Adversarial training is so far the most effective strategy in defending against adversarial examples. However, it suffers from high computational costs due to the iterative adversarial attacks in each training step. Recent studies show that it is possible to achieve fast Adversarial Training by performing a single-step attack with random initialization. However, such an approach still lags behind state-of-the-art adversarial training algorithms on both stability and model robustness. In this work, we develop a new understanding towards Fast Adversarial Training, by viewing random initialization as performing randomized smoothing for better optimization of the inner maximization problem. Following this new perspective, we also propose a new initialization strategy, backward smoothing, to further improve the stability and model robustness over single-step robust training methods. Experiments on multiple benchmarks demonstrate that our method achieves similar model robustness as the original TRADES method while using much less training time (~3x improvement with the same training schedule).

Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide range of VL tasks. However, the large number of parameters in such models hinders their application in practice. In parallel, work on the lottery ticket hypothesis (LTH) has shown that deep neural networks contain small matching subnetworks that can achieve on par or even better performance than the dense networks when trained in isolation. In this work, we perform the first empirical study to assess whether such trainable subnetworks also exist in pre-trained VL models. We use UNITER as the main testbed (also test on LXMERT and ViLT), and consolidate 7 representative VL tasks for experiments, including visual question answering, visual commonsense reasoning, visual entailment, referring expression comprehension, image-text retrieval, GQA, and NLVR2. Through comprehensive analysis, we summarize our main findings as follows. (i) It is difficult to find subnetworks that strictly match the performance of the full model. However, we can find relaxed winning tickets at 50%-70% sparsity that maintain 99% of the full accuracy. (ii) Subnetworks found by task-specific pruning transfer reasonably well to the other tasks, while those found on the pre-training tasks at 60%/70% sparsity transfer universally, matching 98%/96% of the full accuracy on average over all the tasks. (iii) Besides UNITER, other models such as LXMERT and ViLT can also play lottery tickets. However, the highest sparsity we can achieve for ViLT is far lower than LXMERT and UNITER (30% vs. 70%). (iv) LTH also remains relevant when using other training methods (e.g., adversarial training).

Large-scale cross-lingual language models (LM), such as mBERT, Unicoder and XLM, have achieved great success in cross-lingual representation learning. However, when applied to zero-shot cross-lingual transfer tasks, most existing methods use only single-language input for LM finetuning, without leveraging the intrinsic cross-lingual alignment between different languages that proves essential for multilingual tasks. In this paper, we propose FILTER, an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. Specifically, FILTER first encodes text input in the source language and its translation in the target language independently in the shallow layers, then performs cross-language fusion to extract multilingual knowledge in the intermediate layers, and finally performs further language-specific encoding. During inference, the model makes predictions based on the text input in the target language and its translation in the source language. For simple tasks such as classification, translated text in the target language shares the same label as the source language. However, this shared label becomes less accurate or even unavailable for more complex tasks such as question answering, NER and POS tagging. To tackle this issue, we further propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language. Extensive experiments demonstrate that FILTER achieves new state of the art on two challenging multilingual multi-task benchmarks, XTREME and XGLUE.

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). 2021.

The primary goal of knowledge distillation (KD) is to encapsulate the information of a model learned from a teacher network into a student network, with the latter being more compact than the former. Existing work, e.g., using Kullback-Leibler divergence for distillation, may fail to capture important structural knowledge in the teacher network and often lacks the ability for feature generalization, particularly in situations when teacher and student are built to address different classification tasks. We propose Wasserstein Contrastive Representation Distillation (WCoRD), which leverages both primal and dual forms of Wasserstein distance for KD. The dual form is used for global knowledge transfer, yielding a contrastive learning objective that maximizes the lower bound of mutual information between the teacher and the student networks. The primal form is used for local contrastive knowledge transfer within a mini-batch, effectively matching the distributions of features between the teacher and the student networks. Experiments demonstrate that the proposed WCoRD method outperforms state-of-the-art approaches on privileged information distillation, model compression and cross-modal transfer.

