Fan Wang

Bio: Fan Wang is an academic researcher from Baidu. The author has contributed to research in topics: Computer science & Reinforcement learning. The author has an hindex of 10, co-authored 55 publications receiving 469 citations. Previous affiliations of Fan Wang include Chinese Academy of Sciences & Center for Excellence in Education.

PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable

Abstract: Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering. In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation. We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation. Two reciprocal tasks of response generation and latent act recognition are designed and carried out simultaneously within a shared network. Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.

Learning to Select Knowledge for Response Generation in Dialog Systems

Abstract: End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few previous work has focused on selecting appropriate knowledge in the learning process. The inappropriate selection of knowledge could prohibit the model from learning to make full use of the knowledge. Motivated by this, we propose an end-to-end neural model which employs a novel knowledge selection mechanism where both prior and posterior distributions over knowledge are used to facilitate knowledge selection. Specifically, a posterior distribution over knowledge is inferred from both utterances and responses, and it ensures the appropriate selection of knowledge during the training process. Meanwhile, a prior distribution, which is inferred from utterances only, is used to approximate the posterior distribution so that appropriate knowledge can be selected even without responses during the inference process. Compared with the previous work, our model can better incorporate appropriate knowledge in response generation. Experiments on both automatic and human evaluation verify the superiority of our model over previous baselines.

PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable

Abstract: Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering. In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation. We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation. Two reciprocal tasks of response generation and latent act recognition are designed and carried out simultaneously within a shared network. Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.

ConSTGAT: Contextual Spatial-Temporal Graph Attention Network for Travel Time Estimation at Baidu Maps

Abstract: The task of travel time estimation (TTE), which estimates the travel time for a given route and departure time, plays an important role in intelligent transportation systems such as navigation, route planning, and ride-hailing services. This task is challenging because of many essential aspects, such as traffic prediction and contextual information. First, the accuracy of traffic prediction is strongly correlated with the traffic speed of the road segments in a route. Existing work mainly adopts spatial-temporal graph neural networks to improve the accuracy of traffic prediction, where spatial and temporal information is used separately. However, one drawback is that the spatial and temporal correlations are not fully exploited to obtain better accuracy. Second, contextual information of a route, i.e., the connections of adjacent road segments in the route, is an essential factor that impacts the driving speed. Previous work mainly uses sequential encoding models to address this issue. However, it is difficult to scale up sequential models to large-scale real-world services. In this paper, we propose an end-to-end neural framework named ConSTGAT, which integrates traffic prediction and contextual information to address these two problems. Specifically, we first propose a spatial-temporal graph neural network that adopts a novel graph attention mechanism, which is designed to fully exploit the joint relations of spatial and temporal information. Then, in order to efficiently take advantage of the contextual information, we design a computationally efficient model that applies convolutions over local windows to capture a route's contextual information and further employs multi-task learning to improve the performance. In this way, the travel time of each road segment can be computed in parallel and in advance. Extensive experiments conducted on large-scale real-world datasets demonstrate the superiority of ConSTGAT. In addition, ConSTGAT has already been deployed in production at Baidu Maps, and it successfully keeps serving tens of billions of requests every day. This confirms that ConSTGAT is a practical and robust solution for large-scale real-world TTE services.

PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning

Abstract: To build a high-quality open-domain chatbot, we introduce the effective training process of PLATO-2 via curriculum learning. There are two stages involved in the learning process. In the first stage, a coarse-grained generation model is trained to learn response generation under the simplified framework of one-to-one mapping. In the second stage, a fine-grained generative model augmented with latent variables and an evaluation model are further trained to generate diverse responses and to select the best response, respectively. PLATO-2 was trained on both Chinese and English data, whose effectiveness and superiority are verified through comprehensive evaluations, achieving new state-of-the-art results.

A Simple Language Model for Task-Oriented Dialogue

Abstract: Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2. SimpleTOD improves over the prior state-of-the-art by 0.49 points in joint goal accuracy for dialogue state tracking. More impressively, SimpleTOD also improves the main metrics used to evaluate action decisions and response generation in an end-to-end setting for task-oriented dialog systems: inform rate by 8.1 points, success rate by 9.7 points, and combined score by 7.2 points.

A Survey of Applications and Human Motion Recognition with Microsoft Kinect

Abstract: Microsoft Kinect, a low-cost motion sensing device, enables users to interact with computers or game consoles naturally through gestures and spoken commands without any other peripheral equipment. As such, it has commanded intense interests in research and development on the Kinect technology. In this paper, we present, a comprehensive survey on Kinect applications, and the latest research and development on motion recognition using data captured by the Kinect sensor. On the applications front, we review the applications of the Kinect technology in a variety of areas, including healthcare, education and performing arts, robotics, sign language recognition, retail services, workplace safety training, as well as 3D reconstructions. On the technology front, we provide an overview of the main features of both versions of the Kinect sensor together with the depth sensing technologies used, and review literatures on human motion recognition techniques used in Kinect applications. We provide a classification of motion recognition techniques to highlight the different approaches used in human motion recognition. Furthermore, we compile a list of publicly available Kinect datasets. These datasets are valuable resources for researchers to investigate better methods for human motion recognition and lower-level computer vision tasks such as segmentation, object detection and human pose estimation.

TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue

Abstract: The underlying difference of linguistic patterns between general text and task-oriented dialogue makes existing pre-trained language models less useful in practice. In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling. To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling. We propose a contrastive objective function to simulate the response selection task. Our pre-trained task-oriented dialogue BERT (TOD-BERT) outperforms strong baselines like BERT on four downstream task-oriented dialogue applications, including intention recognition, dialogue state tracking, dialogue act prediction, and response selection. We also show that TOD-BERT has a stronger few-shot ability that can mitigate the data scarcity problem for task-oriented dialogue.