SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.01958 · 2021

SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks

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

Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1) gradient-based methods: updating all latent representations of pre-trained models with gradients from attribute models; (2) weighted-decoding methods: re-ranking beam candidates from pre-trained models with attribute functions. However, gradient-based methods lead to high computation cost and can easily get overfitted on small training sets, while weighted-decoding methods are inherently constrained by the low-variance high-bias pre-trained model. In this work, we propose a novel approach to control the generation of Transformer-based pre-trained language models: the SideControl framework, which leverages a novel control attributes loss to incorporate useful control signals, and is shown to perform well with very limited training samples. We evaluate our proposed method on two benchmark open-domain dialogue datasets, and results show that the SideControl framework has better controllability, higher generation quality and better sample-efficiency than existing gradient-based and weighted-decoding baselines.

For agents

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

get_harvested_code_for_paper("2109.01958")
get_code_for_paper("2109.01958")
have("2109.01958")

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

curl https://syntology.ai/api/ran/2109.01958.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.01958.svg)](https://syntology.ai/paper/2109.01958)

Connect an agent — have() is free.