The canonical approach to video-and-language learning (e.g., video question answering) dictates a neural model to learn from offline-extracted dense video features from vision models and text features from language models. These feature extractors are trained independently and usually on tasks different from the target domains, rendering these fixed features sub-optimal for downstream tasks. Moreover, due to the high computational overload of dense video features, it is often difficult (or infeasible) to plug feature extractors directly into existing approaches for easy finetuning. To provide a remedy to this dilemma, we propose a generic framework CLIPBERT that enables affordable endto-end learning for video-and-language tasks, by employing sparse sampling, where only a single or a few sparsely sampled short clips from a video are used at each training step. Experiments on text-to-video retrieval and video question answering on six datasets demonstrate that CLIPBERT outperforms (or is on par with) existing methods that exploit full-length videos, suggesting that end-to-end learning with just a few sparsely sampled clips is often more accurate than using densely extracted offline features from full-length videos, proving the proverbial less-is-more principle. Videos in the datasets are from considerably different domains and lengths, ranging from 3-second genericdomain GIF videos to 180-second YouTube human activity videos, showing the generalization ability of our approach. Comprehensive ablation studies and thorough analyses are provided to dissect what factors lead to this success. Our code is publicly available.1

Vision-and-language pre-training has achieved impressive success in learning multimodal representations between vision and language. To generalize this success to non-English languages, we introduce UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning. To tackle the scarcity problem of multilingual captions for image datasets, we first augment existing English-only datasets with other languages via machine translation (MT). Then we extend the standard Masked Language Modeling and Image-Text Matching training objectives to multilingual setting, where alignment between different languages is captured through shared visual context (i.e., using image as pivot). To facilitate the learning of a joint embedding space of images and all languages of interest, we further propose two novel pre-training tasks, namely Masked Region-to-Token Modeling (MRTM) and Visual Translation Language Modeling (VTLM), leveraging MT-enhanced translated data. Evaluation on multilingual image-text retrieval and multilingual visual question answering benchmarks demonstrates that our proposed framework achieves new state of the art on diverse non-English benchmarks while maintaining comparable performance to monolingual pre-trained models on English tasks.

Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains unclear whether these state-of-the-art (SOTA) models are robust when encountering examples in the wild. To study this, we introduce Adversarial VQA, a new large-scale VQA benchmark, collected iteratively via an adversarial human-and-model-in-the-loop procedure. Through this new benchmark, we discover several interesting findings. (i) Surprisingly, we find that during dataset collection, non-expert annotators can easily attack SOTA VQA models successfully. (ii) Both large-scale pre-trained models and adversarial training methods achieve far worse performance on the new benchmark than over standard VQA v2 dataset, revealing the fragility of these models while demonstrating the effectiveness of our adversarial dataset. (iii) When used for data augmentation, our dataset can effectively boost model performance on other robust VQA benchmarks. We hope our Adversarial VQA dataset can shed new light on robustness study in the community and serve as a valuable benchmark for future work.

Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao, Lawrence Carin, Jingjing Liu. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

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. 2021.

Training generative adversarial networks (GANs) with limited real image data generally results in deteriorated performance and collapsed models. To conquer this challenge, we are inspired by the latest observation, that one can discover independently trainable and highly sparse subnetworks (a.k.a., lottery tickets) from GANs. Treating this as an inductive prior, we suggest a brand-new angle towards data-efficient GAN training: by first identifying the lottery ticket from the original GAN using the small training set of real images; and then focusing on training that sparse subnetwork by re-using the same set. We find our coordinated framework to offer orthogonal gains to existing real image data augmentation methods, and we additionally present a new feature-level augmentation that can be applied together with them. Comprehensive experiments endorse the effectiveness of our proposed framework, across various GAN architectures (SNGAN, BigGAN, and StyleGAN-V2) and diverse datasets (CIFAR-10, CIFAR-100, Tiny-ImageNet, ImageNet, and multiple few-shot generation datasets). Codes are available at: https://github.com/VITA-Group/Ultra-Data-Efficient-GAN-Training.

