Embedding Methods for Fine Grained Entity Type Classification

By Dani Yogatama, D. Gillick, Nevena Lazic. 2015

126 citations recorded by the source corpus.

We propose a new approach to the task of fine grained entity type classifications based on label embeddings that allows for information sharing among related labels. Specifically, we learn an embedding for each label and each feature such that labels which frequently co-occur are close in the embedded space. We show that it outperforms state-of-the-art methods on two fine grained entity-classification benchmarks and that the model can exploit the finer-grained labels to improve classification of standard coarse types.

Subfields: Artificial Intelligence, Management Science and Operations Research

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

In Management Science and Operations Research

Citations in the corpus

Joint Embedding of Words and Labels for Text Classification (2018, background): “It is particularly successful on the task of zero-shot learning (Palatucci et al., 2009; Yogatama et al., 2015; Ma et al., 2016), where the label correlation captured in the embedding space can improve the prediction when some classes are unseen.”
Ultra-Fine Entity Typing (2018, methodology): “Researchers studied typing in varied contexts, including mentions in specific sentences (as we consider) (Ling and Weld, 2012; Gillick et al., 2014; Yogatama et al., 2015; Dong et al., 2015; Schutze et al., 2017), corpus-level prediction (Yaghoobzadeh and Schütze, 2016), and lexicon level (given…”
Label Embedding for Zero-shot Fine-grained Named Entity Typing (2016, methodology): “However, unlike (Yogatama et al., 2015), we use a relative threshold t to decide whether the selected type should remain in the final results, which is more consistent with the margin-infused objective function than a global threshold.”
CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases (2016, methodology): “Our proposed framework incorporates embedding techniques used in modeling words and phrases in large text corpora [30, 54, 45] ,and nodes and links in graphs/networks [50, 38].”
Knowledge Graphs (2020, unknown): “Distant supervision [319, 436, 572] uses known entities in a knowledge graph as seed examples through which similar entities can be detected.”
Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding (2016, methodology): “The presence of incorrect type labels in a mention’s candidate type set poses a unique challenge to estimating the relatedness between entity mentions and types using fully/semisupervised learning methods [34, 3, 33]—co-occurrence patterns alone between mentions and their candidate types in the corp”
Cross-lingual Name Tagging and Linking for 282 Languages (2017, background): “Many fine-grained entity typing approaches (Fleischman and Hovy, 2002; Giuliano, 2009; Ekbal et al., 2010; Ling and Weld, 2012; Yosef et al., 2012; Nakashole et al., 2013; Gillick et al., 2014; Yogatama et al., 2015; Del Corro et al., 2015) also created annotations based on Wikipedia anchor links.”