Solution of RuSimpleSentEval, competition in Dialogue2021. Overall 37 SARI score.
Solution based on RuGPT-3XL. Model was tuned on the train data.
Our approach has achieved second place on the public leaderboard and fifth place on the privateleaderboard.
-
Download pre-trained XL model here and put in folder
model. -
Example of usage is here
-
Explore all experiments in the article.
Text Simplification is the task of reducing the complexity of the vocabulary and sentence structure of the text while retaining its original meaning with the goal of improving readability and understanding. We explore the capability of the autoregressive models such as RuGPT3 (Generative Pre-trained Transformer 3 for Russian) to generate high quality simplified sentences. Within the shared task RuSimpleSentEval we present our solution based on different usages of RuGPT3 models. The following setups are described: 1) few-shot unsupervised generation with the RuGPTs models 2) the effect of the size of the training dataset on the downstream performance of fine-tuned model 3) 3 inference strategies 4) the downstream transfer and post-processing procedure using pretrained paraphrasers for Russian. This paper presents the second-place solution on the public leaderboard and the fifth-place solution on the private leaderboard. The proposed method is comparable with the novel state-of-the-art approaches. Additionally, we analyze the performance and discuss the flaws of RuGPTs generation.
title={Text Simplification with Autoregressive Models},
author={Fenogenova, Alena and Sberbank, SberDevices}}
To see the video, click on the screenshot =>
