Work

Spectral Learning for Non-Deterministic Dependency Parsing

Year: 2012

Type: conference-paper

Abstract: In this paper we study spectral learning methods for non-deterministic split head-automata grammars, a powerful hidden-state formalism for dependency parsing. We present a learning algorithm that, like other spectral methods, is efficient and non-susceptible to local minima. We show how this algorithm can be formulated as a technique for inducing hidden structure from distributions computed by forward-backward recursions. Furthermore, we also present an inside-outside algorithm for the parsing model that runs in cubic time, hence maintaining the standard parsing costs for context-free grammars.

Source: RECERCAT (Consorci de Serveis Universitaris de Catalunya)

Authors: Franco M. Luque, Ariadna Quattoni, Borja Balle, Xavier Carreras

Institutions: Consejo Nacional de Investigaciones Científicas y Técnicas, Universidad Nacional de Córdoba, Universitat Politècnica de Catalunya

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W2121142987

FWCI: 7.385

Cites: 27

Cited by: 36

Related to: 10