mlsanityData to 14 Oct 2026

Argumentative Text Generation in Economic Domain

arXiv 2206.09251 ↗First posted 18 Jun 2022cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 33 references that are in the map. First posted on arXiv 18 Jun 2022.

Builds on

15 of 33 references.

References · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  4. 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 762
  5. 2019Defending Against Neural Fake Newscited by 559
  6. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  7. 2021ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generationcited by 260
  8. 2019Adaptation of Deep Bidirectional Multilingual Transformers for Russian Languagecited by 109
  9. 2019The Limitations of Stylometry for Detecting Machine-Generated Fake Newscited by 63
  10. 2018Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networkscited by 58
  11. 2019Argument Generation with Retrieval, Planning, and Realizationcited by 45
  12. 2020Aspect-Controlled Neural Argument Generationcited by 43
3 more
  1. 2020The workweek is the best time to start a family -- A Study of GPT-2 Based Claim Generationcited by 15
  2. 2019Argument Invention from First Principlescited by 8
  3. 2021Traditional Machine Learning and Deep Learning Models for Argumentation Mining in Russian Textscited by 3

Built on by

Not cited yet.