Unsupervised Entity Linking with Abstract Meaning Representation

By Xiaoman Pan, Taylor Cassidy, Ulf Hermjakob, Heng Ji, Kevin Knight. 2015

99 citations recorded by the source corpus.

Most successful Entity Linking (EL) methods aim to link mentions to their referent entities in a structured Knowledge Base (KB) by comparing their respective contexts, often using similarity measures. While the KB structure is given, current methods have suffered from impoverished information representations on the mention side. In this paper, we demonstrate the effectiveness of Abstract Meaning Representation (AMR) (Banarescu et al., 2013) to select high quality sets of entity “collaborators” to feed a simple similarity measure (Jaccard) to link entity mentions. Experimental results show that AMR captures contextual properties discriminative enough to make linking decisions, without the need for EL training data, and that system with AMR parsing output outperforms hand labeled traditional semantic roles as context representation for EL. Finally, we show promising preliminary results for using AMR to select sets of “coherent” entity mentions for collective entity linking 1 .

Subfields: Information Retrieval & Search, Natural Language Processing

How researchers see this paper

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

In Information Retrieval & Search

In Natural Language Processing

Citations in the corpus

Improving Question Answering with External Knowledge (2019, methodology): “For concept disambiguation and linking, we simply adopt an existing unsupervised approach (Pan et al., 2015) that first selects high quality sets of concept collaborators to feed a simple similarity measure (i.”
Broad-coverage CCG Semantic Parsing with AMR (2015, background): “AMR (Banarescu et al., 2013) is a general-purpose meaning representation and has been used in a number of applications (Pan et al., 2015; Liu et al., 2015).”
Cross-lingual Name Tagging and Linking for 282 Languages (2017, methodology): “…reliable word translations from cross-lingual Wikipedia titles, which enables us to adopt unsupervised English entity linking techniques such as (Pan et al., 2015) to directly link translated English name mentions to English KB. Efforts to save annotation cost for name tagging: Some previous…”