Word Sense Disambiguation: The State of the Art

By Nancy Ide, Jean Véronis. 2005

1,041 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/dc98f1c3bed54ff12643f36d1382c60ee4235544

How researchers see this paper

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

Citations in the corpus

South-East European Times : A parallel corpus of Balkan languages , Francis Tyers and (2010, methodology): “We can divide the task of WSD into two basic steps: 1 (1) choosing a sense inventory, (2) assigning the meanings listed in the sense inventory to the word form in question, according to some algorithm (Ide & Véronis, 1998).”
Investigation of Zipf’s ‘law-of-meaning’ on Turkish corpora (2007, background): “There are several works that deal with the word meanings [5].”
That’s sick dude!: Automatic identification of word sense change across different timescales (2014, background): “Two of the fundamental components of a natural language communication are word sense discovery (Jones, 1986) and word sense disambiguation (Ide and Veronis, 1998).”
Toponym resolution in text: annotation, evaluation and applications of spatial grounding (2007, methodology): “See Ide and Véronis (1998) for a broad survey of the methods used in WSD and the state of the art before the arrival of SENSEVAL, as well as Snyder and Palmer (2004) for a more recent performance overview in the context of the SENSEVAL-3 evaluation.”
Ontology Matching (2007, background): “Dealing with this problem is known as word sense disambiguation (Lesk 1986; Ide and Véronis 1998).”
Discriminative Reranking for Semantic Parsing (2006, methodology): “Experimenting with other effective reranking algorithms, such as SVMs (Joachims, 2002) and MaxEnt (Charniak and Johnson, 2005), is also a direction of our future research.”
MANULEX: A grade-level lexical database from French elementary school readers (2004, background): “However, as pointed out by Ide and Véronis (1998), natural languages display rather complex structure and therefore it is not surprising that attempts to process them by simple deterministic algorithms do not always yield satisfactory results.”
Learning Semantic Parsers: An Important but Under-Studied Problem (2004, methodology): “…learning methods that could successfully acquire knowledge from large corpora for more tractable problems such as speech recognition, part-of-speech tagging, and syntactic parsing, significant progress has been made on these tasks over the past decade (Jelinek 1998; Manning & Schütze 1999).”
WordNet improves text document clustering (2003, background): “[13]), it has not been our intention to determine which one could be the most appropriate, but simply whether word sense disambiguation is needed at all.”
Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language (2014, background): “However, annotating sentences with the requisite parse trees (Marcus, Santorini, & Marcinkiewicz, 1993), word senses (Ide & J´eronis, 1998) and semantic roles (Kingsbury, Palmer, & Marcus, 2002) is a difﬁcult and expensive undertaking.”
An automatic approach to identify word sense changes in text media across timescales (2015, background): “Automatic discovery and disambiguation of word senses from a given text is an important and challenging problem that has been extensively studied in the literature (Spärk-Jones 1986; Ide and Veronis 1998; Schütze 1998; Navigli 2009).”
On the Use of Automatically Acquired Examples for All-Nouns Word Sense Disambiguation (2008, background): “…separate chapters to WSD (Manning & Sch¨utze, 1999; Jurafsky & Martin, 2000; Dale, Moisl, & Somers, 2000), special issues on WSD in NLP journals (Ide & Veronis, 1998; Edmonds & Kilgarriﬀ, 2002), and books devoted speciﬁcally to the issue (Ravin & Leacock, 2001; Stevenson, 2003; Agirre &…”
Ontologies improve text document clustering (2003, background): “[5]), it has not been our intention to determine which one could be the most appropriate, but simply whether word sense disambiguation is needed at all.”