Word Mention to Word Sense Resolution Task
(Redirected from Word Sense Identification Task)
Jump to navigation
Jump to search
A Word Mention to Word Sense Resolution Task is a reference resolution task that requires the mapping of each word mention to a word sense referencer with the same referent.
- AKA: Word Mention to Concept Record Reference Normalization.
- Context:
- Input:
- a Word Segmented Text Item (e.g. produced by word mention detection)
- a Word Record Set.
- optional: a Training Set of Sense Tagged Expressions.
- output: a Sense Tagged Expression (with a word sense record identifier for some or all word mention whose sense is represented)
- It can be:
- a Word Sense Discrimination Task (where a Word Sense Inventory is NOT provided).
- a Word Sense Superclass Classification Task (where a Semantic Class Inventory is provided) such as a Named Entity Recognition Task.
- a Word Sense Classification Task (where a Word Sense Inventory is provided).
- It can range from being a Heuristic Word Mention to Word Sense Resolution Task to being a Data-Driven Word Mention to Word Sense Resolution Task (such as supervised word mention to word sense resolution).
- It can be an Interactive Word Mention to Word Sense Resolution Task (with Human Feedback).
- It can range from being an All-Words Word Sense Resolution Task (for all the words in the input) to being a Target-Word Word Sense Resolution Task (for some specified words in the input).
- It can range from being a Nontechnical Word Mention to Word Sense Resolution Task to being a Technical Term Mention to Word Sense Resolution Task.
- It can be solved by a Word Mention Reference Resolution System (that implements a Word Mention Reference Resolution Algorithm.
- It can be supported by a Word Mention Detection Task.
- It can assume that all Word Mentions have been accurately detected.
- It can support a Semantic Annotation Task.
- Input:
- Example(s):
- a Word Sense Disambiguation Task, if the Word Mention is for a Dictionary Word in a Dictionary (which assumes that the Word Sense Record is present).
- an Entity Mention Normalization Task, if the Word Sense Inventorys is restricted to an Entity Database.
- a Term Mention Reference Resolution Task, if the Word Mentions are restricted to Term Mentions, such as:
- [math]\displaystyle{ f }[/math]("The system supports tree-structured conditional random field models.”) ⇒ "The system supports tree-structured CRF models.
- …
- Counter-Example(s):
- See: DNA Segment Reference Resolution Task.
References
2011
- (Mihalcea, 2011) ⇒ Rada Mihalcea. (2011). “Word Sense Disambiguation" In: (Sammut & Webb, 2011) p.1027
2009
- (Navigli, 2009) ⇒ Roberto Navigli. (2009). “Word Sense Disambiguation: A survey.” In: ACM Computing Surveys (CSUR) 41(2). doi:10.1145/1459352.1459355
2002
- (Pantel & Lin, 2002b) ⇒ Patrick Pantel, and Dekang Lin. (2002). “Discovering Word Senses from Text.” In: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2002). doi:10.1145/775047.775138
1998
- (Schütze, 1998) ⇒ Hinrich Schütze. (1998). “Automatic Word Sense Discrimination.” In: Computational Linguistics, 24(1).
1995
- (Yarowsky, 1995) ⇒ David Yarowsky. (1995). “Unsupervised Word Sense Disambiguation Rivaling Supervised Methods." Proceedings of the 33rd annual meeting on Association for Computational Linguistics. http://dx.doi.org/10.3115/981658.981684
1994
- (Grefenstette, 1994) ⇒ Gregory Grefenstette. (1994). “Explorations in Automatic Thesaurus Discovery." Kluwer, ISBN:0792394682
1993
- (Leacock et al., 1993) ⇒ Claudia Leacock, Geoffrey Towell, and Ellen Voorhees. (1993). “Corpus-based Statistical Sense Resolution.” In: Proceedings of the workshop on Human Language Technology at HLT 1993.
1986
- (Lesk, 1986) ⇒ Michael Lesk. (1986). “Automatic Sense Disambiguation Uusing Machine Readable Dictionaries: How to tell a pine cone from a ice cream cone.” In: Proceedings of SIGDOC-1986.