Word Space

By Hinrich Schütze. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Enriching Word Vectors with Subword Information (2016, methodology): “Our approach, which incorporates character n -grams into the skipgram model, is related to an idea that was introduced by Schütze (1993).”
Advances in Pre-Training Distributed Word Representations (2017, background): “A simple yet effective approach is to enrich the word vectors with a bag of character n-gram vectors that is either derived from the singular value decomposition of the co-occurence matrix (Sch¨utze, 1993) or directly learned from a large corpus of data (Bojanowski et al., 2017).”
Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD (2012, background): “…that simple word – word co-occurrence statistics from large text corpora are able to capture certain aspects of word meaning, and a number of different approaches for doing that have been proposed (e.g., Landauer & Dumais, 1997; Lund & Burgess, 1996; Patel, Bullinaria, & Levy, 1997; Schütze, 1993).”
An Introduction to Random Indexing (2005, unknown): “An Introduction to Random Indexing”
The Unstoppable Rise of Computational Linguistics in Deep Learning (2020, unknown): “(Deerwester et al., 1990; Schütze, 1993; Burgess, 1998; Padó and Lapata, 2007; Erk, 2010)).”
Word Embeddings Go to Italy: A Comparison of Models and Training Datasets (2015, background): “Research on word representation models [19,20], word embeddings, has gained a lot of attention in the recent years [9].”
Compositional Matrix-Space Models of Language (2010, background): “In computational linguistics and information retrieval, Vector Space Models (Salton et al., 1975) and its variations – such as Word Space Models (Schütze, 1993), Hyperspace Analogue to Language (Lund and Burgess, 1996), or Latent Semantic Analysis (Deerwester et al., 1990) – have become a…”
Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL (2001, methodology): “Various measures of semantic similarity between word pairs have been proposed, some using statistical (unsupervised learning from text) techniques [16, 17, 18], some using lexical databases (hand-built) [19, 20], and some hybrid approaches, combining statistics and lexical information [21, 22].”
A Neural Probabilistic Language Model (2003, background): “The idea of using a vector-space representation for words h as been well exploited in the area of information retrieval(for example see [12]), where vectorial feature vectors for words are learned on the basis of their probability of co -occurring in the same documents (Latent Semantic Indexing [4])”