Mention and Entity Description Co-Attention for Entity Disambiguation

By Feng Nie, Yunbo Cao, Jinpeng Wang, Chin-Yew Lin, Rong Pan. 2018

33 citations recorded by the source corpus.

For the task of entity disambiguation, mention contexts and entity descriptions both contain various kinds of information content while only a subset of them are helpful for disambiguation. In this paper, we propose a type-aware co-attention model for entity disambiguation, which tries to identify the most discriminative words from mention contexts and most relevant sentences from corresponding entity descriptions simultaneously. To bridge the semantic gap between mention contexts and entity descriptions, we further incorporate entity type information to enhance the co-attention mechanism. Our evaluation shows that the proposed model outperforms the state-of-the-arts on three public datasets. Further analysis also confirms that both the co-attention mechanism and the type-aware mechanism are effective.

Subfields: Artificial Intelligence, Information Extraction, Knowledge Graphs & Representation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sebastian Riedel
2. Fabio Petroni
3. Luke S. Zettlemoyer
4. Mohit Bansal
5. Hannaneh Hajishirzi
6. Xiao-Dan Zhu
7. Wen-tau Yih
8. Yejin Choi

In Information Extraction

1. Luke S. Zettlemoyer
2. Fabio Petroni
3. Sebastian Riedel

In Knowledge Graphs & Representation

1. QUAN LIU
2. Luke S. Zettlemoyer
3. Sebastian Riedel

Citations in the corpus

• Learning Dense Representations for Entity Retrieval (2019, neutral): “Nie et al. (2018) define a complex model that uses both entity type information and attention between the mention string and the entity description.”
• Scalable Zero-shot Entity Linking with Dense Entity Retrieval (2019, methodology): “WikilinksNED Unseen-Mentions was created by Onoe and Durrett (2019) from the original WikilinksNED dataset (Eshel et al.”
• Attention in Natural Language Processing (2019, methodology): “[88], whereby M1 and M2 are fed to a multilayer perceptron, as is done by Lu et al.”
• Program Enhanced Fact Verification with Verbalization and Graph Attention Network (2020, methodology): “Specifically, entity linking (Nie et al., 2018) detects relevant entities (i.e., cells in evidence table T ) in statement S using a set of string matching rules.”