• Publications
  • Influence
Hierarchical Embeddings for Hypernymy Detection and Directionality
TLDR
We present a novel neural model HyperVec to learn hierarchical embeddings for hypernymy detection and directionality. Expand
  • 70
  • 22
  • PDF
Chasing Hypernyms in Vector Spaces with Entropy
TLDR
In this paper, we introduce SLQS , a new entropy-based distributional measure for the unsupervised identification of hypernymy and its directionality in Distributional Semantic Models . Expand
  • 129
  • 12
  • PDF
Clustering Verbs Semantically According to their Alternation Behaviour
TLDR
This paper empirically investigates the proposition that verbs can be semantically classi ed according to their syntactic alternation behaviour concerning subcategorisation frames and their selectional preferences for the arguments within the frames. Expand
  • 124
  • 9
  • PDF
Experiments on the Automatic Induction of German Semantic Verb Classes
TLDR
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 interface, and the unsupervised clustering algorithm k-means uses empirical verb properties to perform an automatic induction of verb classes. Expand
  • 230
  • 8
  • PDF
Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction
TLDR
We propose a novel vector representation that integrates lexical contrast into distributional vectors and strengthens the most salient features for determining degrees of word similarity. Expand
  • 93
  • 7
  • PDF
Acquiring Lexical Knowledge for Anaphora Resolution
TLDR
The lack of adequate bases of commonsense or even lexical knowledge is perhaps the main obstacle to the development of highperformance, robust tools for semantic interpretation. Expand
  • 109
  • 7
  • PDF
Multilingual Reliability and "Semantic" Structure of Continuous Word Spaces
TLDR
We present a systematic exploration of morpho-syntactic and semantic relatedness in English and German, a morphologically rich language. Expand
  • 35
  • 7
  • PDF
Diachronic Usage Relatedness (DURel): A Framework for the Annotation of Lexical Semantic Change
TLDR
We propose a framework that extends synchronic polysemy annotation to diachronic changes in lexical meaning, to counteract the lack of resources for evaluating computational models of lexical semantic change. Expand
  • 28
  • 7
  • PDF
Combining EM Training and the MDL Principle for an Automatic Verb Classification Incorporating Selectional Preferences
TLDR
This paper presents an innovative, complex approach to semantic verb classification that relies on selectional preferences as verb properties. Expand
  • 41
  • 6
  • PDF
Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network
TLDR
We present a novel neural network model AntSynNET that exploits lexico-syntactic patterns from syntactic parse trees to distinguish between antonyms and synonyms. Expand
  • 33
  • 5
  • PDF