classification tasks show that our method is more efficient and stealthier. We hope this work can raise the awareness of such a critical security risk hidden in the embedding layers of NLP models. Our code is available at https://github.com/lancopku/Embedding-Poisoning.

pdf bib
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects
Zhiyuan Zhang | Xuancheng Ren | Qi Su | Xu Sun | Bin He
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Side effects during neural network tuning are typically measured by overall accuracy changes. However, we find that even with similar overall accuracy, existing tuning methods result in non-negligible instance-wise side effects. Motivated by neuroscientific evidence and theoretical results, we demonstrate that side effects can be controlled by the number of changed parameters and thus, we propose to conduct neural network surgery by only modifying a limited number of parameters. Neural network surgery can be realized using diverse techniques and we investigate three lines of methods. Experimental results on representative tuning problems validate the effectiveness of the surgery approach. The dynamic selecting method achieves the best overall performance that not only satisfies the tuning goal but also induces fewer instance-wise side effects by changing only 10-5 of the parameters.

pdf bib
Rethinking Denoised Auto-Encoding in Language Pre-Training
Fuli Luo | Pengcheng Yang | Shicheng Li | Xuancheng Ren | Xu Sun | Songfang Huang | Fei Huang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise, such as masking, shuffling, or substitution, and then try to recover the original input. However, such pre-training approaches are prone to learning representations that are covariant with the noise, leading to the discrepancy between the pre-training and fine-tuning stage. To remedy this, we present ContrAstive Pre-Training (CAPT) to learn noise invariant sequence representations. The proposed CAPT encourages the consistency between representations of the original sequence and its corrupted version via unsupervised instance-wise training signals. In this way, it not only alleviates the pretrain-finetune discrepancy induced by the noise of pre-training, but also aids the pre-trained model in better capturing global semantics of the input via more effective sentence-level supervision. Different from most prior work that focuses on a particular modality, comprehensive empirical evidence on 11 natural language understanding and cross-modal tasks illustrates that CAPT is applicable for both language and vision-language tasks, and obtains surprisingly consistent improvement, including 0.6% absolute gain on GLUE benchmarks and 0.8% absolute increment on NLVR2.

pdf bib
O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning
Fenglin Liu | Xuancheng Ren | Xian Wu | Bang Yang | Shen Ge | Xu Sun
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021


pdf bib
Rethinking Skip Connection with Layer Normalization
Fenglin Liu | Xuancheng Ren | Zhiyuan Zhang | Xu Sun | Yuexian Zou
Proceedings of the 28th International Conference on Computational Linguistics

Skip connection is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through the neural network layers. However, from another point of view, it can also be seen as a modulating mechanism between the input and the output, with the input scaled by a pre-defined value one. In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious gradient exploding or vanishing in line with the deepness of the models, which could by addressed by normalization, in particular, layer normalization, which induces consistent improvements over the plain skip connection. Inspired by the findings, we further propose to adaptively adjust the scale of the input by recursively applying skip connection with layer normalization, which promotes the performance substantially and generalizes well across diverse tasks including both machine translation and image classification datasets.

pdf bib
Regularizing Dialogue Generation by Imitating Implicit Scenarios
Shaoxiong Feng | Xuancheng Ren | Hongshen Chen | Bin Sun | Kan Li | Xu Sun
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve generative dialogue systems from the scenario perspective, where both dialogue history and future conversation are taken into account to implicitly reconstruct the scenario knowledge. More importantly, the conversation scenarios are further internalized using imitation learning framework, where the conventional dialogue model that has no access to future conversations is effectively regularized by transferring the scenario knowledge contained in hierarchical supervising signals from the scenario-based dialogue model, so that the future conversation is not required in actual inference. Extensive evaluations show that our approach significantly outperforms state-of-the-art baselines on diversity and relevance, and expresses scenario-specific knowledge.


pdf bib
Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations
Guangxiang Zhao | Jingjing Xu | Qi Zeng | Xuancheng Ren | Xu Sun
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)

This paper explores a new natural languageprocessing task, review-driven multi-label musicstyle classification. This task requires systemsto identify multiple styles of music basedon its reviews on websites. The biggest challengelies in the complicated relations of musicstyles. To tackle this problem, we proposea novel deep learning approach to automaticallylearn and exploit style correlations.Experiment results show that our approachachieves large improvements over baselines onthe proposed dataset. Furthermore, the visualizedanalysis shows that our approach performswell in capturing style correlations.

