A Pilot Study on Dialogue-Level Dependency Parsing for Chinese

05/21/2023
by   Gongyao Jiang, et al.
0

Dialogue-level dependency parsing has received insufficient attention, especially for Chinese. To this end, we draw on ideas from syntactic dependency and rhetorical structure theory (RST), developing a high-quality human-annotated corpus, which contains 850 dialogues and 199,803 dependencies. Considering that such tasks suffer from high annotation costs, we investigate zero-shot and few-shot scenarios. Based on an existing syntactic treebank, we adopt a signal-based method to transform seen syntactic dependencies into unseen ones between elementary discourse units (EDUs), where the signals are detected by masked language modeling. Besides, we apply single-view and multi-view data selection to access reliable pseudo-labeled instances. Experimental results show the effectiveness of these baselines. Moreover, we discuss several crucial points about our dataset and approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/27/2019

Zero-shot Chinese Discourse Dependency Parsing via Cross-lingual Mapping

Due to the absence of labeled data, discourse parsing still remains chal...
research
06/24/2019

On the Definition of Japanese Word

The annotation guidelines for Universal Dependencies (UD) stipulate that...
research
05/31/2017

Analysis of the Effect of Dependency Information on Predicate-Argument Structure Analysis and Zero Anaphora Resolution

This paper investigates and analyzes the effect of dependency informatio...
research
01/28/2021

Syntactic Nuclei in Dependency Parsing – A Multilingual Exploration

Standard models for syntactic dependency parsing take words to be the el...
research
06/01/2021

An In-depth Study on Internal Structure of Chinese Words

Unlike English letters, Chinese characters have rich and specific meanin...
research
08/03/2022

Benchmarking zero-shot and few-shot approaches for tokenization, tagging, and dependency parsing of Tagalog text

The grammatical analysis of texts in any human language typically involv...

Please sign up or login with your details

Forgot password? Click here to reset