Shuohang Wang


pdf bib
LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval
Siqi Sun | Yen-Chun Chen | Linjie Li | Shuohang Wang | Yuwei Fang | Jingjing Liu
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Multimodal pre-training has propelled great advancement in vision-and-language research. These large-scale pre-trained models, although successful, fatefully suffer from slow inference speed due to enormous computational cost mainly from cross-modal attention in Transformer architecture. When applied to real-life applications, such latency and computation demand severely deter the practical use of pre-trained models. In this paper, we study Image-text retrieval (ITR), the most mature scenario of V+L application, which has been widely studied even prior to the emergence of recent pre-trained models. We propose a simple yet highly effective approach, LightningDOT that accelerates the inference time of ITR by thousands of times, without sacrificing accuracy. LightningDOT removes the time-consuming cross-modal attention by extracting pre-cached feature indexes offline, and employing instant dot-product matching online, which significantly speeds up retrieval process. In fact, our LightningDOT achieves superior performance across mainstream ITR benchmarks such as Flickr30k and COCO datasets, outperforming existing pre-trained models that consume 1000 times magnitude of computational hours using the same features.

pdf bib
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
Xiaohan Chen | Yu Cheng | Shuohang Wang | Zhe Gan | Zhangyang Wang | Jingjing 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)

Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous computation resources and extremely long training time for both pre-training and fine-tuning. Many works have studied model compression on large NLP models, but only focusing on reducing inference time while still requiring an expensive training process. Other works use extremely large batch sizes to shorten the pre-training time, at the expense of higher computational resource demands. In this paper, inspired by the Early-Bird Lottery Tickets recently studied for computer vision tasks, we propose EarlyBERT, a general computationally-efficient training algorithm applicable to both pre-training and fine-tuning of large-scale language models. By slimming the self-attention and fully-connected sub-layers inside a transformer, we are the first to identify structured winning tickets in the early stage of BERT training. We apply those tickets towards efficient BERT training, and conduct comprehensive pre-training and fine-tuning experiments on GLUE and SQuAD downstream tasks. Our results show that EarlyBERT achieves comparable performance to standard BERT, with 35 45% less training time. Code is available at

pdf bib
On Orthogonality Constraints for Transformers
Aston Zhang | Alvin Chan | Yi Tay | Jie Fu | Shuohang Wang | Shuai Zhang | Huajie Shao | Shuochao Yao | Roy Ka-Wei Lee
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Orthogonality constraints encourage matrices to be orthogonal for numerical stability. These plug-and-play constraints, which can be conveniently incorporated into model training, have been studied for popular architectures in natural language processing, such as convolutional neural networks and recurrent neural networks. However, a dedicated study on such constraints for transformers has been absent. To fill this gap, this paper studies orthogonality constraints for transformers, showing the effectiveness with empirical evidence from ten machine translation tasks and two dialogue generation tasks. For example, on the large-scale WMT’16 En→De benchmark, simply plugging-and-playing orthogonality constraints on the original transformer model (Vaswani et al., 2017) increases the BLEU from 28.4 to 29.6, coming close to the 29.7 BLEU achieved by the very competitive dynamic convolution (Wu et al., 2019).

pdf bib
Cluster-Former: Clustering-based Sparse Transformer for Question Answering
Shuohang Wang | Luowei Zhou | Zhe Gan | Yen-Chun Chen | Yuwei Fang | Siqi Sun | Yu Cheng | Jingjing Liu
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021


pdf bib
Cross-Thought for Sentence Encoder Pre-training
Shuohang Wang | Yuwei Fang | Siqi Sun | Zhe Gan | Yu Cheng | Jingjing Liu | Jing Jiang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering. Instead of using the original signals of full sentences, we train a Transformer-based sequence encoder over a large set of short sequences, which allows the model to automatically select the most useful information for predicting masked words. Experiments on question answering and textual entailment tasks demonstrate that our pre-trained encoder can outperform state-of-the-art encoders trained with continuous sentence signals as well as traditional masked language modeling baselines. Our proposed approach also achieves new state of the art on HotpotQA (full-wiki setting) by improving intermediate information retrieval performance.

pdf bib
Contrastive Distillation on Intermediate Representations for Language Model Compression
Siqi Sun | Zhe Gan | Yuwei Fang | Yu Cheng | Shuohang Wang | Jingjing Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Existing language model compression methods mostly use a simple L_2 loss to distill knowledge in the intermediate representations of a large BERT model to a smaller one. Although widely used, this objective by design assumes that all the dimensions of hidden representations are independent, failing to capture important structural knowledge in the intermediate layers of the teacher network. To achieve better distillation efficacy, we propose Contrastive Distillation on Intermediate Representations (CoDIR), a principled knowledge distillation framework where the student is trained to distill knowledge through intermediate layers of the teacher via a contrastive objective. By learning to distinguish positive sample from a large set of negative samples, CoDIR facilitates the student’s exploitation of rich information in teacher’s hidden layers. CoDIR can be readily applied to compress large-scale language models in both pre-training and finetuning stages, and achieves superb performance on the GLUE benchmark, outperforming state-of-the-art compression methods.

