Dependency Parse Reranking with Rich Subtree Features

Abstract

In pursuing machine understanding of human language, highly accurate syntactic analysis is a crucial step. In this work, we focus on dependency grammar, which models syntax by encoding transparent predicate-argument structures. Recent advances in dependency parsing have shown that employing higherorder subtree structures in graph-based parsers can substantially improve the parsing accuracy. However, the inefficiency of this approach increases with the order of the subtrees. This work explores a new reranking approach for dependency parsing that can utilize complex subtree representations by applying efficient subtree selection methods. We demonstrate the effectiveness of the approach in experiments conducted on the Penn Treebank and the Chinese Treebank. Our system achieves the best performance among known supervised systems evaluated on these datasets, improving the baseline accuracy from 91.88% to 93.42% for English, and from 87.39% to 89.25% for Chinese.

Evaluating word embedding models: methods and experimental results

“…We choose two-layer Bi-LSTM with 256 hidden dimensions. The adopted CNN has three layers with 100 filters per layer of size [3,4,5], respectively. For FastText [72], we use the bi-gram setting and only one layer for optimization.…”

“…W ORD embedding is a real-valued vector representation of words by embedding both semantic and syntactic meanings obtained from unlabeled large corpus. It is a powerful tool widely used in modern natural language processing (NLP) tasks, including semantic analysis [1], information retrieval [2], dependency parsing [3], [4], [5], question answering [6], [7] and machine translation [6], [8], [9]. Learning a high quality representation is extremely important for these tasks, yet the question "what is a good word embedding model" remains an open problem.…”

A Quantum Language-Inspired Tree Structural Text Representation for Semantic Analysis

“…Wang et al structured a regional CNN-LSTM model based on a subtree to analyze sentiment predictions [35]. A reranking approach for the dependency tree was provided utilizing complex subtree representations [36]. A bidirectional dependency tree representation was provided to extract dependency features from the input sentences [37].…”

A Natural Language Query Builder Interface for Structured Databases Using Dependency Parsing

“…Mo Shen et al [2] proposed a dependency grammar, in which predicate-argument structures are encoded to build modelled syntax. New reranking approach was proposed for dependency parsing that can utilize complex sub tree representations.…”