SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.08912 · 2019

Unlexicalized Transition-based Discontinuous Constituency Parsing

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head (ii) bilexical statistics are crucial to solve ambiguities. In this paper, we introduce an unlexicalized transition-based parser for discontinuous constituency structures, based on a structure-label transition system and a bi-LSTM scoring system. We compare it to lexicalized parsing models in order to address the question of lexicalization in the context of discontinuous constituency parsing. Our experiments show that unlexicalized models systematically achieve higher results than lexicalized models, and provide additional empirical evidence that lexicalization is not necessary to achieve strong parsing results. Our best unlexicalized model sets a new state of the art on English and German discontinuous constituency treebanks. We further provide a per-phenomenon analysis of its errors on discontinuous constituents.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1902.08912")
get_code_for_paper("1902.08912")
have("1902.08912")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1902.08912.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1902.08912.svg)](https://syntology.ai/paper/1902.08912)

Connect an agent — have() is free.