A Span-based Linearization for Constituent Trees

04/30/2020
by   Yang Wei, et al.
0

We propose a novel linearization of a constituent tree, together with a new locally normalized model. For each split point in a sentence, our model computes the normalizer on all spans ending with that split point, and then predicts a tree span from them. Compared with global models, our model is fast and parallelizable. Different from previous local models, our linearization method is tied on the spans directly and considers more local features when performing span prediction, which is more interpretable and effective. Experiments on PTB (95.8 F1) and CTB (92.4 F1) show that our model significantly outperforms existing local models and efficiently achieves competitive results with global models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/01/2022

Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation

Recently CKY-based models show great potential in unsupervised grammar i...
research
06/24/2020

Efficient Constituency Parsing by Pointing

We propose a novel constituency parsing model that casts the parsing pro...
research
02/14/2023

Scalable Optimal Multiway-Split Decision Trees with Constraints

There has been a surge of interest in learning optimal decision trees us...
research
10/07/2020

Unsupervised Parsing via Constituency Tests

We propose a method for unsupervised parsing based on the linguistic not...
research
03/31/2022

A Character-level Span-based Model for Mandarin Prosodic Structure Prediction

The accuracy of prosodic structure prediction is crucial to the naturaln...
research
11/05/2019

Coreference Resolution as Query-based Span Prediction

In this paper, we present an accurate and extensible approach for the co...
research
07/21/2017

End-to-end Neural Coreference Resolution

We introduce the first end-to-end coreference resolution model and show ...

Please sign up or login with your details

Forgot password? Click here to reset