Lottery Ticket Hypothesis (LTH) raises keen attention to identifying sparse trainable subnetworks, or winning tickets, which can be trained in isolation to achieve similar or even better performance compared to the full models. Despite many efforts being made, the most effective method to identify such winning tickets is still Iterative Magnitude-based Pruning (IMP), which is computationally expensive and has to be run thoroughly for every different network. A natural question that comes in is: can we “transform” the winning ticket found in one network to another with a different architecture, yielding a winning ticket for the latter at the beginning, without re-doing the expensive IMP? Answering this question is not only practically relevant for efficient “once-for-all” winning ticket finding, but also theoretically appealing for uncovering inherently scalable sparse patterns in networks. We conduct extensive experiments on CIFAR-10 and ImageNet, and propose a variety of strategies to tweak the winning tickets found from different networks of the same model family (e.g., ResNets). Based on these results, we articulate the Elastic Lottery Ticket Hypothesis (E-LTH): by mindfully replicating (or dropping) and re-ordering layers for one network, its corresponding winning ticket could be stretched (or squeezed) into a subnetwork for another deeper (or shallower) network from the same family, whose performance is nearly the same competitive as the latter’s winning ticket directly found by IMP. We have also extensively compared E-LTH with pruning-at-initialization and dynamic sparse training methods, as well as discussed the generalizability of E-LTH to different model families, layer types, and across datasets. Code is available at https://github.com/VITA-Group/ElasticLTH.

Neural Module Network (NMN) exhibits strong interpretability and compositionality thanks to its handcrafted neural modules with explicit multi-hop reasoning capability. However, most NMNs suffer from two critical draw-backs: 1) scalability: customized module for specific function renders it impractical when scaling up to a larger set of functions in complex tasks; 2) generalizability: rigid pre-defined module inventory makes it difficult to generalize to unseen functions in new tasks/domains. To design a more powerful NMN architecture for practical use, we propose Meta Module Network (MMN) centered on a novel meta module, which can take in function recipes and morph into diverse instance modules dynamically. The instance modules are then woven into an execution graph for complex visual reasoning, inheriting the strong explainability and compositionality of NMN. With such a flexible instantiation mechanism, the parameters of instance modules are inherited from the central meta module, retaining the same model complexity as the function set grows, which promises better scalability. Meanwhile, as functions are encoded into the embedding space, unseen functions can be readily represented based on its structural similarity with previously observed ones, which ensures better generalizability. Experiments on GQA and CLEVR datasets validate the superiority of MMN over state-of-the-art NMN designs. Synthetic experiments on held-out unseen functions from GQA dataset also demonstrate the strong generalizability of MMN. Our code and model are released in Github1.

Previous storytelling approaches mostly focused on optimizing traditional metrics such as BLEU, ROUGE and CIDEr. In this paper, we re-examine this problem from a different angle, by looking deep into what defines a natural and topically-coherent story. To this end, we propose three assessment criteria: relevance, coherence and expressiveness, which we observe through empirical analysis could constitute a “high-quality” story to the human eye. We further propose a reinforcement learning framework, ReCo-RL, with reward functions designed to capture the essence of these quality criteria. Experiments on the Visual Storytelling Dataset (VIST) with both automatic and human evaluation demonstrate that our ReCo-RL model achieves better performance than state-of-the-art baselines on both traditional metrics and the proposed new criteria.

Large-scale pre-trained language model such as BERT has achieved great success in language understanding tasks.However, it remains an open question how to utilize BERT for language generation.In this paper, we present a novel approach, Conditional Masked Language Modeling (C-MLM), to enable the finetuning of BERT on target generation tasks.The finetuned BERT (teacher) is exploited as extra supervision to improve conventional Seq2Seq models (student) for better text generation performance.By leveraging BERT's idiosyncratic bidirectional nature, distilling knowledge learned in BERT can encourage auto-regressive Seq2Seq models to plan ahead, imposing global sequence-level supervision for coherent text generation.Experiments show that the proposed approach significantly outperforms strong Transformer baselines on multiple language generation tasks such as machine translation and text summarization.Our proposed model also achieves new state of the art on IWSLT German-English and English-Vietnamese MT datasets.1

Recently BERT has been adopted for document encoding in state-of-the-art text summarization models.However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries.Also, long-range dependencies throughout a document are not well captured by BERT, which is pre-trained on sentence pairs instead of documents.To address these issues, we present a discourse-aware neural summarization model -DISCOBERT 1 .DISCOBERT extracts sub-sentential discourse units (instead of sentences) as candidates for extractive selection on a finer granularity.To capture the long-range dependencies among discourse units, structural discourse graphs are constructed based on RST trees and coreference mentions, encoded with Graph Convolutional Networks.Experiments show that the proposed model outperforms state-of-the-art methods by a significant margin on popular summarization benchmarks compared to other BERT-base models.

