SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.03285 · 2019

Semantic Role Labeling with Iterative Structure Refinement

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

Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on expressive sentence encoders (e.g., multi-layer LSTMs) but tend to model only local (if any) interactions between individual argument labeling decisions. This contrasts with earlier work and also with the intuition that the labels of individual arguments are strongly interdependent. We model interactions between argument labeling decisions through {\it iterative refinement}. Starting with an output produced by a factorized model, we iteratively refine it using a refinement network. Instead of modeling arbitrary interactions among roles and words, we encode prior knowledge about the SRL problem by designing a restricted network architecture capturing non-local interactions. This modeling choice prevents overfitting and results in an effective model, outperforming strong factorized baseline models on all 7 CoNLL-2009 languages, and achieving state-of-the-art results on 5 of them, including English.

For agents

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

get_harvested_code_for_paper("1909.03285")
get_code_for_paper("1909.03285")
have("1909.03285")

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

curl https://syntology.ai/api/ran/1909.03285.json

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

[![Syntology run record](https://syntology.ai/api/ran/1909.03285.svg)](https://syntology.ai/paper/1909.03285)

Connect an agent — have() is free.