Semi-Supervised Neural System for Tagging, Parsing and Lematization

04/26/2020
by   Piotr Rybak, et al.
0

This paper describes the ICS PAS system which took part in CoNLL 2018 shared task on Multilingual Parsing from Raw Text to Universal Dependencies. The system consists of jointly trained tagger, lemmatizer, and dependency parser which are based on features extracted by a biLSTM network. The system uses both fully connected and dilated convolutional neural architectures. The novelty of our approach is the use of an additional loss function, which reduces the number of cycles in the predicted dependency graphs, and the use of self-training to increase the system performance. The proposed system, i.e. ICS PAS (Warszawa), ranked 3th/4th in the official evaluation obtaining the following overall results: 73.02 (LAS), 60.25 (MLAS) and 64.44 (BLEX).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/24/2020

ThamizhiUDp: A Dependency Parser for Tamil

This paper describes how we developed a neural-based dependency parser, ...
research
07/11/2018

An improved neural network model for joint POS tagging and dependency parsing

We propose a novel neural network model for joint part-of-speech (POS) t...
research
07/09/2018

Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation

This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 s...
research
03/15/2017

SyntaxNet Models for the CoNLL 2017 Shared Task

We describe a baseline dependency parsing system for the CoNLL2017 Share...
research
01/29/2019

Universal Dependency Parsing from Scratch

This paper describes Stanford's system at the CoNLL 2018 UD Shared Task....
research
07/08/2021

COMBO: a new module for EUD parsing

We introduce the COMBO-based approach for EUD parsing and its implementa...
research
06/01/2020

Efficient EUD Parsing

We present the system submission from the FASTPARSE team for the EUD Sha...

Please sign up or login with your details

Forgot password? Click here to reset