Automatic Summarization of Russian Texts: Comparison of Extractive and Abstractive Methods

TL;DR

This paper compares extractive and abstractive summarization methods for Russian texts, utilizing large language models and argumentation corpora to improve argument text generation accuracy.

Contribution

It introduces a novel approach using fine-tuned RuBERT and ruGPT-3 models on argumentation corpora for Russian text generation.

Findings

Improved argument generation accuracy by over 20 percentage points.

Utilized translated argumentation corpora for model fine-tuning.

Enhanced performance of Russian text summarization and argumentation models.

Abstract

The development of large and super-large language models, such as GPT-3, T5, Switch Transformer, ERNIE, etc., has significantly improved the performance of text generation. One of the important research directions in this area is the generation of texts with arguments. The solution of this problem can be used in business meetings, political debates, dialogue systems, for preparation of student essays. One of the main domains for these applications is the economic sphere. The key problem of the argument text generation for the Russian language is the lack of annotated argumentation corpora. In this paper, we use translated versions of the Argumentative Microtext, Persuasive Essays and UKP Sentential corpora to fine-tune RuBERT model. Further, this model is used to annotate the corpus of economic news by argumentation. Then the annotated corpus is employed to fine-tune the ruGPT-3 model, which generates argument texts. The results show that this approach improves the accuracy of the argument generation by more than 20 percentage points (63.2% vs. 42.5%) compared to the original ruGPT-3 model.