Heterogeneous network representation learning: A unified framework with survey and benchmark

C Yang, Y **ao, Y Zhang, Y Sun… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Since real-world objects and their interactions are often multi-modal and multi-typed,
heterogeneous networks have been widely used as a more powerful, realistic, and generic …

Empower sequence labeling with task-aware neural language model

L Liu, J Shang, X Ren, F Xu, H Gui, J Peng… - Proceedings of the AAAI …, 2018 - ojs.aaai.org
Linguistic sequence labeling is a general approach encompassing a variety of problems,
such as part-of-speech tagging and named entity recognition. Recent advances in neural …

DAGA: Data augmentation with a generation approach for low-resource tagging tasks

B Ding, L Liu, L Bing, C Kruengkrai, TH Nguyen… - arxiv preprint arxiv …, 2020 - arxiv.org
Data augmentation techniques have been widely used to improve machine learning
performance as they enhance the generalization capability of models. In this work, to …

Learning named entity tagger using domain-specific dictionary

J Shang, L Liu, X Ren, X Gu, T Ren, J Han - arxiv preprint arxiv …, 2018 - arxiv.org
Recent advances in deep neural models allow us to build reliable named entity recognition
(NER) systems without handcrafting features. However, such methods require large …

Scimine: An efficient systematic prioritization model based on richer semantic information

F Guo, Y Luo, L Yang, Y Zhang - … of the 46th International ACM SIGIR …, 2023 - dl.acm.org
Systematic review is a crucial method that has been widely used. by scholars from different
research domains. However, screening for relevant scientific literature from paper …

Reinforcement-learning based portfolio management with augmented asset movement prediction states

Y Ye, H Pei, B Wang, PY Chen, Y Zhu… - Proceedings of the AAAI …, 2020 - ojs.aaai.org
Portfolio management (PM) is a fundamental financial planning task that aims to achieve
investment goals such as maximal profits or minimal risks. Its decision process involves …

Keyphrase generation with correlation constraints

J Chen, X Zhang, Y Wu, Z Yan, Z Li - arxiv preprint arxiv:1808.07185, 2018 - arxiv.org
In this paper, we study automatic keyphrase generation. Although conventional approaches
to this task show promising results, they neglect correlation among keyphrases, resulting in …

Contextualized weak supervision for text classification

D Mekala, J Shang - Proceedings of the 58th Annual Meeting of …, 2020 - aclanthology.org
Weakly supervised text classification based on a few user-provided seed words has recently
attracted much attention from researchers. Existing methods mainly generate pseudo-labels …

Teleclass: Taxonomy enrichment and llm-enhanced hierarchical text classification with minimal supervision

Y Zhang, R Yang, X Xu, R Li, J **ao, J Shen… - arxiv preprint arxiv …, 2024 - arxiv.org
Hierarchical text classification aims to categorize each document into a set of classes in a
label taxonomy. Most earlier works focus on fully or semi-supervised methods that require a …

Empirical analysis of unlabeled entity problem in named entity recognition

Y Li, L Liu, S Shi - arxiv preprint arxiv:2012.05426, 2020 - arxiv.org
In many scenarios, named entity recognition (NER) models severely suffer from unlabeled
entity problem, where the entities of a sentence may not be fully annotated. Through …