Jianfeng Gao

is this you? claim profile


Partner Research Manager at Microsoft Research

  • Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing

    Variational autoencoders (VAEs) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. The VAE objective consists of two terms, (i) reconstruction and (ii) KL regularization, balanced by a weighting hyper-parameter β. One notorious training difficulty is that the KL term tends to vanish. In this paper we study scheduling schemes for β, and show that KL vanishing is caused by the lack of good latent codes in training the decoder at the beginning of optimization. To remedy this, we propose a cyclical annealing schedule, which repeats the process of increasing β multiple times. This new procedure allows the progressive learning of more meaningful latent codes, by leveraging the informative representations of previous cycles as warm re-starts. The effectiveness of cyclical annealing is validated on a broad range of NLP tasks, including language modeling, dialog response generation and unsupervised language pre-training.

    03/25/2019 ∙ by Hao Fu, et al. ∙ 22 share

    read it

  • The Design and Implementation of XiaoIce, an Empathetic Social Chatbot

    This paper describes the development of the Microsoft XiaoIce system, the most popular social chatbot in the world. XiaoIce is uniquely designed as an AI companion with an emotional connection to satisfy the human need for communication, affection, and social belonging. We take into account both intelligent quotient (IQ) and emotional quotient (EQ) in system design, cast human-machine social chat as decision-making over Markov Decision Processes (MDPs), and optimize XiaoIce for long-term user engagement, measured in expected Conversation-turns Per Session (CPS). We detail the system architecture and key components including dialogue manager, core chat, skills, and an empathetic computing module. We show how XiaoIce dynamically recognizes human feelings and states, understands user intents, and responds to user needs throughout long conversations. Since the release in 2014, XiaoIce has communicated with over 660 million users and succeeded in establishing long-term relationships with many of them. Analysis of large-scale online logs shows that XiaoIce has achieved an average CPS of 23, which is significantly higher than that of other chatbots and even human conversations.

    12/21/2018 ∙ by Li Zhou, et al. ∙ 10 share

    read it

  • Object-driven Text-to-Image Synthesis via Adversarial Training

    In this paper, we propose Object-driven Attentive Generative Adversarial Newtorks (Obj-GANs) that allow object-centered text-to-image synthesis for complex scenes. Following the two-step (layout-image) generation process, a novel object-driven attentive image generator is proposed to synthesize salient objects by paying attention to the most relevant words in the text description and the pre-generated semantic layout. In addition, a new Fast R-CNN based object-wise discriminator is proposed to provide rich object-wise discrimination signals on whether the synthesized object matches the text description and the pre-generated layout. The proposed Obj-GAN significantly outperforms the previous state of the art in various metrics on the large-scale COCO benchmark, increasing the Inception score by 27 score by 11 the new object-driven attention is provided through analyzing their mechanisms and visualizing their attention layers, showing insights of how the proposed model generates complex scenes in high quality.

    02/27/2019 ∙ by Wenbo Li, et al. ∙ 6 share

    read it

  • Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation

    We present FAST NAVIGATOR, a general framework for action decoding, which yields state-of-the-art results on the recent 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 must navigate from a source to a target location as quickly as possible. While all of current approaches make local action decisions or score entire trajectories with beam search, our framework seamlessly balances local and global signals when exploring the environment. Importantly, this allows us to act greedily, but use global signals to backtrack when necessary. Our FAST framework, applied to existing models, yielded a 17 gain on success rate weighted by path length (SPL).

    03/06/2019 ∙ by Liyiming Ke, et al. ∙ 6 share

    read it

  • ConvLab: Multi-Domain End-to-End Dialog System Platform

    We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments. ConvLab offers a set of fully annotated datasets and associated pre-trained reference models. As a showcase, we extend the MultiWOZ dataset with user dialog act annotations to train all component models and demonstrate how ConvLab makes it easy and effortless to conduct complicated experiments in multi-domain end-to-end dialog settings.

    04/18/2019 ∙ by Sungjin Lee, et al. ∙ 6 share

    read it

  • Challenges in Building Intelligent Open-domain Dialog Systems

    There is a resurgent interest in developing intelligent open-domain dialog systems due to the availability of large amounts of conversational data and the recent progress on neural approaches to conversational AI. Unlike traditional task-oriented bots, an open-domain dialog system aims to establish long-term connections with users by satisfying the human need for communication, affection, and social belonging. This paper reviews the recent works on neural approaches that are devoted to addressing three challenges in developing such systems: semantics, consistency, and interactiveness. Semantics requires a dialog system to not only understand the content of the dialog but also identify user's social needs during the conversation. Consistency requires the system to demonstrate a consistent personality to win users trust and gain their long-term confidence. Interactiveness refers to the system's ability to generate interpersonal responses to achieve particular social goals such as entertainment, conforming, and task completion. The works we select to present here is based on our unique views and are by no means complete. Nevertheless, we hope that the discussion will inspire new research in developing more intelligent dialog systems.

