Heterogeneous network representation learning: A unified framework with survey and benchmark
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 …
heterogeneous networks have been widely used as a more powerful, realistic, and generic …
Empower sequence labeling with task-aware neural language model
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 …
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
Data augmentation techniques have been widely used to improve machine learning
performance as they enhance the generalization capability of models. In this work, to …
performance as they enhance the generalization capability of models. In this work, to …
Learning named entity tagger using domain-specific dictionary
Recent advances in deep neural models allow us to build reliable named entity recognition
(NER) systems without handcrafting features. However, such methods require large …
(NER) systems without handcrafting features. However, such methods require large …
Scimine: An efficient systematic prioritization model based on richer semantic information
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 …
research domains. However, screening for relevant scientific literature from paper …
Reinforcement-learning based portfolio management with augmented asset movement prediction states
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 …
investment goals such as maximal profits or minimal risks. Its decision process involves …
Keyphrase generation with correlation constraints
In this paper, we study automatic keyphrase generation. Although conventional approaches
to this task show promising results, they neglect correlation among keyphrases, resulting in …
to this task show promising results, they neglect correlation among keyphrases, resulting in …
Contextualized weak supervision for text classification
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 …
attracted much attention from researchers. Existing methods mainly generate pseudo-labels …
Teleclass: Taxonomy enrichment and llm-enhanced hierarchical text classification with minimal supervision
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 …
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 …
entity problem, where the entities of a sentence may not be fully annotated. Through …