Word Sense Discrimination Task

A Word Sense Discrimination Task is a word-level analysis task that requires Word Form Sets that are in a synonym relation.

• Context:
  • Input: Background Knowledge or/and Text Corpus.
  • output: a Word Sense Cluster Set (such as a thesaurus).
  • It can be solved by a Word Sense Discrimination System (that implements a Word Sense Discrimination algorithm).
  • It can range from being a Heuristic Word Sense Discrimination Task to being a Data-Driven Word Sense Discrimination Task (such as supervised WSD).
  • It can support a Word Sense Disambiguation Task.
  • …
• Counter-Example(s):
  • Word Sense Clustering Task,
• See: Terminological Unit Extraction; Information Extraction.

---

---

References

2011

• (Sammut & Webb, 2011) ⇒ Claude Sammut, and Geoffrey I. Webb. (2011). “Word Sense Discrimination.” In: (Sammut & Webb, 2011) p.1030

2005

• (Mihalcea & Petersen, 2005) ⇒ Rada Mihalcea, and Ted Pedersen. (2005). “Advances in Word Sense Disambiguation." Tutorial at ACL-2005.
  • Word sense discrimination is the problem of dividing the usages of a word into different meanings, without regard to any particular existing sense inventory.

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
  • … We present a clustering algorithm called CBC (Clustering By Committee) that automatically discovers word senses from text.

1998

• (Schütze, 1998) ⇒ Hinrich Schütze. (1998). “Automatic Word Sense Discrimination.” In: Computational Linguistics, 24(1).
  • Word sense disambiguation is the task of assigning sense labels to occurrences of an ambiguous word. This problem can be divided into two subproblems: sense discrimination and sense labeling. Sense discrimination divides the occurrences of a word into a number of classes by determining for any two occurrences whether they belong to the same sense or not. ... In this paper, we will address the problem of sense discrimination as defined above.
• (Lin, 1998b) ⇒ Dekang Lin. (1998). “Automatic Retrieval and Clustering of Similar Words.” In: Proceedings of the ACL Conference (ACL 1998).

1994

• (Grefenstette, 1994) ⇒ Gregory Grefenstette. (1994). “Explorations in Automatic Thesaurus Discovery." Kluwer, ISBN:0792394682
  • Explorations in Automatic Thesaurus Discovery presents an automated method for creating a first-draft thesaurus from raw text. It describes natural processing steps of tokenization, surface syntactic analysis, and syntactic attribute extraction. From these attributes, word and term similarity is calculated and a thesaurus is created showing important common terms and their relation to each other, common verb--noun pairings, common expressions, and word family members.

---