• Corpus ID: 8568496

Determining the Degree of Compositionality of German Particle Verbs by Clustering Approaches

  title={Determining the Degree of Compositionality of German Particle Verbs by Clustering Approaches},
  author={Natalie K{\"u}hner and Sabine Schulte im Walde},
This work determines the degree of compositionality of German particle verbs by two soft clustering approaches. We assume that the more compositional a particle verb is, the more often it appears in the same cluster with its base verb, after applying a probability threshold to establish cluster membership. As German particle verbs are difficult to approach automatically at the syntax-semantics interface, because they typically change the subcategorisation behaviour in comparison to their base… 

Tables from this paper

German particle verbs: Compositionality at the syntax-semantics interface

This work computationally assess the levels of particle verb compositionality, with the use of distributional semantic methods, and investigates properties of German particle verbs that are relevant for their compositionality: the particular subcategorization behavior of particle verbs and their corresponding base verbs.

Optimizing a Distributional Semantic Model for the Prediction of German Particle Verb Compositionality

It is shown that theranking of distributional similarity correlates significantly with the ranking of human judgements on semantic compositionality for a series of Particle Verbs and the Base Verbs they are derived from.

Modelling Regular Subcategorization Changes in German Particle Verbs

German particle verbs are a type of multi word expression which is often compositional with respect to a base verb. If they are compositional they tend to express the same types of semantic

Syntactic Transfer Patterns of German Particle Verbs and their Impact on Lexical Semantics

This paper demonstrates that the syntactic behavior of particle verb and base verbs together and applying clustering techniques allows us to distinguish particle verb meaning and shows the tight connection between transfer patterns and the semantic classes of particle verbs.

GhoSt-PV: A Representative Gold Standard of German Particle Verbs

This paper presents a gold standard data set containing 400 randomly selected German particle verbs, balanced across several particle types and three frequency bands, and accomplished by human ratings on the degree of semantic compositionality.

Exploiting Fine-grained Syntactic Transfer Features to Predict the Compositionality of German Particle Verbs

Evaluating against three human-rated gold standards, the finegrained syntactic approach is able to predict the level of compositionality of the particle verbs but is nevertheless inferior to a coarse-grained bag-of-words approach.

Factoring Ambiguity out of the Prediction of Compositionality for German Multi-Word Expressions

This paper presents a soft-clustering approach to sense discrimination that filters sense-irrelevant features when predicting the degrees of compositionality for German noun-noun compounds and German particle verbs.

Automatic classification of German 'an' particle verbs

Based on a thorough analysis of the particle verbs from a theoretical point of view, empirical features were identified and an automatic semantic classification was performed that confirmed and enlarged the knowledge about salient properties.

Assessing Meaning Components in German Complex Verbs: A Collection of Source-Target Domains and Directionality

A novel strategy to obtain source and target domain characterisations via sentence generation rather than sentence annotation is used, and a selection of arrows adds spatial directional information to the generated contexts.

Exploring Vector Space Models to Predict the Compositionality of German Noun-Noun Compounds

It is demonstrated that window-based rather than syntax-based distributional features perform better predictions, and that not adjectives or verbs but nouns represent the most salient part-of-speech.



Predicting the Degree of Compositionality of German Particle Verbs based on Empirical Syntactic and Semantic Subcategorisation Transfer Patterns

German particle verbs are productive compositions of a base verb and a prefix particle, whose part-of-speech varies between open-class nouns , adjectives, and verbs, and closed-class prepositions and

Detecting a Continuum of Compositionality in Phrasal Verbs

It is shown that whilst the compositionality judgements correlate with some statistics commonly used for extracting multiwords, the relationship is not as strong as that using the automatically constructed thesaurus.

Experiments on the Automatic Induction of German Semantic Verb Classes

This article presents clustering experiments on German verbs: A statistical grammar model for German serves as the source for a distributional verb description at the lexical syntax-semantics

Clustering Verbs Semantically According to their Alternation Behaviour

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

German Particle Verbs and Pleonastic Prepositions

The paper gives an overview of the semantic verb classes influencing this phenomenon, based on corpus data, and explains the underlying reasons for the behaviour of the particle verb including the verb particle as a preposition.

Combining EM Training and the MDL Principle for an Automatic Verb Classification Incorporating Selectional Preferences

This paper presents an innovative, complex approach to semantic verb classification that relies on selectional preferences as verb properties, trained by a combination of the EM algorithm and the MDL principle, providing soft clusters with two dimensions.

On Particle Verbs and Similar Constructions in German

Linguistic distinctions between the notions of a phrase, a word and their components are challenged by so-called particle verbs in German and similar features in other languages. Particle verbs look

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.

Towards a Dynamic Lexicon: Predicting the Syntactic Argument Structure of Complex Verbs

The study shows that the argument structure effects of verb formation with separable preverbs are astonishingly regular, even if the meaning of the resulting complex verb itself is opaque, as well as allowing for sensible guesses at argument structure frames for newly encountered complex verbs.

Detecting Compositionality of Verb-Object Combinations using Selectional Preferences

A highly signicant correlation between measures which use these ‘typebased’ selectional preferences and compositionality judgements from a data set used in previous research is demonstrated.