SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.14710 · ACL · 2020

Towards Unsupervised Language Understanding and Generation by Joint Dual Learning

Yun-Nung Chen, Shang-Yu Su, Chao-Wei Huang

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

In modular dialogue systems, natural language understanding (NLU) and natural language generation (NLG) are two critical components, where NLU extracts the semantics from the given texts and NLG is to construct corresponding natural language sentences based on the input semantic representations. However, the dual property between understanding and generation has been rarely explored. The prior work (Su et al., 2019) is the first attempt that utilized the duality between NLU and NLG to improve the performance via a dual supervised learning framework. However, the prior work still learned both components in a supervised manner; instead, this paper introduces a general learning framework to effectively exploit such duality, providing flexibility of incorporating both supervised and unsupervised learning algorithms to train language understanding and generation models in a joint fashion. The benchmark experiments demonstrate that the proposed approach is capable of boosting the performance of both NLU and NLG. 1

For agents

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

get_harvested_code_for_paper("2004.14710")
get_code_for_paper("2004.14710")
have("2004.14710")

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

curl https://syntology.ai/api/ran/2004.14710.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.14710.svg)](https://syntology.ai/paper/2004.14710)

Connect an agent — have() is free.