Automatic Induction of German Aspectual Verb Classes in a Distributional Framework

The central question of this study is whether aspectual verb classes (Vendler, 1967) can be induced from corpus data in a fully automatic, distributionally motivated procedure. We propose an operationalization of ‘aspectivity’ utilizing distributional information about nominal fillers in the argument positions of verbs in combination with aspectual features automatically derived from dependency information. Using a support vector machine classifier and a classification into five aspectual classes (Richter and van Hout, 2015) as the gold standard, we observed excellent results that support our hypothesis.

[1]  W. Klein.  How time is encoded , 2009 .

[2]  Barbara B. Levin,et al.  English verb classes and alternations , 1993 .

[3]  Eric V. Siegel.  Learning Methods for Combining Linguistic Indicators to Classify Verbs , 1997, EMNLP.

[4]  Tim Fernando,et al.  A Finite-state Approach to Events in Natural Language Semantics , 2004, J. Log. Comput..

[5]  Z. Vendler.  Linguistics in Philosophy , 1967 .

[6]  Sabine Gründer.  An Algorithm for Adverbial Aspect Shift , 2008, COLING.

[7]  Sabine Schulte im Walde.  Experiments on the Choice of Features for Learning Verb Classes , 2003, EACL.

[8]  Michael Richter,et al.  Classification of German verbs using nouns in argument positions and aspectual features , 2015, NetWordS.

[9]  Suzanne Stevenson,et al.  Generalizing between form and meaning using learned verb classes , 2011, CogSci.

[10]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[11]  Bernd Bohnet,et al.  Very high accuracy and fast dependency parsing is not a contradiction , 2010, COLING 2010.

[12]  Michael Richter,et al.  A classification of German verbs using empirical language data and concepts of Vendler and Dowty , 2016 .

[13]  H. Schumacher.  Verben in Feldern : Valenzwörterbuch zur Syntax und Semantik deutscher Verben , 1986 .

[14]  Chris Brew,et al.  Inducing German Semantic Verb Classes from Purely Syntactic Subcategorisation Information , 2002, ACL.

[15]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[16]  Judith Aissen,et al.  Differential Object Marking: Iconicity vs. Economy , 2003 .

[17]  W. Bruce Croft.  Typology and Universals , 1990 .

[18]  김두식,et al.  English Verb Classes and Alternations , 2006 .

[19]  Ping Li,et al.  The Expression of Time , 2010 .

[20]  Bonnie J. Dorr,et al.  Role of Word Sense Disalnbiguation in Lexical Acquisition: Predicting Semantics from Syntactic Cues , 1996, COLING.

[21]  Ted Briscoe,et al.  A System for Large-Scale Acquisition of Verbal, Nominal and Adjectival Subcategorization Frames from Corpora , 2007, ACL.

[22]  Hinrich Schütze,et al.  A Vector Model for Syntagmatic and Paradigmatic Relatedness , 1993 .

[23]  Zoubin Ghahramani,et al.  Unsupervised and Constrained Dirichlet Process Mixture Models for Verb Clustering , 2009 .

[24]  Suzanne Stevenson,et al.  Automatic Verb Classification Based on Statistical Distributions of Argument Structure , 2001, CL.

[25]  Kathleen McKeown,et al.  Learning Methods to Combine Linguistic Indicators:Improving Aspectual Classification and Revealing Linguistic Insights , 2000, CL.

[26]  Martin Chodorow,et al.  Degrees of Stativity: The Lexical Representation of Verb Aspect , 1992, COLING.

[27]  Sabine Schulte,et al.  Automatic Induction of Semantic Classes for German Verbs , 2004 .

[28]  Suzanne Stevenson,et al.  A General Feature Space for Automatic Verb Classification , 2003, EACL.

[29]  R. Darnell.  Translation , 1873, The Indian medical gazette.

[30]  Susan T. Dumais,et al.  Statistical semantics: analysis of the potential performance of keyword information systems , 1984 .