    05/13/2019 ∙ by Minlie Huang, et al. ∙ 5 share

    read it

  • Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading

    Although neural conversation models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to contentful neural conversation that jointly models response generation and on-demand machine reading. The key idea is to provide the conversation model with relevant long-form text on the fly as a source of external knowledge. The model performs QA-style reading comprehension on this text in response to each conversational turn, thereby allowing for more focused integration of external knowledge than has been possible in prior approaches. To support further research on knowledge-grounded conversation, we introduce a new large-scale conversation dataset grounded in external web pages (2.8M turns, 7.4M sentences of grounding). Both human evaluation and automated metrics show that our approach results in more contentful responses compared to a variety of previous methods, improving both the informativeness and diversity of generated output.

    06/06/2019 ∙ by Lianhui Qin, et al. ∙ 5 share

    read it

  • Towards Amortized Ranking-Critical Training for Collaborative Filtering

    Collaborative filtering is widely used in modern recommender systems. Recent research shows that variational autoencoders (VAEs) yield state-of-the-art performance by integrating flexible representations from deep neural networks into latent variable models, mitigating limitations of traditional linear factor models. VAEs are typically trained by maximizing the likelihood (MLE) of users interacting with ground-truth items. While simple and often effective, MLE-based training does not directly maximize the recommendation-quality metrics one typically cares about, such as top-N ranking. In this paper we investigate new methods for training collaborative filtering models based on actor-critic reinforcement learning, to directly optimize the non-differentiable quality metrics of interest. Specifically, we train a critic network to approximate ranking-based metrics, and then update the actor network (represented here by a VAE) to directly optimize against the learned metrics. In contrast to traditional learning-to-rank methods that require to re-run the optimization procedure for new lists, our critic-based method amortizes the scoring process with a neural network, and can directly provide the (approximate) ranking scores for new lists. Empirically, we show that the proposed methods outperform several state-of-the-art baselines, including recently-proposed deep learning approaches, on three large-scale real-world datasets. The code to reproduce the experimental results and figure plots is on Github: https://github.com/samlobel/RaCT_CF

    06/10/2019 ∙ by Sam Lobel, et al. ∙ 3 share

    read it

  • Budgeted Policy Learning for Task-Oriented Dialogue Systems

    This paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions (budget) for learning task-oriented dialogue agents. BCS consists of (1) a Poisson-based global scheduler to allocate budget over different stages of training; (2) a controller to decide at each training step whether the agent is trained using real or simulated experiences; (3) a user goal sampling module to generate the experiences that are most effective for policy learning. Experiments on a movie-ticket booking task with simulated and real users show that our approach leads to significant improvements in success rate over the state-of-the-art baselines given the fixed budget.

    06/02/2019 ∙ by Zhirui Zhang, et al. ∙ 2 share

    read it

  • ReasoNet: Learning to Stop Reading in Machine Comprehension

    Teaching a computer to read and answer general questions pertaining to a document is a challenging yet unsolved problem. In this paper, we describe a novel neural network architecture called the Reasoning Network (ReasoNet) for machine comprehension tasks. ReasoNets make use of multiple turns to effectively exploit and then reason over the relation among queries, documents, and answers. Different from previous approaches using a fixed number of turns during inference, ReasoNets introduce a termination state to relax this constraint on the reasoning depth. With the use of reinforcement learning, ReasoNets can dynamically determine whether to continue the comprehension process after digesting intermediate results, or to terminate reading when it concludes that existing information is adequate to produce an answer. ReasoNets have achieved exceptional performance in machine comprehension datasets, including unstructured CNN and Daily Mail datasets, the Stanford SQuAD dataset, and a structured Graph Reachability dataset.

    09/17/2016 ∙ by Yelong Shen, et al. ∙ 0 share

    read it

  • Combating Reinforcement Learning's Sisyphean Curse with Intrinsic Fear

    To use deep reinforcement learning in the wild, we might hope for an agent that can avoid catastrophic mistakes. Unfortunately, even in simple environments, the popular deep Q-network (DQN) algorithm is doomed by a Sisyphean curse. Owing to the use of function approximation, these agents may eventually forget experiences as they become exceedingly unlikely under a new policy. Consequently, for as long as they continue to train, DQNs may periodically repeat avoidable catastrophic mistakes. In this paper, we learn a reward shaping that accelerates learning and guards oscillating policies against repeated catastrophes. First, we demonstrate unacceptable performance of DQNs on two toy problems. We then introduce intrinsic fear, a new method that mitigates these problems by avoiding dangerous states. Our approach incorporates a second model trained via supervised learning to predict the probability of catastrophe within a short number of steps. This score then acts to penalize the Q-learning objective. Equipped with intrinsic fear, our DQNs solve the toy environments and improve on the Atari games Seaquest, Asteroids, and Freeway.

    11/03/2016 ∙ by Zachary C Lipton, et al. ∙ 0 share

    read it