• Publications
  • Influence
Personalized entity recommendation: a heterogeneous information network approach
This paper proposes to combine heterogeneous relationship information for each user differently and aim to provide high-quality personalized recommendation results using user implicit feedback data and personalized recommendation models. Expand
Automated Phrase Mining from Massive Text Corpora
This paper proposes a novel framework for automated phrase mining, which supports any language as long as a general knowledge base in that language is available, while benefiting from, but not requiring, a POS tagger. Expand
Empower Sequence Labeling with Task-Aware Neural Language Model
A novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task by leveraging character-level knowledge from self-contained order information of training sequences is developed. Expand
Learning Named Entity Tagger using Domain-Specific Dictionary
After identifying the nature of noisy labels in distant supervision, a novel, more effective neural model AutoNER is proposed with a new Tie or Break scheme and how to refine distant supervision for better NER performance is discussed. Expand
CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning
A constrained text generation task, CommonGen associated with a benchmark dataset, to explicitly test machines for the ability of generative commonsense reasoning, and demonstrates that the learned generative Commonsense reasoning capability can be transferred to improve downstream tasks such as CommonsenseQA by generating additional context. Expand
Collaborative Filtering with Entity Similarity Regularization in Heterogeneous Information Networks
Researchers have been studying hybrid recommender systems which combine user-item rating data with external information in recent years. Some studies suggest that by leveraging additional user and /Expand
HMEAE: Hierarchical Modular Event Argument Extraction
A Hierarchical Modular Event Argument Extraction model is proposed, to provide effective inductive bias from the concept hierarchy of event argument roles and significantly outperform the state-of-the-art baselines. Expand
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering
A novel knowledge-aware approach that equips pre-trained language models (PTLMs) with a multi-hop relational reasoning module, namedmulti-hop graph relation network (MHGRN), which performs multi-Hop, multi-relational reasoning over subgraphs extracted from external knowledge graphs. Expand
Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning
A multi-task learning framework for BioNER is proposed to collectively use the training data of different entity types and improve the performance on each of them, which outperforms state-of-the-art systems and other neural network models by a large margin. Expand
Hierarchical Text Classification with Reinforced Label Assignment
The proposed method, HiLAP, explores the hierarchy during both training and inference time in a consistent manner and makes inter-dependent decisions and outperforms state-of-the-art HTC methods by a large margin. Expand