We propose a new task towards more practical applications for image generation - high-quality image synthesis from salient object layout. This new setting requires users to provide only the layout of salient objects (i.e., foreground bounding boxes and categories) and lets the model complete the drawing with an invented background and a matching foreground. Two main challenges spring from this new task: (i) how to generate fine-grained details and realistic textures without segmentation map input; and (ii) how to create and weave a background into standalone objects in a seamless way. To tackle this, we propose Background Hallucination Generative Adversarial Network (BachGAN), which leverages a background retrieval module to first select a set of segmentation maps from a large candidate pool, then encodes these candidate layouts via a background fusion module to hallucinate a suitable background for the given objects. By generating the hallucinated background representation dynamically, our model can synthesize high-resolution images with both photo-realistic foreground and integral background. Experiments on Cityscapes and ADE20K datasets demonstrate the advantage of BachGAN over existing approaches, measured on both visual fidelity of generated images and visual alignment between output images and input layouts.

We introduce a new task, Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. A new large-scale dataset, named Violin (VIdeO-and-Language INference), is introduced for this task, which consists of 95,322 video-hypothesis pairs from 15,887 video clips, spanning over 582 hours of video. These video clips contain rich content with diverse temporal dynamics, event shifts, and people interactions, collected from two sources: (i) popular TV shows, and (ii) movie clips from YouTube channels. In order to address our new multimodal inference task, a model is required to possess sophisticated reasoning skills, from surface-level grounding (e.g., identifying objects and characters in the video) to in-depth commonsense reasoning (e.g., inferring causal relations of events in the video). We present a detailed analysis of the dataset and an extensive evaluation over many strong baselines, providing valuable insights on the challenges of this new task.

Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE.However, systemgenerated 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 multimasking strategies to either iteratively or autoregressively 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.* *Most of this work was done when the first author was an intern at Microsoft.CNNDM Source (CNN) About a quarter of a million Australian homes and businesses have no power after a "once in a decade" storm battered Sydney and nearby areas.About 4,500 people

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 multihop 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. 1

We present HERO, a novel framework for large-scale video+language omnirepresentation learning.HERO encodes multimodal inputs in a hierarchical structure, where local context of a video frame is captured by a Cross-modal Transformer via multimodal fusion, and global video context is captured by a Temporal Transformer.In addition to standard Masked Language Modeling (MLM) and Masked Frame Modeling (MFM) objectives, we design two new pre-training tasks: (i) Video-Subtitle Matching (VSM), where the model predicts both global and local temporal alignment; and (ii) Frame Order Modeling (FOM), where the model predicts the right order of shuffled video frames.HERO is jointly trained on HowTo100M and large-scale TV datasets to gain deep understanding of complex social dynamics with multi-character interactions.Comprehensive experiments demonstrate that HERO achieves new state of the art on multiple benchmarks over Text-based Video/Video-moment Retrieval, Video Question Answering (QA), Video-and-language Inference and Video Captioning tasks across different domains.We also introduce two new challenging benchmarks How2QA and How2R for Video QA and Retrieval, collected from diverse video content over multimodalities. 1

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 pretraining and finetuning stages, and achieves superb performance on the GLUE benchmark, outperforming state-of-the-art compression methods. 1

