TAC-KBP 2014 Entity Linking Task
Jump to navigation
Jump to search
A TAC-KBP 2014 Entity Linking Task is a TAC-KBP entity linking task created by TAC-2014 Entity Linking Track.
- Example(s):
- …
- Counter-Example(s):
- See: TAC-KBP 2014 Task.
References
2014
- http://nlp.cs.rpi.edu/kbp/2014/
- QUOTE: The Entity Linking (EL) task at NIST TAC-KBP2014 aims to extract named entities from a source collection of textual documents, and link them to an existing Knowledge Base (KB). An EL system is also required to cluster those NIL entities which don't have corresponding KB entries. This year the task includes the following tracks: Mono-lingual English EL (English text to English KB), Cross-lingual Chinese-to-English EL (Chinese text to English KB) and Cross-lingual Spanish-to-English (Spanish text to English KB).
- http://nlp.cs.rpi.edu/kbp/2014/KBP2014EL_V0.2.pdf
- QUOTE: The Entity Linking (EL) task at NIST TAC-KBP 2014 aims to extract named entities from a source collection of textual documents, and link them to an existing Knowledge Base (KB). An EL system is also required to cluster those NIL entities which don't have corresponding KB entries. This year the task includes the following tracks: English Mono-lingual Entity Discovery and Linking (English text to English KB), Chinese-to-English Cross-lingual Entity Linking (Chinese text to English KB), Spanish-to-English Cross-lingual Entity Linking (Spanish text to English KB).
Compared to the KBP entity linking evaluations in previous years, the main changes and improvement in KBP2014 include:
- Extend English task to Entity Discovery and Linking (full Entity Extraction + Entity Linking + NIL Clustering)
- Add discussion fora to Cross-lingual tracks (some entity morphs naturally exist in Chinese discussion fora)
- Provide basic NLP, full IE, Entity Linking and semantic annotations for some source documents
- Increase ambiguity and variety in query selection to ensure outstanding advanced algorithms to outperform naive baseline approaches
- Share some source collections and queries with regular and cold-start slot filling tracks
- QUOTE: The Entity Linking (EL) task at NIST TAC-KBP 2014 aims to extract named entities from a source collection of textual documents, and link them to an existing Knowledge Base (KB). An EL system is also required to cluster those NIL entities which don't have corresponding KB entries. This year the task includes the following tracks: English Mono-lingual Entity Discovery and Linking (English text to English KB), Chinese-to-English Cross-lingual Entity Linking (Chinese text to English KB), Spanish-to-English Cross-lingual Entity Linking (Spanish text to English KB).