Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCombining (second-order) graph-based and headed span-based projective dependency parsing
99
0
0.0
(
0
)
Added by
Songlin Yang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Graph-based methods are popular in dependency parsing for decades. Recently, citet{yang2021headed} propose a headed span-based method. Both of them score all possible trees and globally find the highest-scoring tree. In this paper, we combine these two kinds of methods, designing several dynamic programming algorithms for joint inference. Experiments show the effectiveness of our proposed methodsfootnote{Our code is publicly available at url{https://github.com/sustcsonglin/span-based-dependency-parsing}.}.
rate research
Read More
We propose a headed span-based method for projective dependency parsing. In a projective tree, the subtree rooted at each word occurs in a contiguous sequence (i.e., span) in the surface order, we call the span-headword pair textit{headed span}. In this view, a projective tree can be regarded as a collection of headed spans. It is similar to the case in constituency parsing since a constituency tree can be regarded as a collection of constituent spans. Span-based methods decompose the score of a constituency tree sorely into the score of constituent spans and use the CYK algorithm for global training and exact inference, obtaining state-of-the-art results in constituency parsing. Inspired by them, we decompose the score of a dependency tree into the score of headed spans. We use neural networks to score headed spans and design a novel $O(n^3)$ dynamic programming algorithm to enable global training and exact inference. We evaluate our method on PTB, CTB, and UD, achieving state-of-the-art or comparable results.
Most of the unsupervised dependency parsers are based on first-order probabilistic generative models that only consider local parent-child information. Inspired by second-order supervised dependency parsing, we proposed a second-order extension of unsupervised neural dependency models that incorporate grandparent-child or sibling information. We also propose a novel design of the neural parameterization and optimization methods of the dependency models. In second-order models, the number of grammar rules grows cubically with the increase of vocabulary size, making it difficult to train lexicalized models that may contain thousands of words. To circumvent this problem while still benefiting from both second-order parsing and lexicalization, we use the agreement-based learning framework to jointly train a second-order unlexicalized model and a first-order lexicalized model. Experiments on multiple datasets show the effectiveness of our second-order models compared with recent state-of-the-art methods. Our joint model achieves a 10% improvement over the previous state-of-the-art parser on the full WSJ test set
In this paper, we present an approach to improve the accuracy of a strong transition-based dependency parser by exploiting dependency language models that are extracted from a large parsed corpus. We integrated a small number of features based on the dependency language models into the parser. To demonstrate the effectiveness of the proposed approach, we evaluate our parser on standard English and Chinese data where the base parser could achieve competitive accuracy scores. Our enhanced parser achieved state-of-the-art accuracy on Chinese data and competitive results on English data. We gained a large absolute improvement of one point (UAS) on Chinese and 0.5 points for English.
In this paper, we study the problem of parsing structured knowledge graphs from textual descriptions. In particular, we consider the scene graph representation that considers objects together with their attributes and relations: this representation has been proved useful across a variety of vision and language applications. We begin by introducing an alternative but equivalent edge-centric view of scene graphs that connect to dependency parses. Together with a careful redesign of label and action space, we combine the two-stage pipeline used in prior work (generic dependency parsing followed by simple post-processing) into one, enabling end-to-end training. The scene graphs generated by our learned neural dependency parser achieve an F-score similarity of 49.67% to ground truth graphs on our evaluation set, surpassing best previous approaches by 5%. We further demonstrate the effectiveness of our learned parser on image retrieval applications.
Chinese word segmentation and dependency parsing are two fundamental tasks for Chinese natural language processing. The dependency parsing is defined on word-level. Therefore word segmentation is the precondition of dependency parsing, which makes dependency parsing suffer from error propagation and unable to directly make use of the character-level pre-trained language model (such as BERT). In this paper, we propose a graph-based model to integrate Chinese word segmentation and dependency parsing. Different from previous transition-based joint models, our proposed model is more concise, which results in fewer efforts of feature engineering. Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing. Besides, when BERT is combined, our model can substantially reduce the performance gap of dependency parsing between joint models and gold-segmented word-based models. Our code is publicly available at https://github.com/fastnlp/JointCwsParser.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
