Xiaolei Lu

Xiaolei Lu

Auto-generated profile, based on publicly available information

Xiaolei Lu

University of California (San Diego), San Diego, CA, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 September 2019 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
XLXiaolei Lu
Xiaolei Lu
TCTommy W. S. Chow
Tommy W. S. Chow
Existing methods for keyphrase extraction need preprocessing to generate candidate phrase or post-processing to transform keyword into keyphrase. In this paper, we propose a novel approach called duration modeling with semi-Markov Conditional Random Fields (DM-SMCRFs) for keyphrase extraction. First of all, based on the property of semi-Markov chain, DM-SMCRFs can encode segment-level features and sequentially classify the phrase in the sentence as keyphrase or non-keyphrase. Second, by assuming the independence between state transition and state duration, DM-SMCRFs model the distribution of duration (length) of keyphrases to further explore state duration information, which can help identify the size of keyphrase. Based on the convexity of parametric duration feature derived from duration distribution, a constrained Viterbi algorithm is derived to improve the performance of decoding in DM-SMCRFs. We thoroughly evaluate the performance of DM-SMCRFs on the datasets from various domains. The experimental results demonstrate the effectiveness of proposed model.

9 January 2025 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
JMJianghong Ma
Jianghong Ma
RWRong Wang
Rong Wang
TWTianjun WEI
Tianjun WEI
KLKangzhe Liu
Kangzhe Liu
HZHaijun Zhang
Haijun Zhang
XLXiaolei Lu
Xiaolei Lu
Recommender systems are essential in the ever-evolving landscape of e-commerce and social media platforms, delivering personalized recommendations by predicting user preferences. However, the growing need for explainable recommendation has arisen to enhance transparency and persuasiveness. In response, we present correlation-driven explainable recommendation with aspect and rating boosted representation learning (CER-ARRL), a unified joint-ranking framework that capitalizes on the robust capabilities of neural collaborative filtering to model the intricate dynamics among users, items, and explanations. By extracting information from explicit and implicit user emotional reviews, our framework enriches the representations of users and items. This integration yields simultaneous improvements in both item recommendation and explanation ranking tasks. In addition, CER-ARRL effectively exploits the structural correlation between phrases as well as the structural and semantic correlations between emojis to facilitate explanation ranking. This work represents the pioneering work to address the item-explanation joint recommendation task by integrating both interpretative phrases and illustrative emojis. Through extensive experiments on various datasets, including our collected dataset, we demonstrate the superiority of the proposed method over existing baselines.

23 June 2020 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
XLXiaolei Lu
Xiaolei Lu
TCTommy W. S. Chow
Tommy W. S. Chow
Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates that can be false positive or similar to the ground-truth label. In this article, we propose a novel weak disambiguation for partial structured output learning (WD-PSL). First, a piecewise large margin formulation is generalized to partial structured output learning, which effectively avoids handling a large number of candidate-structured outputs for complex structures. Second, in the proposed weak disambiguation strategy, each candidate label is assigned with a confidence value indicating how likely it is the true label, which aims to reduce the negative effects of wrong ground-truth label assignment in the learning process. Then, two large margins are formulated to combine two types of constraints which are the disambiguation between candidates and noncandidates, and the weak disambiguation for candidates. In the framework of alternating optimization, a new 2n-slack variables cutting plane algorithm is developed to accelerate each iteration of optimization. The experimental results on several sequence labeling tasks of natural language processing show the effectiveness of the proposed model.

8 April 2021
Verified
Conference Paper
Open access
PDF file
XLXiaolei Lu
Xiaolei Lu
JQJing Qiu
Jing Qiu
RWRuiwu Wu
Ruiwu Wu
This study determined 7 indicators that affect the learning effect of online learning behaviors by consulting relevant literature materials, and used SPSS21.0 to analyse and research the learning behavior data of college students. The study found that the length of the online learning time interval has a significant impact on the online learning effect of college students. The learning effect of students in the short-time interval group is significantly higher than that of the students in the long-time interval group. Different time interval groups have a certain effect on students’ final exam results. Test efficiency, test completion rate, and test timeliness have significant effects on college students’ learning effects, while the number of forums initiated, the number of replies, and the average test attempt rate have little effect on learning effects. The results show that: decentralized learning is conducive to improving the online learning effect of college students; the online teaching platform should be more intelligent and have automatic reminder function; teaching resources should be based on knowledge points and suitable for fragmented learning; teachers should pay more attention to the learning process of students’ management, strengthen the supervision of teaching links; students should strengthen the training of knowledge points. This research provides an effective path for how to improve the teaching level of teachers and the learning effect of students under the new teaching mode.

29 March 2024 in arXiv
Verified
Preprint
Open access
PDF file
XLXiaolei Lu
Xiaolei Lu
JMJianghong Ma
Jianghong Ma
Explainability algorithms aimed at interpreting decision-making AI systems usually consider balancing two critical dimensions: 1) \textit{faithfulness}, where explanations accurately reflect the model's inference process. 2) \textit{plausibility}, where explanations are consistent with domain experts. However, the question arises: do faithfulness and plausibility inherently conflict? In this study, through a comprehensive quantitative comparison between the explanations from the selected explainability methods and expert-level interpretations across three NLP tasks: sentiment analysis, intent detection, and topic labeling, we demonstrate that traditional perturbation-based methods Shapley value and LIME could attain greater faithfulness and plausibility. Our findings suggest that rather than optimizing for one dimension at the expense of the other, we could seek to optimize explainability algorithms with dual objectives to achieve high levels of accuracy and user accessibility in their explanations.

19 October 2021 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
XLXiaolei Lu
Xiaolei Lu
TCTommy W. S. Chow
Tommy W. S. Chow
Crowd sequential annotations can be an efficient and cost-effective way to build large datasets for sequence labeling. Different from tagging independent instances, for crowd sequential annotations, the quality of label sequence relies on the expertise level of annotators in capturing internal dependencies for each token in the sequence. In this article, we propose modeling sequential annotation for sequence labeling with crowds (SA-SLC). First, a conditional probabilistic model is developed to jointly model sequential data and annotators’ expertise, in which categorical distribution is introduced to estimate the reliability of each annotator in capturing local and nonlocal label dependencies for sequential annotation. To accelerate the marginalization of the proposed model, a valid label sequence inference (VLSE) method is proposed to derive the valid ground-truth label sequences from crowd sequential annotations. VLSE derives possible ground-truth labels from the tokenwise level and further prunes subpaths in the forward inference for label sequence decoding. VLSE reduces the number of candidate label sequences and improves the quality of possible ground-truth label sequences. The experimental results on several sequence labeling tasks of Natural Language Processing show the effectiveness of the proposed model.