A System for Experiments with Dependency Parsers

نویسندگان

  • Kiril Ivanov Simov
  • Iliana Simova
  • Ginka Ivanova
  • Maria Mateva
  • Petya Osenova
چکیده

In this paper we present a system for experimenting with combinations of dependency parsers. The system supports initial training of different parsing models, creation of parsebank(s) with these models, and different strategies for the construction of ensemble models aimed at improving the output of the individual models by voting. The system employs two algorithms for construction of dependency trees from several parses of the same sentence and several ways for ranking of the arcs in the resulting trees. We have performed experiments with state-of-the-art dependency parsers including MaltParser (Nivre et al., 2006), MSTParser (McDonald, 2006), TurboParser (Martins et al., 2010), and MATEParser (Bohnet, 2010), on the data from the Bulgarian treebank – BulTreeBank. Our best result from these experiments is slightly better then the best result reported in the literature for this language (Martins et al.,

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Experiments with an ensemble of Spanish dependency parsers

This article presents an ensemble system for dependency parsing of Spanish that combines three machine-learning-based dependency parsers. The system operates in two stages. In the first stage, each of the three parsers analyzes an input sentence and produces a dependency graph. In the second stage, a voting system distills a final dependency graph out of the three first-stage dependency graphs.

متن کامل

Experiments for Dependency Parsing of Greek

This paper describes experiments for statistical dependency parsing using two different parsers trained on a recently extended dependency treebank for Greek, a language with a moderately rich morphology. We show how scores obtained by the two parsers are influenced by morphology and dependency types as well as sentence and arc length. The best LAS obtained in these experiments was 80.16 on a te...

متن کامل

Wide-Coverage Deep Statistical Parsing Using Automatic Dependency Structure Annotation

A number of researchers (Lin 1995; Carroll, Briscoe, and Sanfilippo 1998; Carroll et al. 2002; Clark and Hockenmaier 2002; King et al. 2003; Preiss 2003; Kaplan et al. 2004;Miyao and Tsujii 2004) have convincingly argued for the use of dependency (rather than CFG-tree) representations for parser evaluation. Preiss (2003) and Kaplan et al. (2004) conducted a number of experiments comparing “deep...

متن کامل

LSTM Feature Representation in Projective and Non-Projective Transition-Based Dependency Parsers

The objective of the first part of my project was to investigate how allowing for nonprojectivity influences the attachment accuracy of transition-based dependency parsers. I implemented four parsers, two of which were based on novel transition systems. Since the novel non-projective parser achieved the highest attachment scores, I concluded that allowing for all kinds of dependency arcs gives ...

متن کامل

Hybrid Combination of Constituency and Dependency Trees into an Ensemble Dependency Parser

Dependency parsing has made many advancements in recent years, in particular for English. There are a few dependency parsers that achieve comparable accuracy scores with each other but with very different types of errors. This paper examines creating a new dependency structure through ensemble learning using a hybrid of the outputs of various parsers. We combine all tree outputs into a weighted...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014