Discovering word senses from text

By Patrick Pantel, Dekang Lin. Knowledge Discovery and Data Mining, 2002

742 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/3317f2788b2b07d9ba4cb4335e29316fcf8a971a

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Corpus-based Learning of Analogies and Semantic Relations (2005, methodology): “…of individual concepts (Lesk, 1969; Church and Hanks, 1989; Dunning, 1993; Smadja, 1993; Resnik, 1995; Landauer and Dumais, 1997; Turney, 2001; Pantel and Lin, 2002), there has been relatively little work on measuring the similarity of semantic re-Table lationships between concepts…”
Improving Distributional Similarity with Lessons Learned from Word Embeddings (2015, background): “Like other smoothing techniques (Pantel and Lin, 2002; Turney and Littman, 2003), context distribution smoothing alleviates PMI’s bias towards rare words.”
Sense discovery via co-clustering on images and text (2015, background): “A significant amount of previous work has investigated the problem of automatically inducing word senses from statistics derived from text corpora [32, 7, 23].”
Neural context embeddings for automatic discovery of word senses (2015, methodology): “For vectors satisfying the conditions stated above, we have ψ semantic i,c = σ ( P MI ( w i , w c ) − log k ) , establishing a connection between the semantic weights applied to Skip-gram embeddings, and PMI, a function frequently used for measuring word similarity (Pantel and Lin, 2002).”
From Word Embeddings to Document Similarities for Improved Information Retrieval in Software Engineering (2016, background): “For example, Pantel and Lin [33] compute Mij as the pointwise mutual information (PMI) between wi and cj .”
Discovering word senses from a network of lexical cooccurrences (2004, methodology): “We chose to take up the evaluation method proposed in (Pantel and Lin, 2002).”
Extracting implicit knowledge from text (2009, methodology): “Terminal nodes of the resultant structure were used as the basis for inferring semantic type restrictions, reminiscent of the use of CBC clusters (Pantel and Lin, 2002) by Pantel et al.”
Unsupervised Does Not Mean Uninterpretable: The Case for Word Sense Induction and Disambiguation (2017, methodology): “Word ego-network clustering methods (Lin, 1998; Pantel and Lin, 2002; Widdows and Dorow, 2002; Biemann, 2006; Hope and Keller, 2013) cluster graphs of words semantically related to the ambiguous word.”
Analysing Lexical Semantic Change with Contextualised Word Representations (2020, background): “…step partitions usage representations into clusters of similar usages of the same word, or usage types (see Figure 1a), and thus it is directly related to automatic word sense discrimination (Sch¨utze, 1998; Pantel and Lin, 2002; Manandhar et al., 2010; Navigli and Vannella, 2013, among others).”
The Distributional Inclusion Hypotheses and Lexical Entailment (2005, background): “Concrete similarity measures compare a pair of weighted context feature vectors that characterize two words (Church and Hanks, 1990; Ruge, 1992; Pereira et al., 1993; Grefenstette, 1994; Lee, 1997; Lin, 1998; Pantel and Lin, 2002; Weeds and Weir, 2003).”
Evaluating the Inferential Utility of Lexical-Semantic Resources (2009, methodology): “CBC : A knowledgebase of labeled clusters generated by the statistical clustering and labeling algorithms in (Pantel and Lin, 2002; Pantel and Ravichandran, 2004) 5 .”
Similarity of Semantic Relations (2006, methodology): “The VSM approach has also been used to measure the attributional similarity of words (Lesk, 1969; Ruge, 1992; Pantel and Lin, 2002).”
Multi-Prototype Vector-Space Models of Word Meaning (2010, background): “from the words surrounding the target term (Pereira et al., 1993; Pantel and Lin, 2002).”
Finding Predominant Word Senses in Untagged Text (2004, neutral): “There has been some related work on using automatic thesauruses for discovering word senses from corpora Pantel and Lin (2002).”
A Joint Model for Extended Semantic Role Labeling (2011, methodology): “We also used the CBC word clusters of Pantel and Lin (2002) as additional gazetteers and Brown cluster features as used by Ratinov and Roth (2009) and Koo et al. (2008).”
Domain and Function: A Dual-Space Model of Semantic Relations and Compositions (2012, background): “It should be possible to extend past work with polysemy in VSMs to the dual-space model (Schütze, 1998; Pantel & Lin, 2002; Erk & Padó, 2008).”