A general feature space for automatic verb classification

Abstract

We develop a general feature space for automatic classification of verbs into lexical semantic classes. Previous work was limited in scope by the need for manual selection of discriminating features, through a linguistic analysis of the target verb classes (Merlo and Stevenson, 2001). We instead analyze the classification structure at a higher level, using the possible defining characteristics of classes as the basis for our feature space. The general feature space achieves reductions in error rates of 42-69%, on a wider range of classes than investigated previously, with comparable performance to feature sets manually selected for the particular classification tasks. Our results show that the approach is generally applicable, and avoids the need for resource-intensive linguistic analysis for each new task.

Do as I say, not as I do: A lexical distributional account of English locative verb class acquisition

“…For example, if cover occurs frequently in the LT structure (e.g., I covered the table with paper) and never in the TL structure (e.g., *I covered paper onto the table), then cover is assigned to a verb class that only allows the LT structure. Another approach to distributional learning is to assign syntax-relevant semantics using the words that co-occur with the verb (Dorr & Jones, 1996;Dumais & Landauer, 1997;Joanis, Stevenson & James, 2008;Resnik, 1996;Rohde, Gonnerman & Plaut, 2006;Riordan & Jones, 2011;Sun and Korhonen, 2009;Redington et al, 1998). For example, if a child hears the utterance He is sloshing paint around, the child classifies slosh with other verbs that take paint as an object (e.g., the man poured paint into the bucket; the girl spilled paint on the table), creating a verb class based on word distributional similarities.…”

Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation

“…Approaches which aim to learn verb classes automatically offer an attractive alternative. However, existing methods rely on carefully engineered features that are extracted using sophisticated language-specific resources (Joanis et al, 2008;Sun et al, 2010;Falk et al, 2012, i.a. ), ranging from accurate parsers to pre-compiled subcategorisation frames (Schulte im Walde, 2006;Li and Brew, 2008;Messiant, 2008).…”

Automatic lexical classification: bridging research and practice

“…They concluded that syntactic information about core constituents occurring with a verb (syntactic slots) is most important for verb classification. Finally, the unsupervised method of Sun & Korhonen (2009) performs quite similarly to the supervised approach of Joanis et al (2008), yielding an accuracy of 57.6. Sun & Korhonen used a variation of spectral clustering and experimented with a variety of features (e.g.…”

“…Therefore, most works on automatic verb classification have used syntactic frames as basic features, exploiting the fact that verbs taking similar alternations take similar SCFs. For example, Joanis et al (2008) have used shallow syntactic slots (e.g. the relative frequency of noun phrases following specific verbs) to approximate the frames.…”

“…GS1 The gold standard of Joanis et al (2008). When frequency-based selection criteria are applied and the class imbalance is restricted, this gold standard provides a classification of 205 verbs in 15 (some broad, some fine-grained) Levin classes.…”