Yara Parser: A Fast and Accurate Dependency Parser

Abstract

Dependency parsers are among the most crucial tools in natural language processing as they have many important applications in downstream tasks such as information retrieval, machine translation and knowledge acquisition. We introduce the Yara Parser, a fast and accurate open-source dependency parser based on the arc-eager algorithm and beam search. It achieves an unlabeled accuracy of 93.32 on the standard WSJ test set which ranks it among the top dependency parsers. At its fastest, Yara can parse about 4000 sentences per second when in greedy mode (1 beam). When optimizing for accuracy (using 64 beams and Brown cluster features), Yara can parse 45 sentences per second. The parser can be trained on any syntactic dependency treebank and different options are provided in order to make it more flexible and tunable for specific tasks. It is released with the Apache version 2.0 license and can be used for both commercial and academic purposes. The parser can be found at https://github.com/yahoo/YaraParser.

Cited by in corpus (18)

• Linguistic Features for Readability Assessment
• CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
• How Important is Syntactic Parsing Accuracy? An Empirical Evaluation on Rule-Based Sentiment Analysis
• Transferring Semantic Roles Using Translation and Syntactic Information
• XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection
• Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks
• The Persian Dependency Treebank Made Universal
• PoBRL: Optimizing Multi-Document Summarization by Blending Reinforcement Learning Policies
• Robust Cross-lingual Hypernymy Detection using Dependency Context
• The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages
• Relation Extraction with Explanation
• Cross-Lingual Syntactic Transfer with Limited Resources
• Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
• Neuro-Symbolic Contrastive Learning for Cross-domain Inference
• Transition-based Parsing with Lighter Feed-Forward Networks
• MDQE: A More Accurate Direct Pretraining for Machine Translation Quality Estimation
• Multi-Round Parsing-based Multiword Rules for Scientific OpenIE
• Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering