Xin Zhang, Guangwei Xu, Yueheng Sun, Meishan Zhang, Pengjun Xie. 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.

Personalized news recommendation aims to help users find news content they prefer, which has attracted increasing attention recently. There are two core issues in news recommendation: learning news representation and matching candidate news with user interests. In this context, “candidate” indicates potential for interest. Due to the superior ability to understand natural language demonstrated by Pretrained Language Models (PLMs), recent works utilize PLMs (e.g., BERT) to strengthen news modeling, obtaining more accurate user interest matching and achieving notable improvement in news recommendation. However, the existing PLM-based methods are usually incapable of fully exploring the fine-grained (i.e., word-level) relatedness between user behaviors and candidate news due to the heavy computational cost brought by PLMs. In this article, we propose a group-based personalized news recommendation method with long- and short-term matching mechanisms between users and candidate news based on PLMs to learn fine-grained matching efficiently and effectively. In our approach, we design to group user historical clicked news into chunks with quite shorter news sequences according to their clicked timestamps, which could alleviate the computation issues of PLMs. PLMs are applied in each group jointly with the candidate news to capture their word-level interaction, and global group-level matching is learned across different groups. In addition, the group-based mechanism could be naturally adapted for long- and short-term user representation learning, in which we build users’ long preferences from the representations of all groups and treat the last group as short interests, respectively. Finally, we employ a gate network to dynamically unify the group-level, long- and short-term representations, yielding comprehensive user-news matching effectively. Extensive experiments are conducted on two real-world datasets. The results show that our proposed method achieves superior performance in news recommendations.

Unsupervised cross-lingual transfer has been shown great potentials for dependency parsing of the low-resource languages when there is no annotated treebank available. Recently, the self-training method has received increasing interests because of its state-of-the-art performance in this scenario. In this work, we advance the method further by coupling it with curriculum learning, which guides the self-training in an easy-to-hard manner. Concretely, we present a novel metric to measure the instance difficulty of a dependency parser which is trained mainly on a Treebank from a resource-rich source language. By using the metric, we divide a low-resource target language into several fine-grained sub-languages by their difficulties, and then apply iterative-self-training progressively on these sub-languages. To fully explore the auto-parsed training corpus from sub-languages, we exploit an improved parameter generation network to model the sub-languages for better representation learning. Experimental results show that our final curriculum-style self-training can outperform a range of strong baselines, leading to new state-of-the-art results on unsupervised cross-lingual dependency parsing. We also conduct detailed experimental analyses to examine the proposed approach in depth for comprehensive understandings.

Multi-label text classification has a wide range of applications in the real world. However, the data distribution in the real world is often imbalanced, which leads to serious long-tailed problems. For multi-label classification, due to the vast scale of datasets and existence of label co-occurrence, how to effectively improve the prediction accuracy of tail labels without degrading the overall precision becomes an important challenge. To address this issue, we propose A Dual-Branch Learning Model with Gradient-Balanced Loss (DBGB) based on the paradigm of existing pre-trained multi-label classification SOTA models. Our model consists of two main long-tailed module improvements. First, with the shared text representation, the dual-classifier is leveraged to process two kinds of label distributions; one is the original data distribution and the other is the under-sampling distribution for head labels to strengthen the prediction for tail labels. Second, the proposed gradient-balanced loss can adaptively suppress the negative gradient accumulation problem related to labels, especially tail labels. We perform extensive experiments on three multi-label text classification datasets. The results show that the proposed method achieves competitive performance on overall prediction results compared to the state-of-the-art methods in solving the multi-label classification, with significant improvement on tail-label accuracy.

Exploring and understanding the temporal structure of dynamic networks attract extensive attentions over the past few years. Most of these current research focuses on temporal community detection, evolution analysis or link prediction from a mission-oriented perspective. In fact, these three tasks should be not isolated but mutually reinforcing. Transforming these three tasks into a unified framework, it is crucial to extract the evolution pattern, which helps to understand the time-varying characteristics of temporal structure in essence. In addition, to the best of our knowledge, there is no work focusing on modeling and uncovering the local and global evolution pattern hidden in temporal community structure simultaneously. In this paper, we propose a novel framework based on Orthogonal Nonnegative Matrix Factorization to Explore the Evolution Pattern (ONMF-EEP) for analyzing and predicting the time-varying structures in dynamic networks from local and global perspectives. The nature of this framework assumes that community structures are subject to a local evolution pattern (LEP) at each snapshot, and these LEPs are from a common global evolution pattern (GEP). The framework can synchronously detect temporal community structure, extract evolution pattern, and predict structure including communities and future snapshot links. The extensive experiments on real-world networks and artificial networks demonstrate that our proposed framework is highly effective on the tasks of dynamic network analysis.