pdf bib
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack
Boxin Wang | Hengzhi Pei | Boyuan Pan | Qian Chen | Shuohang Wang | Bo Li
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Adversarial attacks against natural language processing systems, which perform seemingly innocuous modifications to inputs, can induce arbitrary mistakes to the target models. Though raised great concerns, such adversarial attacks can be leveraged to estimate the robustness of NLP models. Compared with the adversarial example generation in continuous data domain (e.g., image), generating adversarial text that preserves the original meaning is challenging since the text space is discrete and non-differentiable. To handle these challenges, we propose a target-controllable adversarial attack framework T3, which is applicable to a range of NLP tasks. In particular, we propose a tree-based autoencoder to embed the discrete text data into a continuous representation space, upon which we optimize the adversarial perturbation. A novel tree-based decoder is then applied to regularize the syntactic correctness of the generated text and manipulate it on either sentence (T3(Sent)) or word (T3(Word)) level. We consider two most representative NLP tasks: sentiment analysis and question answering (QA). Extensive experimental results and human studies show that T3 generated adversarial texts can successfully manipulate the NLP models to output the targeted incorrect answer without misleading the human. Moreover, we show that the generated adversarial texts have high transferability which enables the black-box attacks in practice. Our work sheds light on an effective and general way to examine the robustness of NLP models. Our code is publicly available at

pdf bib
Hierarchical Graph Network for Multi-hop Question Answering
Yuwei Fang | Siqi Sun | Zhe Gan | Rohit Pillai | Shuohang Wang | Jingjing Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, we present Hierarchical Graph Network (HGN) for multi-hop question answering. To aggregate clues from scattered texts across multiple paragraphs, a hierarchical graph is created by constructing nodes on different levels of granularity (questions, paragraphs, sentences, entities), the representations of which are initialized with pre-trained contextual encoders. Given this hierarchical graph, the initial node representations are updated through graph propagation, and multi-hop reasoning is performed via traversing through the graph edges for each subsequent sub-task (e.g., paragraph selection, supporting facts extraction, answer prediction). By weaving heterogeneous nodes into an integral unified graph, this hierarchical differentiation of node granularity enables HGN to support different question answering sub-tasks simultaneously. Experiments on the HotpotQA benchmark demonstrate that the proposed model achieves new state of the art, outperforming existing multi-hop QA approaches.

pdf bib
Multi-Fact Correction in Abstractive Text Summarization
Yue Dong | Shuohang Wang | Zhe Gan | Yu Cheng | Jackie Chi Kit Cheung | Jingjing Liu
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE. However, system-generated abstractive summaries often face the pitfall of factual inconsistency: generating incorrect facts with respect to the source text. To address this challenge, we propose Span-Fact, a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text, while retaining the syntactic structure of summaries generated by abstractive summarization models. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.


pdf bib
Unsupervised Deep Structured Semantic Models for Commonsense Reasoning
Shuohang Wang | Sheng Zhang | Yelong Shen | Xiaodong Liu | Jingjing Liu | Jianfeng Gao | Jing Jiang
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)

Commonsense reasoning is fundamental to natural language understanding. While traditional methods rely heavily on human-crafted features and knowledge bases, we explore learning commonsense knowledge from a large amount of raw text via unsupervised learning. We propose two neural network models based on the Deep Structured Semantic Models (DSSM) framework to tackle two classic commonsense reasoning tasks, Winograd Schema challenges (WSC) and Pronoun Disambiguation (PDP). Evaluation shows that the proposed models effectively capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.

pdf bib
Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks
Yi Tay | Aston Zhang | Anh Tuan Luu | Jinfeng Rao | Shuai Zhang | Shuohang Wang | Jie Fu | Siu Cheung Hui
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Many state-of-the-art neural models for NLP are heavily parameterized and thus memory inefficient. This paper proposes a series of lightweight and memory efficient neural architectures for a potpourri of natural language processing (NLP) tasks. To this end, our models exploit computation using Quaternion algebra and hypercomplex spaces, enabling not only expressive inter-component interactions but also significantly (75%) reduced parameter size due to lesser degrees of freedom in the Hamilton product. We propose Quaternion variants of models, giving rise to new architectures such as the Quaternion attention Model and Quaternion Transformer. Extensive experiments on a battery of NLP tasks demonstrates the utility of proposed Quaternion-inspired models, enabling up to 75% reduction in parameter size without significant loss in performance.

pdf bib
Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives
Yi Tay | Shuohang Wang | Anh Tuan Luu | Jie Fu | Minh C. Phan | Xingdi Yuan | Jinfeng Rao | Siu Cheung Hui | Aston Zhang
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

This paper tackles the problem of reading comprehension over long narratives where documents easily span over thousands of tokens. We propose a curriculum learning (CL) based Pointer-Generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty. This can be interpreted as a form of domain randomization and/or generative pretraining during training. To this end, the usage of the Pointer-Generator softens the requirement of having the answer within the context, enabling us to construct diverse training samples for learning. Additionally, we propose a new Introspective Alignment Layer (IAL), which reasons over decomposed alignments using block-based self-attention. We evaluate our proposed method on the NarrativeQA reading comprehension benchmark, achieving state-of-the-art performance, improving existing baselines by 51% relative improvement on BLEU-4 and 17% relative improvement on Rouge-L. Extensive ablations confirm the effectiveness of our proposed IAL and CL components.


pdf bib
A Co-Matching Model for Multi-choice Reading Comprehension
Shuohang Wang | Mo Yu | Jing Jiang | Shiyu Chang
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair. This paper proposes a new co-matching approach to this problem, which jointly models whether a passage can match both a question and a candidate answer. Experimental results on the RACE dataset demonstrate that our approach achieves state-of-the-art performance.


pdf bib
Learning Natural Language Inference with LSTM
Shuohang Wang | Jing Jiang
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies