Using a Semantic Concordance for Sense Identification

By George A. Miller, Martin Chodorow, S. Landes, Claudia Leacock, Robert G. Thomas. 1994

This paper proposes benchmarks for systems of automatic sense identification. A textual corpus in which open-class words had been tagged both syntactically and semantically was used to explore three statistical strategies for sense identification: a guessing heuristic, a most-frequent heuristic, and a co-occurrence heuristic. When no information about sense-frequencies was available, the guessing heuristic using the numbers of alternative senses in WordNet was correct 45% of the time. When statistics for sense-frequencies were derived from a semantic concordance, the assumption that each word is used in its most frequently occurring sense was correct 69% of the time; when that figure was calculated for polysemous words alone, it dropped to 58%. And when a co-occurrence heuristic took advantage of prior occurrences of words together in the same sentences, little improvement was observed. The semantic concordance is still too small to estimate the potential limits of a co-occurrence heuristic.

Subfields: Natural Language Processing

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

Deep Contextualized Word Representations (2018, methodology): “To do so, we ﬁrst use the biLM to compute representations for all words in Sem-Cor 3.0, our training corpus (Miller et al., 1994), and then take the average representation for each sense.”
Knowledge Enhanced Contextual Word Representations (2019, methodology): “For supervision, we combined the SemCor word sense disambiguation (WSD) dataset (Miller et al., 1994) with all lemma example usages from WordNet6 and link directly to synsets.”
Structural semantic interconnection: a knowledge-based approach to Word Sense Disambiguation (2005, unknown): “SemCor [20] is a corpus where each word in a sentence is assigned a sense selected from the WordNet sense inventory for that word;(10) an example of a SemCor document is the following:”
It Makes Sense: A Wide-Coverage Word Sense Disambiguation System for Free Text (2010, methodology): “We also provide classification models trained with examples collected from parallel texts, SEMCOR (Miller et al., 1994), and the DSO corpus (Ng and Lee, 1996).”
Integrating Folksonomies with the Semantic Web (2007, background): “For example, in WordNet, chapterhouse has as ancestors building (1 st level) and construction (2 nd level), while edifice has as ancestor construction (1 st level).”
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison (2017, methodology): “To ensure a fair comparison, all supervised systems use the same corpus for training: SemCor and Semcor+OMSTI 7 (see Section 4.2).”
Embeddings for Word Sense Disambiguation: An Evaluation Study (2016, methodology): “SemCor (Miller et al., 1994) is a manually sense-tagged corpus created by the WordNet project team at Princeton University.”