Clustering Verbs Semantically According to their Alternation Behaviour

  title={Clustering Verbs Semantically According to their Alternation Behaviour},
  author={Sabine Schulte im Walde},
  booktitle={International Conference on Computational Linguistics},
Verbs were clustered semantically on the basis of their alternation behaviour, as characterised by their syntactic subcategorisation frames extracted from maximum probability parses of a robust statistical parser, and completed by assigning WordNet classes as selectional preferences to the frame arguments. The clustering was achieved (a) iteratively by measuring the relative entropy between the verbs' probability distributions over the frame types, and (b) by utilising a latent class analysis… 

Figures from this paper

Inducing German Semantic Verb Classes from Purely Syntactic Subcategorisation Information

Using probability distributions over verb subcategorisation frames, an intuitively plausible clustering of 57 verbs into 14 classes is obtained, and the automatic clustering was evaluated against independently motivated, hand-constructed semantic verb classes.

Deriving verb-meaning clusters from syntactic structure

This paper presents a methodology for using the argument structure of sentences, as encoded by the PropBank project, to develop clusters of verbs with similar meaning and usage. These clusters can be

Automatic Learning of Syntactic Verb Classes

An experiment devised to group Catalan verbs according to their syntactic behavior, using a clustering methodology applied to data extracted from a tagged corpus to acquire a small number of basic classes with a high level of accuracy.

Exploring Soft-Clustering for German (Particle) Verbs across Frequency Ranges

It is demonstrated that low-frequency German verbs are clustered significantly worse than midor high- frequencies German verbs, and that German complex verbs are in general more difficult to cluster than German base verbs.

First Attempt to Automatically Generate Hungarian Semantic Verb Classes

Aiming to create verb paraphrases to lay the foundation of sentence paraphrases I automatically created Hungarian semantic verb classes with k-means algorithm. The vector representation of verbs was

Verb Alternations and Their Impact on Frame Induction

This work discusses the influence that diathesis alternations have on frame induction, compares several possible frame structures for verbs in the causative alternation, and proposes a systematic analysis of alternating verbs that encodes their similarities as well as their differences.

Verb Frame Frequency as a Predictor of Verb Bias

Evidence is provided for the view that lexical preferences are records of prior linguistic experience and it is shown that a type of lexial syntactic preference can be approximated by verb frame frequencies extracted from a large, balanced corpus using computational learning techniques.

Experiments on the Choice of Features for Learning Verb Classes

Cl clustering experiments on 168 German verbs are presented, which present evidence for a linguistically defined limit on the usefulness of features which is driven by the idiosyncratic properties of the verbs and the specific attributes of the desired verb classification.

Clustering Polysemic Subcategorization Frame Distributions Semantically

A novel evaluation scheme is proposed which accounts for the effect of polysemy on the clusters, offering a good insight into the potential and limitations of semantically classifying undisambiguated SCF data.

Learning Verb Argument Structure from Minimally Annotated Corpora

This work shows that a subcategorization frame (SF) learning algorithm previously applied to Czech is used to extract SFs in English and the extracted SFs are evaluated by classifying verbs into verb alternation classes.



Automatic Verb Classification Using Distributions of Grammatical Features

It is concluded that corpus data is a usable repository of verb class information, and that corpus-driven extraction of grammatical features is a promising methodology for automatic lexical acquisition.

Acquiring Lexical Generalizations from Corpora: A Case Study for Diathesis Alternations

The extent to which verb diathesis alternations are empirically attested in corpus data is examined and the productivity of an alternation and the typicality of its members using type and token frequencies is estimated.

Role of Verbs in Document Analysis

The results show that articles in which communication verbs predominate tends to be opinion pieces, whereas articles with a high percentage of agreement verbs tend to be about mergers or legal cases.

Valence Induction with a Head-Lexicalized PCFG

This paper addresses the problem of constructing a lexicon of complementation frames or valences for open-class words by means of a learning tech on probabilistic lexicalized context free grammars and the expectation-maximi~";ation (EM) algorithm.

Verb Classes and Alternations in Bangla, German, English, and Korean

This report includes a survey and classification of several hundred verbs from these languages into the cross-linguistic equivalents of Levin''s classes, based on the English Verb Classes and Alternations of (Levin, 1993).

Verb Classes and Alternations

In this report, we investigate the relationship between the semantic and syntactic properties of verbs. Our work is based on the English Verb Classes and Alternations of (Levin, 1993). We explore how

Role of Word Sense Disalnbiguation in Lexical Acquisition: Predicting Semantics from Syntactic Cues

This paper addresses the issue of word-sense ambiguity in extraction from machine-readable resources for the construction of large-scale knowledge sources and shows that a 15-fold improvement can be achieved in deriving semantic information from syntactic cues if the authors first divide the Syntactic cues into distinct groupings that correlate with different word senses.

An Experiment on Learning Appropriate Selectional Restrictions From a Parsed Corpus

The method relays in the use of a wide-coverage noun taxonomy and a statistical measure of the co-occurrence of linguistic items to extract Selectional Restrictions at a variable level of abstraction from phrasally analyzed corpora.

Automatically Acquiring a Classification of Words

This Thesis is an investigation into how a meaningful classi cation of words can be automatically extracted from ordinary unaltered English text on the assumption that similar words of similar rôle

Automatic Semantic Classification of Verbs According to their Alternation Behaviour

The algorithm behaves slightly di erent to Resnik's who splits the number of times a certain noun appears in an argument position by the total number of classes it appears in, up to the top of the hierarchy, in order to describe the degree of uncertainty about the word's sense.