DeepAI
Log In Sign Up

Multi-Criteria Chinese Word Segmentation with Transformer

06/28/2019
by   Xipeng Qiu, et al.
0

Different linguistic perspectives cause many diverse segmentation criteria for Chinese word segmentation (CWS). Most existing methods focus on improving the performance of single-criterion CWS. However, it is interesting to exploit these heterogeneous segmentation criteria and mine their common underlying knowledge. In this paper, we propose a concise and effective model for multi-criteria CWS, which utilizes a shared fully-connected self-attention model to segment the sentence according to a criterion indicator. Experiments on eight datasets with heterogeneous segmentation criteria show that the performance of each corpus obtains a significant improvement, compared to single-criterion learning.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/25/2017

Adversarial Multi-Criteria Learning for Chinese Word Segmentation

Different linguistic perspectives causes many diverse segmentation crite...
12/19/2018

Switch-LSTMs for Multi-Criteria Chinese Word Segmentation

Multi-criteria Chinese word segmentation is a promising but challenging ...
04/13/2020

Unified Multi-Criteria Chinese Word Segmentation with BERT

Multi-Criteria Chinese Word Segmentation (MCCWS) aims at finding word bo...
12/07/2017

Effective Neural Solution for Multi-Criteria Word Segmentation

We present a simple yet elegant solution to train a single joint model o...
03/11/2019

Toward Fast and Accurate Neural Chinese Word Segmentation with Multi-Criteria Learning

The ambiguous annotation criteria bring into the divergence of Chinese W...
11/13/2020

RethinkCWS: Is Chinese Word Segmentation a Solved Task?

The performance of the Chinese Word Segmentation (CWS) systems has gradu...
06/24/2017

Fundamental Matrix Estimation: A Study of Error Criteria

The fundamental matrix (FM) describes the geometric relations that exist...