Learning Syntax from Function Words
نویسندگان
چکیده
This paper presents an approximation of word clustering, using only function words as context. We use this to induce classes of function words. Our algorithm identifies some classes with consistency, and could be useful for guiding greedy grammar learners.
منابع مشابه
Learning Syntax-Semantics Mappings to Bootstrap Word Learning
This paper addresses possible interactive effects between word learning and syntax learning at an early stage of development. We present a computational model that simulates how the results from a syntax learning process and a word learning process can be integrated to build syntax-semantics mappings, and how the emergence of links between syntax and word learning could facilitate subsequent wo...
متن کاملUsing Graph-Kernels to Represent Semantic Information in Text Classification
Most text classification systems use bag-of-words representation of documents to find the classification target function. Linguistic structures such as morphology, syntax and semantic are completely neglected in the learning process. This paper proposes a new document representation that, while including its context independent sentence meaning, is able to be used by a structured kernel functio...
متن کاملDiagnostics for Constituents: Dependency, Constituency, and the Status of Function Words
This contribution delivers two messages: 1) that the tests for constituents that are widely employed in linguistics and syntax textbooks are more congruent with dependency-based syntax than with constituency-based syntax and 2) that these same tests support the conventional analysis of function words, that is, the analysis that takes most function words (auxiliary verbs, adpositions, subordinat...
متن کاملUniversal Dependencies: A Cross-Linguistic Perspective on Grammar and Lexicon
Universal Dependencies is an initiative to develop cross-linguistically consistent grammatical annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning and parsing research from a language typology perspective. It assumes a dependency-based approach to syntax and a lexicalist approach to morphology, which together entail that the funda...
متن کاملText classification using Semantic Information and Graph Kernels
The most common approach to the text classification problem is to use a bag-of-words representation of documents to find the classification target function. Linguistic structures such as morphology, syntax and semantic are completely neglected in the learning process. This paper uses another document representation that, while including its context independent sentence meaning, is able to be us...
متن کامل