SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.07058 · NAACL · 2021

Predicting Discourse Trees from Transformer-based Neural Summarizers

Giuseppe Carenini, Wen Xiao, Patrick Huber

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

Previous work indicates that discourse information benefits summarization. In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained neural summarizers. In particular, we generate unlabeled RST-style discourse trees from the self-attention matrices of the transformer model. Experiments across models and datasets reveal that the summarizer learns both, dependency-and constituencystyle discourse information, which is typically encoded in a single head, covering long-and short-distance discourse dependencies. Overall, the experimental results suggest that the learned discourse information is general and transferable inter-domain 1 .

For agents

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

get_harvested_code_for_paper("2104.07058")
get_code_for_paper("2104.07058")
have("2104.07058")

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

curl https://syntology.ai/api/ran/2104.07058.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.07058.svg)](https://syntology.ai/paper/2104.07058)

Connect an agent — have() is free.