Argumentative Text Generation in Economic Domain
This addresses the need for argumentative text generation in Russian economic applications, such as business meetings or student essays, but is incremental as it adapts existing methods to a new language and domain.
The paper tackled the problem of generating argumentative texts in the economic domain for Russian, which lacked annotated corpora, by using translated datasets to fine-tune a model for annotation and then training a generation model, resulting in a 20.7 percentage point improvement in accuracy (63.2% vs. 42.5%).
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.