pdf bib
Incorporating Fine-grained Events in Stock Movement Prediction
Deli Chen | Yanyan Zou | Keiko Harimoto | Ruihan Bao | Xuancheng Ren | Xu Sun
Proceedings of the Second Workshop on Economics and Natural Language Processing

Considering event structure information has proven helpful in text-based stock movement prediction. However, existing works mainly adopt the coarse-grained events, which loses the specific semantic information of diverse event types. In this work, we propose to incorporate the fine-grained events in stock movement prediction. Firstly, we propose a professional finance event dictionary built by domain experts and use it to extract fine-grained events automatically from finance news. Then we design a neural model to combine finance news with fine-grained event structure and stock trade data to predict the stock movement. Besides, in order to improve the generalizability of the proposed method, we design an advanced model that uses the extracted fine-grained events as the distant supervised label to train a multi-task framework of event extraction and stock prediction. The experimental results show that our method outperforms all the baselines and has good generalizability.

pdf bib
A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer
Chen Wu | Xuancheng Ren | Fuli Luo | Xu Sun
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Unsupervised text style transfer aims to alter text styles while preserving the content, without aligned data for supervision. Existing seq2seq methods face three challenges: 1) the transfer is weakly interpretable, 2) generated outputs struggle in content preservation, and 3) the trade-off between content and style is intractable. To address these challenges, we propose a hierarchical reinforced sequence operation method, named Point-Then-Operate (PTO), which consists of a high-level agent that proposes operation positions and a low-level agent that alters the sentence. We provide comprehensive training objectives to control the fluency, style, and content of the outputs and a mask-based inference algorithm that allows for multi-step revision based on the single-step trained agents. Experimental results on two text style transfer datasets show that our method significantly outperforms recent methods and effectively addresses the aforementioned challenges.


pdf bib
simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions
Fenglin Liu | Xuancheng Ren | Yuanxin Liu | Houfeng Wang | Xu Sun
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

The encode-decoder framework has shown recent success in image captioning. Visual attention, which is good at detailedness, and semantic attention, which is good at comprehensiveness, have been separately proposed to ground the caption on the image. In this paper, we propose the Stepwise Image-Topic Merging Network (simNet) that makes use of the two kinds of attention at the same time. At each time step when generating the caption, the decoder adaptively merges the attentive information in the extracted topics and the image according to the generated context, so that the visual information and the semantic information can be effectively combined. The proposed approach is evaluated on two benchmark datasets and reaches the state-of-the-art performances.

pdf bib
Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation
Junyang Lin | Xu Sun | Xuancheng Ren | Muyu Li | Qi Su
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Most of the Neural Machine Translation (NMT) models are based on the sequence-to-sequence (Seq2Seq) model with an encoder-decoder framework equipped with the attention mechanism. However, the conventional attention mechanism treats the decoding at each time step equally with the same matrix, which is problematic since the softness of the attention for different types of words (e.g. content words and function words) should differ. Therefore, we propose a new model with a mechanism called Self-Adaptive Control of Temperature (SACT) to control the softness of attention by means of an attention temperature. Experimental results on the Chinese-English translation and English-Vietnamese translation demonstrate that our model outperforms the baseline models, and the analysis and the case study show that our model can attend to the most relevant elements in the source-side contexts and generate the translation of high quality.

pdf bib
Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation
Jingjing Xu | Xuancheng Ren | Junyang Lin | Xu Sun
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Existing text generation methods tend to produce repeated and ”boring” expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for ”novel” and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines.

pdf bib
A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation
Jingjing Xu | Xuancheng Ren | Yi Zhang | Qi Zeng | Xiaoyan Cai | Xu Sun
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Narrative story generation is a challenging problem because it demands the generated sentences with tight semantic connections, which has not been well studied by most existing generative models. To address this problem, we propose a skeleton-based model to promote the coherence of generated stories. Different from traditional models that generate a complete sentence at a stroke, the proposed model first generates the most critical phrases, called skeleton, and then expands the skeleton to a complete and fluent sentence. The skeleton is not manually defined, but learned by a reinforcement learning method. Compared to the state-of-the-art models, our skeleton-based model can generate significantly more coherent text according to human evaluation and automatic evaluation. The G-score is improved by 20.1% in human evaluation.