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.1

Cross-domain alignment between two sets of entities (e.g., objects in an image, words in a sentence) is fundamental to both computer vision and natural language processing. Existing methods mainly focus on designing advanced attention mechanisms to simulate soft alignment, where no training signals are provided to explicitly encourage alignment. Plus, the learned attention matrices are often dense and difficult to interpret. We propose Graph Optimal Transport (GOT), a principled framework that builds upon recent advances in Optimal Transport (OT). In GOT, cross-domain alignment is formulated as a graph matching problem, by representing entities as a dynamically-constructed graph. Two types of OT distances are considered: (i) Wasserstein distance (WD) for node (entity) matching; and (ii) Gromov-Wasserstein distance (GWD) for edge (structure) matching. Both WD and GWD can be incorporated into existing neural network models, effectively acting as a drop-in regularizer. The inferred transport plan also yields sparse and self-normalized alignment, enhancing the interpretability of the learned model. Experiments show consistent outperformance of GOT over baselines across a wide range of tasks, including image-text retrieval, visual question answering, image captioning, machine translation, and text summarization.

Most existing text-to-image synthesis tasks are static single-turn generation, based on pre-defined textual descriptions of images. To explore more practical and interactive real-life applications, we introduce a new task - Interactive Image Editing, where users can guide an agent to edit images via multi-turn textual commands on-the-fly. In each session, the agent takes a natural language description from the user as the input, and modifies the image generated in previous turn to a new design, following the user description. The main challenges in this sequential and interactive image generation task are two-fold: 1) contextual consistency between a generated image and the provided textual description; 2) step-by-step region-level modification to maintain visual consistency across the generated image sequence in each session. To address these challenges, we propose a novel Sequential Attention Generative Adversarial Network (SeqAttnGAN), which applies a neural state tracker to encode the previous image and the textual description in each turn of the sequence, and uses a GAN framework to generate a modified version of the image that is consistent with the preceding images and coherent with the description. To achieve better region-specific refinement, we also introduce a sequential attention mechanism into the model. To benchmark on the new task, we introduce two new datasets, Zap-Seq and DeepFashion-Seq, which contain multi-turn sessions with image-description sequences in the fashion domain. Experiments on both datasets show that the proposed SeqAttnGAN model outperforms state-of-the-art approaches on the interactive image editing task across all evaluation metrics including visual quality, image sequence coherence and text-image consistency.

We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning. Instead of adding adversarial perturbations on image pixels and textual tokens, we propose to perform adversarial training in the embedding space of each modality. To enable large-scale training, we adopt the ``free'' adversarial training strategy, and combine it with KL-divergence-based regularization to promote higher invariance in the embedding space. We apply VILLA to current best-performing V+L models, and achieve new state of the art on a wide range of tasks, including Visual Question Answering, Visual Commonsense Reasoning, Image-Text Retrieval, Referring Expression Comprehension, Visual Entailment, and NLVR2.

Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectively boost training efficiency using simulated experiences generated by the world model. The effectiveness of Dyna-Q, however, depends on the quality of the world model - or implicitly, the pre-specified ratio of real vs. simulated experiences used for Q-learning. To this end, we extend the recently proposed Deep Dyna-Q (DDQ) framework by integrating a switcher that automatically determines whether to use a real or simulated experience for Q-learning. Furthermore, we explore the use of active learning for improving sample efficiency, by encouraging the world model to generate simulated experiences in the stateaction space where the agent has not (fully) explored. Our results show that by combining switcher and active learning, the new framework named as Switch-based Active Deep Dyna-Q (Switch-DDQ), leads to significant improvement over DDQ and Q-learning baselines in both simulation and human evaluations.1

This paper presents a new model for visual dialog, Recurrent Dual Attention Network (ReDAN), using multi-step reasoning to answer a series of questions about an image. In each question-answering turn of a dialog, ReDAN infers the answer progressively through multiple reasoning steps. In each step of the reasoning process, the semantic representation of the question is updated based on the image and the previous dialog history, and the recurrently-refined representation is used for further reasoning in the subsequent step. On the VisDial v1.0 dataset, the proposed ReDAN model achieves a new state-of-the-art of 64.47% NDCG score. Visualization on the reasoning process further demonstrates that ReDAN can locate context-relevant visual and textual clues via iterative refinement, which can lead to the correct answer step-by-step.

