Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set

Domaine:

natural language processing

Type de record:

papermodel

Créateur:

ShiHuaLee

Hôte:

We first present a minimal feature set for transition-based dependency parsing, continuing a recent trend started by Kiperwasser and Goldberg (2016a) and Cross and Huang (2016a) of using bi-directional LSTM features. We plug our minimal feature set into the dynamic-programming framework of Huang and Sagae (2010) and Kuhlmann et al. (2011) to produce the first implementation of worst-case O(n^3) exact decoders for arc-hybrid and arc-eager transition systems. With our minimal features, we also present O(n^3) global training methods. Finally, using ensembles including our new parsers, we achieve the best unlabeled attachment score reported (to our knowledge) on the Chinese Treebank and the "second-best-in-class" result on the English Penn Treebank. Proceedings of EMNLP, 2017. 12 pages

Visit

arxiv.org

Similaires

Enhancing Multilingual Dependency Parsing via Dynamic Linguistic Feature Extraction and AlignmentMeta-Learning for Fast Cross-Lingual Adaptation in Dependency ParsingCross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource LanguagesTypological Features for Multilingual Delexicalised Dependency ParsingUDapter: Language Adaptation for Truly Universal Dependency Parsing<p>Global Feature Importance via SHAP Values.</p>

Enhancing Multilingual Dependency Parsing via Dynamic Linguistic Feature Extraction and Alignment

Multi-lingual dependency parsing aims to extract useful syntactic knowledge from multiple high-resou

Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing

Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in c

Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages

In cross-lingual dependency annotation projection, information is often lost during transfer because

Typological Features for Multilingual Delexicalised Dependency Parsing

International audience The existence of universal models to describe the syntax of la

UDapter: Language Adaptation for Truly Universal Dependency Parsing

Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser

<p>Global Feature Importance via SHAP Values.</p>

Introduction

Long-acting reversible contraceptives (LARCs) are critical for reducing m