joint learning of the embedding of words and entities for named entity disambiguation
TRANSCRIPT
![Page 1: Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://reader031.vdocuments.net/reader031/viewer/2022022411/58eb9d681a28ab24468b46c1/html5/thumbnails/1.jpg)
Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation
Ikuya Yamada1,2 Hiroyuki Shindo3 Hideaki Takeda4 Yoshiyasu Takefuji2
1Studio Ousia 2Keio University 3Nara Institute of Science and Technology 4National Institute of Informatics
![Page 2: Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://reader031.vdocuments.net/reader031/viewer/2022022411/58eb9d681a28ab24468b46c1/html5/thumbnails/2.jpg)
STUDIO OUSIA
Named Entity Disambiguation
‣ Named Entity Disambiguation (NED) is the task of resolving named entity mentions to their correct references in a knowledge base
2
/wiki/Frozen_(2013_film)
New Frozen Boutique to Open at Disney's Hollywood Studios
/wiki/The_Walt_Disney_Company
/wiki/Disney’s_Hollywood_Studios
![Page 3: Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://reader031.vdocuments.net/reader031/viewer/2022022411/58eb9d681a28ab24468b46c1/html5/thumbnails/3.jpg)
STUDIO OUSIA
Joint Learning of Embedding of Words and Entities
‣ The proposed method extends skip-gram model to map words and entities into the same continuous vector space
‣ Three models are combined to train the embedding:
‣ KB graph model (graph) learns to estimate neighboring entities given the entity in the link graph of Wikipedia
‣ Anchor context model (anchor) learns to predict neighboring words given the entity using anchors and their context words
‣ Conventional skip-gram model (word) learns to predict neighboring words given the target word
3
Wikipedia link graph Neighboring words of words and anchors
Aristotle�was�a�philosopher�+
Logic�
Science�
Europe� Socrates�Renaissance�
Metaphysics�
Philosopher�Philosophy�
Avicenna�Aristotle�Plato�
![Page 4: Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation](https://reader031.vdocuments.net/reader031/viewer/2022022411/58eb9d681a28ab24468b46c1/html5/thumbnails/4.jpg)
STUDIO OUSIA
‣We propose two simple context models based on the proposed embedding:
‣ Textual context: cosine similarity between the vector of the target entity and the average vector of noun words in a document
‣ Coherence: cosine similarity between the vector of the target entity and the average vector of other entities in a document
‣ These context models and standard NED features (e.g., prior probability and entity prior) are combined using supervised machine-learning (GBRT)
‣We achieved state-of-the-art accuracies on two popular NED datasets
4
SOTA accuracies on two popular datasets!