pdf bib
Building an Ellipsis-aware Chinese Dependency Treebank for Web Text
Xuancheng Ren | Xu Sun | Ji Wen | Bingzhen Wei | Weidong Zhan | Zhiyuan Zhang
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
Jingjing Xu | Xu Sun | Qi Zeng | Xiaodong Zhang | Xuancheng Ren | Houfeng Wang | Wenjie Li
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

The goal of sentiment-to-sentiment “translation” is to change the underlying sentiment of a sentence while keeping its content. The main challenge is the lack of parallel data. To solve this problem, we propose a cycled reinforcement learning method that enables training on unpaired data by collaboration between a neutralization module and an emotionalization module. We evaluate our approach on two review datasets, Yelp and Amazon. Experimental results show that our approach significantly outperforms the state-of-the-art systems. Especially, the proposed method substantially improves the content preservation performance. The BLEU score is improved from 1.64 to 22.46 and from 0.56 to 14.06 on the two datasets, respectively.

pdf bib
Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?
Yi Zhang | Xu Sun | Shuming Ma | Yang Yang | Xuancheng Ren
Proceedings of the 27th International Conference on Computational Linguistics

Existing neural models usually predict the tag of the current token independent of the neighboring tags. The popular LSTM-CRF model considers the tag dependencies between every two consecutive tags. However, it is hard for existing neural models to take longer distance dependencies between tags into consideration. The scalability is mainly limited by the complex model structures and the cost of dynamic programming during training. In our work, we first design a new model called “high order LSTM” to predict multiple tags for the current token which contains not only the current tag but also the previous several tags. We call the number of tags in one prediction as “order”. Then we propose a new method called Multi-Order BiLSTM (MO-BiLSTM) which combines low order and high order LSTMs together. MO-BiLSTM keeps the scalability to high order models with a pruning technique. We evaluate MO-BiLSTM on all-phrase chunking and NER datasets. Experiment results show that MO-BiLSTM achieves the state-of-the-art result in chunking and highly competitive results in two NER datasets.

pdf bib
Deconvolution-Based Global Decoding for Neural Machine Translation
Junyang Lin | Xu Sun | Xuancheng Ren | Shuming Ma | Jinsong Su | Qi Su
Proceedings of the 27th International Conference on Computational Linguistics

A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have proved that language is not linear word sequence but sequence of complex structure, translation at each step should be conditioned on the whole target-side context. To tackle the problem, we propose a new NMT model that decodes the sequence with the guidance of its structural prediction of the context of the target sequence. Our model generates translation based on the structural prediction of the target-side context so that the translation can be freed from the bind of sequential order. Experimental results demonstrate that our model is more competitive compared with the state-of-the-art methods, and the analysis reflects that our model is also robust to translating sentences of different lengths and it also reduces repetition with the instruction from the target-side context for decoding.

pdf bib
Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation
Shuming Ma | Xu Sun | Wei Li | Sujian Li | Wenjie Li | Xuancheng Ren
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

Most recent approaches use the sequence-to-sequence model for paraphrase generation. The existing sequence-to-sequence model tends to memorize the words and the patterns in the training dataset instead of learning the meaning of the words. Therefore, the generated sentences are often grammatically correct but semantically improper. In this work, we introduce a novel model based on the encoder-decoder framework, called Word Embedding Attention Network (WEAN). Our proposed model generates the words by querying distributed word representations (i.e. neural word embeddings), hoping to capturing the meaning of the according words. Following previous work, we evaluate our model on two paraphrase-oriented tasks, namely text simplification and short text abstractive summarization. Experimental results show that our model outperforms the sequence-to-sequence baseline by the BLEU score of 6.3 and 5.5 on two English text simplification datasets, and the ROUGE-2 F1 score of 5.7 on a Chinese summarization dataset. Moreover, our model achieves state-of-the-art performances on these three benchmark datasets.

pdf bib
Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text
Ji Wen | Xu Sun | Xuancheng Ren | Qi Su
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Relation classification is an important semantic processing task in the field of natural language processing. In this paper, we propose the task of relation classification for Chinese literature text. A new dataset of Chinese literature text is constructed to facilitate the study in this task. We present a novel model, named Structure Regularized Bidirectional Recurrent Convolutional Neural Network (SR-BRCNN), to identify the relation between entities. The proposed model learns relation representations along the shortest dependency path (SDP) extracted from the structure regularized dependency tree, which has the benefits of reducing the complexity of the whole model. Experimental results show that the proposed method significantly improves the F1 score by 10.3, and outperforms the state-of-the-art approaches on Chinese literature text.