Alibaba Group

About: Alibaba Group is a company organization based out in Hangzhou, China. It is known for research contribution in the topics: Computer science & Terminal (electronics). The organization has 6810 authors who have published 7389 publications receiving 55653 citations. The organization is also known as: Alibaba Group Holding Limited & Alibaba Group (Cayman Islands).

Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching

Abstract: Deep text matching approaches have been widely studied for many applications including question answering and information retrieval systems. To deal with a domain that has insufficient labeled data, these approaches can be used in a Transfer Learning (TL) setting to leverage labeled data from a resource-rich source domain. To achieve better performance, source domain data selection is essential in this process to prevent the "negative transfer" problem. However, the emerging deep transfer models do not fit well with most existing data selection methods, because the data selection policy and the transfer learning model are not jointly trained, leading to sub-optimal training efficiency. In this paper, we propose a novel reinforced data selector to select high-quality source domain data to help the TL model. Specifically, the data selector "acts" on the source domain data to find a subset for optimization of the TL model, and the performance of the TL model can provide "rewards" in turn to update the selector. We build the reinforced data selector based on the actor-critic framework and integrate it to a DNN based transfer learning model, resulting in a Reinforced Transfer Learning (RTL) method. We perform a thorough experimental evaluation on two major tasks for text matching, namely, paraphrase identification and natural language inference. Experimental results show the proposed RTL can significantly improve the performance of the TL model. We further investigate different settings of states, rewards, and policy optimization methods to examine the robustness of our method. Last, we conduct a case study on the selected data and find our method is able to select source domain data whose Wasserstein distance is close to the target domain data. This is reasonable and intuitive as such source domain data can provide more transferability power to the model.

A Weakly Supervised Method for Topic Segmentation and Labeling in Goal-oriented Dialogues via Reinforcement Learning.

Abstract: Topic structure analysis plays a pivotal role in dialogue understanding. We propose a reinforcement learning (RL) method for topic segmentation and labeling in goal-oriented dialogues, which aims to detect topic boundaries among dialogue utterances and assign topic labels to the utterances. We address three common issues in the goal-oriented customer service dialogues: informality, local topic continuity, and global topic structure. We explore the task in a weakly supervised setting and formulate it as a sequential decision problem. The proposed method consists of a state representation network to address the informality issue, and a policy network with rewards to model local topic continuity and global topic structure. To train the two networks and offer a warm-start to the policy, we firstly use some keywords to annotate the data automatically. We then pre-train the networks on noisy data. Henceforth, the method continues to refine the data labels using the current policy to learn better state representations on the refined data for obtaining a better policy. Results demonstrate that this weakly supervised method obtains substantial improvements over state-of-the-art baselines.

Branch-Wise Parallel Successive Algorithm for Online Voltage Regulation in Distribution Networks

Abstract: Due to high penetration of distributed energy resources, voltage violation has become one of the most critical issues in control of modern power systems with integration of renewable distributed generations (DGs). In this paper, an online distributed approach is proposed to regulate voltage in radial distribution networks via DGs. By fully considering the topological properties of the radial distribution network, the proposed approach successfully decomposes the global voltage regulation problem into a sequence of local reactive power optimization subproblems with low dimensions. It has been further shown that the optimal solution of the global voltage regulation problem can be achieved by cyclically solving these local subproblems in a branch-wise parallel successive order. Compared with the existing literature, the proposed online distributed voltage regulation approach does not require synchronous updates of all the participants and can improve the performance of the distribution network during the process of its execution. The effectiveness, robustness to fast voltage fluctuations, convergence speed, and insensitivity to parameters of the proposed approach are validated by performing case studies.

Cross-language Citation Recommendation via Hierarchical Representation Learning on Heterogeneous Graph

Abstract: While the volume of scholarly publications has increased at a frenetic pace, accessing and consuming the useful candidate papers, in very large digital libraries, is becoming an essential and challenging task for scholars. Unfortunately, because of language barrier, some scientists (especially the junior ones or graduate students who do not master other languages) cannot efficiently locate the publications hosted in a foreign language repository. In this study, we propose a novel solution, cross-language citation recommendation via Hierarchical Representation Learning on Heterogeneous Graph (HRLHG), to address this new problem. HRLHG can learn a representation function by mapping the publications, from multilingual repositories, to a low-dimensional joint embedding space from various kinds of vertexes and relations on a heterogeneous graph. By leveraging both global (task specific) plus local (task independent) information as well as a novel supervised hierarchical random walk algorithm, the proposed method can optimize the publication representations by maximizing the likelihood of locating the important cross-language neighborhoods on the graph. Experiment results show that the proposed method can not only outperform state-of-the-art baseline models, but also improve the interpretability of the representation model for cross-language citation recommendation task.

ActiveHNE: Active Heterogeneous Network Embedding

Abstract: This work is supported by NSFC (61872300 and 61873214), Fundamental Research Funds for the Central Universities (XDJK2019B024), NSF of CQ CSTC (cstc2018jcyjAX0228 and cstc2016jcyjA0351), King Abdullah University of Science and Technology (KAUST), Saudi Arabia.