Intelligent personal assistant systems that are able to have multi-turn conversations with human users are becoming increasingly popular. Most previous research has been focused on using either retrieval-based or generation-based methods to develop such systems. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. However, the performance of the methods is limited by the size of the response repository. On the other hand, generation-based methods can produce highly coherent responses on any topics. But the generated responses are often generic and not informative due to the lack of grounding knowledge. In this paper, we propose a hybrid neural conversation model that combines the merits of both response retrieval and generation methods. Experimental results on Twitter and Foursquare data show that the proposed model outperforms both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model) under both automatic evaluation metrics and human evaluation. We hope that the findings in this study provide new insights on how to integrate text retrieval and text generation models for building conversation systems.

We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) Vision-and-Language navigation challenge of Anderson et. al. (2018). Given a natural language instruction and photo-realistic image views of a previously unseen environment, the agent was tasked with navigating from source to target location as quickly as possible. While all current approaches make local action decisions or score entire trajectories using beam search, ours balances local and global signals when exploring an unobserved environment. Importantly, this lets us act greedily but use global signals to backtrack when necessary. Applying FAST framework to existing state-of-the-art models achieved a 17% relative gain, an absolute 6% gain on Success rate weighted by Path Length (SPL)1.

In this work, we propose a new task called Story Visualization. Given a multi-sentence paragraph, the story is visualized by generating a sequence of images, one for each sentence. In contrast to video generation, story visualization focuses less on the continuity in generated images (frames), but more on the global consistency across dynamic scenes and characters -- a challenge that has not been addressed by any single-image or video generation methods. Therefore, we propose a new story-to-image-sequence generation model, StoryGAN, based on the sequential conditional GAN framework. Our model is unique in that it consists of a deep Context Encoder that dynamically tracks the story flow, and two discriminators at the story and image levels, to enhance the image quality and the consistency of the generated sequences. To evaluate the model, we modified existing datasets to create the CLEVR-SV and Pororo-SV datasets. Empirically, StoryGAN outperformed state-of-the-art models in image quality, contextual consistency metrics, and human evaluation.

Siqi Sun, Yu Cheng, Zhe Gan, Jingjing 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). 2019.

Huazheng Wang, Zhe Gan, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Hongning Wang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

In order to answer semantically-complicated questions about an image, a Visual Question Answering (VQA) model needs to fully understand the visual scene in the image, especially the interactive dynamics between different objects. We propose a Relation-aware Graph Attention Network (ReGAT), which encodes each image into a graph and models multi-type inter-object relations via a graph attention mechanism, to learn question-adaptive relation representations. Two types of visual object relations are explored: (i) Explicit Relations that represent geometric positions and semantic interactions between objects; and (ii) Implicit Relations that capture the hidden dynamics between image regions. Experiments demonstrate that ReGAT outperforms prior state-of-the-art approaches on both VQA 2.0 and VQA-CP v2 datasets. We further show that ReGAT is compatible to existing VQA architectures, and can be used as a generic relation encoder to boost the model performance for VQA.

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users.One common alternative is to use a user simulator.However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent.To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning.We incorporate into the dialogue agent a model of the environment, referred to as the world model, to mimic real user response and generate simulated experience.During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience.The effectiveness of our approach is demonstrated on a movie-ticket booking task in both simulated and human-in-theloop settings 1 .

We investigate the problem of Language-Based Image Editing (LBIE). Given a source image and a natural language description, we want to generate a target image by editing the source image based on the description. We propose a generic modeling framework for two subtasks of LBIE: language-based image segmentation and image colorization. The framework uses recurrent attentive models to fuse image and language features. Instead of using a fixed step size, we introduce for each region of the image a termination gate to dynamically determine after each inference step whether to continue extrapolating additional information from the textual description. The effectiveness of the framework is validated on three datasets. First, we introduce a synthetic dataset, called CoSaL, to evaluate the end-to-end performance of our LBIE system. Second, we show that the framework leads to state-of-the-art performance on image segmentation on the ReferIt dataset. Third, we present the first language-based colorization result on the Oxford-102 Flowers dataset.

