Predictability of Distributional Semantics in Derivational Word Formation
Compositional distributional semantic models (CDSMs) have successfully been applied to the task of predicting the meaning of a range of linguistic constructions. Their performance on semi-compositional word formation process of (morphological) derivation, however, has been extremely variable, with no large-scale empirical investigation to date. This paper fills that gap, performing an analysis of CDSM predictions on a large dataset (over 30,000 German derivationally related word pairs). We use linear regression models to analyze CDSM performance and obtain insights into the linguistic factors that influence how predictable the distributional context of a derived word is going to be. We identify various such factors, notably part of speech, argument structure, and semantic regularity.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationregressionSentiment AnalysisWord EmbeddingsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Distributional and Orthographic Aggregation Model for English Derivational Morphology
Modeling derivational morphology to generate words with particular semantics is useful in many text generation tasks, such as machine translation or abstractive question answering. In this work, we tackle the task of der…
abstractive question answeringMachine TranslationQuestion AnsweringText Generation+1Distributional Semantics and Linguistic Theory
Distributional semantics provides multi-dimensional, graded, empirically induced word representations that successfully capture many aspects of meaning in natural languages, as shown in a large body of work in computatio…
Derivational Smoothing for Syntactic Distributional Semantics
Lexical and Derivational Meaning in Vector-Based Models of Relativisation
Sadrzadeh et al (2013) present a compositional distributional analysis of relative clauses in English in terms of the Frobenius algebraic structure of finite dimensional vector spaces. The analysis relies on distinct typ…
ObjectDerivational Morphological Relations in Word Embeddings
Derivation is a type of a word-formation process which creates new words from existing ones by adding, changing or deleting affixes. In this paper, we explore the potential of word embeddings to identify properties of wo…
ClusteringWord Embeddings