Distributional-based Word Relatedness Function

A Distributional-based Word Relatedness Function is a lexical relatedness function that is based on word co-occurrence patterns.

• AKA: Word-Space Model, Word Co-Occurrence-based Semantic Function.
• Context:
  • It can range from being a Continuous Distributional Word Relatedness Function to being a Discrete Distributional Word Relatedness Function.
  • It can range from being a Sparse Distributional Word Relatedness Function to being a Dense Distributional Word Relatedness Function.
  • It can be created by a Distributional Lexical Similarity Function Training Task.
  • …
• Example(s):
  • an word2vec Model.
  • …
• Counter-Example(s):
  • an n-Gram Language Model.
• See: Lexical Semantic Similarity Function, Skip-Gram Model, Text Sequence Likelihood, Next-Word Predictor.

---

---

References

2014

• (Evert, 2014) ⇒ Stefan Evert. (2014). “Distributional Semantics in R with the wordspace Package.” In: Proceedings of COLING, pp. 110-114. 2014.

2006

• (Sahlgren, 2006) ⇒ Magnus Sahlgren. (2006). “The Word-Space Model: Using Distributional Analysis to Represent Syntagmatic and Paradigmatic Relations Between Words in High-dimensional Vector Spaces." PhD. Thesis, Stockholm: Institutionen för Lingvistik
  • QUOTE: The word-space model is a computational model of word meaning that utilizes the distributional patterns of words collected over large text data to represent semantic similarity between words in terms of spatial proximity. The model has been used for over a decade, and has demonstrated its mettle in numerous experiments and applications. It is now on the verge of moving from research environments to practical deployment in commercial systems. Although extensively used and intensively investigated, our theoretical understanding of the word-space model remains unclear. The question this dissertation attempts to answer is: what kind of semantic information does the word-space model acquire and represent?

---