Text-based Semantic Class Expansion Task
(Redirected from Text-based Semantic Class Expansion)
Jump to navigation
Jump to search
A text-based semantic class expansion task is a semantic class expansion task that extracts members of a semantic classes from a text.
- AKA: Corpus-based Semantic Class Expansion, Entity Set Expansion.
- Context:
- It can be a Text-based Named Entity Extraction Task if the Semantic Class is restricted to Entity Types.
- It is unclear how much Disambiguation is required (implemented).
- It can be solved by a Text-based Semantic Class Expansion System (that implements a Text-based Semantic Class Expansion Algorithm.
- Example(s):
- an Entity Mention Set Expansion Task, such as:
- given a Person Set, find more persons / Person Mentions.
- given a Protein Set, find more Proteins / Protein Mentions.
- given an Organization Set, find more Organizations / Organization Mentions.
- …
- an Entity Mention Set Expansion Task, such as:
- Counter-Example(s):
- See: Word Mention to Word Sense Resolution Task.
References
2009
- (Zhang et al., 2009) ⇒ Huibin Zhang, Mingjie Zhu, Shuming Shi, and Ji-Rong Wen. (2009). “Employing Topic Models for Pattern-based Semantic Class Discovery.” In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL 2009).
- (Pantel et al., 2009) ⇒ Patrick Pantel, Eric Crestan, Arkady Borkovsky, Ana-Maria Popescu, and Vishnu Vyas. (2009). “Web-Scale Distributional Similarity and Entity Set Expansion.” In: Proceedings of EMNLP Conference (EMNLP 2009).
2007
- (Sarmento et al., 2007) ⇒ Luis Sarmento, Valentin Jijkoun, Maarten de Rijke\n, and Eugenio Oliveira. (2007). “"More like these": growing entity classes from seeds.” In: Proceedings of the sixteenth ACM conference on Conference on information and knowledge management (CIKM 2007). doi:10.1145/1321440.1321585
1998
- (Roark & Charniak, 1998) ⇒ Brian Roark, and Eugene Charniak. (1998). “Noun-Phrase Co-Occurrence Statistics for Semiautomatic Semantic Lexicon Construction.” In: Proceedings of the 17th International Conference on Computational Linguistics. doi:10.3115/980432.980751