Automatic Word Sense Discrimination

By Hinrich Schütze. 1998

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

Zero-Shot Learning Through Cross-Modal Transfer (2013, methodology): “racteristics – most often their co-occurrences with words in context [25, 9, 1, 32]. These representations have proven very effective in natural language processing tasks such as sense disambiguation [29], thesaurus extraction [23, 8] and cognitive modeling [20]. We initialize all word vectors with ”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Schütze (1998) used a fifty-word window (±25 words, centered on the target word).”
Experimental Support for a Categorical Compositional Distributional Model of Meaning (2011, background): “Compositional type-logical approaches (Montague, 1974; Lambek, 2008) and distributional models of lexical semantics (Schutze, 1998; Firth, 1957) have provided two partial orthogonal solutions to the question.”
A Structured Vector Space Model for Word Meaning in Context (2008, methodology): “There have been several approaches in the literature (Smolensky, 1990; Schütze, 1998; Kintsch, 2001; McDonald and Brew, 2004; Mitchell and Lapata, 2008) that compute meaning in context from lemma vectors.”
Learning Accurate, Compact, and Interpretable Tree Annotation (2006, background): “These kinds of syntactico-semantic categories are typical, and, given distributional clustering results like those of Schuetze (1998), unsurprising.”
Mathematical Foundations for a Compositional Distributional Model of Meaning (2010, methodology): “1 Vector space models of meaning The key idea behind vector space models of meaning [36] can be summed up by Firth’s oft-quoted dictum that “you shall know a word by the company it keeps”.”
Embedding Words and Senses Together via Joint Knowledge-Enhanced Training (2016, background): “senting them into separate vectors (Schütze, 1998; Reisinger and Mooney, 2010; Huang et al., 2012; Neelakantan et al., 2014).”
Neural context embeddings for automatic discovery of word senses (2015, methodology): “This approach was pioneered by Sch¨utze (1998) using second order co-occurrences to construct the context representation.”
Unsupervised Does Not Mean Uninterpretable: The Case for Word Sense Induction and Disambiguation (2017, methodology): “However, most approaches to word sense induction and disambiguation, e.g. (Sch¨utze, 1998; Li and Juraf-sky, 2015; Bartunov et al., 2016), rely on clustering methods and dense vector representations that make a WSD model uninterpretable as compared to knowledge-based WSD methods.”
Learning Word Representations with Hierarchical Sparse Coding (2014, methodology): “We use the movie reviews dataset from Socher et al. (2013).”
Structured Lexical Similarity via Convolution Kernels on Dependency Trees (2011, background): “…Brandes, 2001; Zhao et al., 2009), as well as combining structural and lexical similarity over semantic networks, e.g. (Cowie et al., 1992; Wu and Palmer, 1994; Resnik, 1995; Jiang and Conrath, 1997; Schtze, 1998; Leacock and Chodorow, 1998; Pedersen et al., 2004a; Budanitsky and Hirst, 2006).”
Discovering word senses from a network of lexical cooccurrences (2004, methodology): “The second main trend, found in (Schütze, 1998), (Pedersen and Bruce, 1997) and (Puran-dare, 2003), represents each instance of a target word by a set of features that occur in its neighborhood and applies an unsupervised clustering algorithm to all its instances.”