Derivational Smoothing for Syntactic Distributional Semantics
نویسندگان
چکیده
Syntax-based vector spaces are used widely in lexical semantics and are more versatile than word-based spaces (Baroni and Lenci, 2010). However, they are also sparse, with resulting reliability and coverage problems. We address this problem by derivational smoothing, which uses knowledge about derivationally related words (oldish→ old) to improve semantic similarity estimates. We develop a set of derivational smoothing methods and evaluate them on two lexical semantics tasks in German. Even for models built from very large corpora, simple derivational smoothing can improve coverage considerably.
منابع مشابه
Compositional Distributional Semantics Models in Chunk-based Smoothed Tree Kernels
The field of compositional distributional semantics has proposed very interesting and reliable models for accounting the distributional meaning of simple phrases. These models however tend to disregard the syntactic structures when they are applied to larger sentences. In this paper we propose the chunk-based smoothed tree kernels (CSTKs) as a way to exploit the syntactic structures as well as ...
متن کاملThe role of Persian causative markers in the acquisition of English causative verbs
This project investigates the relationship between lexical semantics and causative morphology in the acquisition of causative/inchoative-related verbs in English as a foreign language by Iranian speakers. Results of translation and picture judgment task show although L2 learners have largely acquired the correct lexico-syntactic classification of verbs in English, they were constrained by ...
متن کاملLexical 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 type assignments and lexical recipes for subject vs object relativisation. The situation for Dutch is different: because of the verb final nature of Dutch, relative clauses are amb...
متن کاملTowards Semantic Validation of a Derivational Lexicon
Derivationally related lemmas like friendN – friendlyA – friendshipN are derived from a common stem. Frequently, their meanings are also systematically related. However, there are also many examples of derivationally related lemma pairs whose meanings differ substantially, e.g., objectN – objectiveN . Most broad-coverage derivational lexicons do not reflect this distinction, mixing up semantica...
متن کاملVector spaces for historical linguistics: Using distributional semantics to study syntactic productivity in diachrony
This paper describes an application of distributional semantics to the study of syntactic productivity in diachrony, i.e., the property of grammatical constructions to attract new lexical items over time. By providing an empirical measure of semantic similarity between words derived from lexical co-occurrences, distributional semantics not only reliably captures how the verbs in the distributio...
متن کامل