Papers by Tiansi Dong

5 papers
Joint Representation Learning of Cross-lingual Words and Entities via Attentive Distant Supervision (D18-1)

Copied to clipboard

Challenge: Existing methods for learning word and entity representations in monolingual settings are limited.
Approach: They propose a method for joint representation learning of cross-lingual words and entities that captures mutually complementary knowledge and enables cross-linguistic inferences.
Outcome: The proposed method captures mutually complementary knowledge and enables cross-lingual inferences among knowledge bases and texts.
Interpretable and Low-Resource Entity Matching via Decoupling Feature Learning from Decision Making (2021.acl-long)

Copied to clipboard

Challenge: Entity Matching (EM) aims at recognizing entity records that denote the same real-world object.
Approach: They propose a novel EM framework that consists of Heterogeneous Information Fusion and Key Attribute Tree Induction to decouple feature representation from matching decision.
Outcome: The proposed framework outperforms SOTA EM models on 6 public datasets and 3 industrial datasets.
How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing? (2022.findings-acl)

Copied to clipboard

Challenge: Extensive experiments on multi-lingual datasets show that our method significantly outperforms multiple baselines and can robustly handle negative transfer.
Approach: They propose to transfer semantic knowledge from rich-resourced languages to low-resource languages by using multilingual transfer learning.
Outcome: The proposed model outperforms baselines and can handle negative transfer.
Attributed and Predictive Entity Embedding for Fine-Grained Entity Typing in Knowledge Bases (C18-1)

Copied to clipboard

Challenge: Existing methods for identifying semantic type of entities are incomplete even in large knowledge bases.
Approach: They propose an attributed and predictive entity embedding method which can fully utilize various kinds of information comprehensively.
Outcome: Experiments on two real DBpedia datasets show that the proposed method outperforms 8 state-of-the-art methods with 4.0% improvement in Mi-F1 and 5.2% improvement in Ma-F1.
Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks (D19-1)

Copied to clipboard

Challenge: Existing methods for inferring the fine-grained type of an entity from knowledge base are incomplete and lack type information.
Approach: They propose a novel Deep Learning architecture to infer the fine-grained type of an entity from a knowledge base.
Outcome: The proposed method significantly outperforms four state-of-the-art methods on two large-scale datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations