Near-Synonymy and Lexical Choice

By Philip Edmonds, Graeme Hirst. International Conference on Computational Logic, 2002

304 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/69f89d88dd025806b741b0fa56c9ff73adbd6c2a

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

Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods (2010, background): “Finally, we also do not discuss the notion of near-synonymy (Hirst 1995; Edmonds and Hirst 2002).”
On learning and representing social meaning in NLP: a sociolinguistic perspective (2021, background): “There is a large body of work on generating text in speciﬁc styles (e.g., Edmonds and Hirst (2002); Ficler and Goldberg (2017); Mairesse and Walker (2011)).”
From distributional to semantic similarity (2004, methodology): “, 2001), topic categories from Roget’s thesaurus (Mandala et al., 1999; Nastase and Szpakowicz, 2001) and information from LDOCE (Kwong, 1998). Stevenson (2002) uses three different similarity metrics to align WORDNET with CIDE+ to augment WORDNET with related term links.”
A survey on sentiment detection of reviews (2009, unknown): “…& Reichenbach , 2004): one based on hypernymy as provided by WordNet (Budanitsky & Hirst, 2001; Curran, 2002; Devitt & Vogel, 2004; Edmonds, 1999; Edmonds & Hirst, 2002; Fellbaum, 1998; Grefenstette, 1994; Justeson & Slava, 1993; Kamps & Maarten, 2002; Rapp, 2004; Riloff & Shepherd, 1997; Roark…”
Formal Distributional Semantics: Introduction to the Special Issue (2016, background): “For instance, imagine formalizing, in such a system, the distinction between near-synonyms such as man/gentleman/chap/lad/guy/dude/bloke (Edmonds and Hirst 2002; Boleda and Erk 2015).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “More often, lexicalisation is harder, for at least two reasons (cf. Bangalore & Rambow, 2000): First, it can involve selection between semantically similar, near-synonymous or taxonomically related words (e.g. animal vs dog; Stede, 2000; Edmonds & Hirst, 2002).”
Choosing words in computer-generated weather forecasts (2005, background): “Perhaps the best-known previous research on choosing between words with similar meanings is Edmonds and Hirst’s [8] model of near-synonym choice.”
Contextual Valence Shifters (2006, background): “(Edmonds & Hirst 2002; Hatzivassiloglou and McKeown 1997; Turney& Littman 2002; Wiebe et al. 2001, In Press).”
Roget's thesaurus and semantic similarity (2012, methodology): “People identify synonyms — strictly speaking, nearsynonyms (Edmonds and Hirst, 2002) — such as angel – cherub, without being able to define synonymy properly.”