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning.To obviate DDQ's high dependency on the quality of simulated experiences, we incorporate an RNN-based discriminator in D3Q to differentiate simulated experience from real user experience in order to control the quality of training data.Experiments show that D3Q significantly outperforms DDQ by controlling the quality of simulated experience used for planning.The effectiveness and robustness of D3Q is further demonstrated in a domain extension setting, where the agent's capability of adapting to a changing environment is tested. 1

This paper presents a new method - adversarial advantage actor-critic (Adversarial A2C), which significantly improves the efficiency of dialogue policy learning in task-completion dialogue systems. Inspired by generative adversarial networks (GAN), we train a discriminator to differentiate responses/actions generated by dialogue agents from responses/actions by experts. Then, we incorporate the discriminator as another critic into the advantage actor-critic (A2C) framework, to encourage the dialogue agent to explore state-action within the regions where the agent takes actions similar to those of the experts. Experimental results in a movie-ticket booking domain show that the proposed Adversarial A2C can accelerate policy exploration efficiently.

Content-based image retrieval (CBIR) shows great significance in clinical decision-making, which explores the visual content of medical images rather than keywords, tags, or descriptions. It provides doctors an image-guided approach to explore relevant cases that could offer doctors instructive reference. Mammogram screening has been known to be widely used in the early stage diagnosis of breast cancer and could reduce its morbidity and mortality. In this paper, we aim to develop a scalable CBIR method for a large repository of mammogram. To this end, we extend the original Anchor Graph Hashing (AGH) and propose a new unsupervised hashing algorithm, named as composite AGH with iterative quantization (C-AGH-ITQ), which compresses mammographic regions of interest (ROIs) into compact binary codes and enables real-time searching in Hamming space. Multimodal features and different distance metrics are integrated, performing upon a composite Anchor Graph. To improve the effectiveness of the hash code, quantization error is further iteratively minimized by introducing an orthogonal rotation matrix. We evaluate the presented C-AGH-ITQ algorithm on a data set of 11 533 mammographic ROIs obtained from the Digital Database for Screening Mammography. Our method obtains more than 84% retrieval precision and 93% classification accuracy (using$k$NN prediction), which demonstrates that hash codes produced by C-AGH-ITQ well capture the visual similarities between mammographic images. In addition, since C-AGH-ITQ ensures linear complexity of the training procedure and constant time for query, our system is readily applicable to large-scale mammogram databases and has the potential to provide abundant clinical cases as reference.

Exploiting contextual cues has been a key idea to improve people detection in crowded scenes. Along this line we present a novel context-driven approach to detect people in crowded scenes. Based on a context graph that incorporates both geometric and social contextual patterns in crowds, we apply label propagation to discover weak detections contextually compatible with true detections while suppressing irrelevant false alarms. Compared to previous approaches for context modeling limited to only pairwise spatial interactions between local object neighbors, our approach provides a more effective way to model people interactions in a global context. Our approach achieves performance comparable to state of the art on two challenging datasets for people and pedestrian detection.

Most recent question answering (QA) systems query large-scale knowledge bases (KBs) to answer a question, after parsing and transforming natural language questions to KBs-executable forms (e.g., logical forms). As a well-known fact, KBs are far from complete, so that information required to answer questions may not always exist in KBs. In this paper, we develop a new QA system that mines answers directly from the Web, and meanwhile employs KBs as a significant auxiliary to further boost the QA performance. Specifically, to the best of our knowledge, we make the first attempt to link answer candidates to entities in Freebase, during answer candidate generation. Several remarkable advantages follow: (1) Redundancy among answer candidates is automatically reduced. (2) The types of an answer candidate can be effortlessly determined by those of its corresponding entity in Freebase. (3) Capitalizing on the rich information about entities in Freebase, we can develop semantic features for each answer candidate after linking them to Freebase. Particularly, we construct answer-type related features with two novel probabilistic models, which directly evaluate the appropriateness of an answer candidate's types under a given question. Overall, such semantic features turn out to play significant roles in determining the true answers from the large answer candidate pool. The experimental results show that across two testing datasets, our QA system achieves an 18%~54% improvement under F_1 metric, compared with various existing QA systems.