2 code implementations • 18 Apr 2024 • Nicolay Rusnachenko, Anton Golubev, Natalia Loukachevitch
Reasoning capabilities of the fine-tuned Flan-T5 models with THoR achieve at least 5% increment with the base-size model compared to the results of the zero-shot experiment.
2 code implementations • 4 Apr 2024 • Nicolay Rusnachenko, HuiZhi Liang
Inspired by the most recent advances in Chain-of-Thought, in this work, we exploit the existing three-hop reasoning approach (THOR) to perform large language model instruction-tuning for answering: emotion states (THOR-state), and emotion caused by one speaker to the other (THOR-cause).
1 code implementation • 28 May 2023 • Anton Golubev, Nicolay Rusnachenko, Natalia Loukachevitch
The paper describes the RuSentNE-2023 evaluation devoted to targeted sentiment analysis in Russian news texts.
2 code implementations • 23 Jun 2020 • Nicolay Rusnachenko, Natalia Loukachevitch
In this paper, we provide a study on attention-based context encoders in the sentiment attitude extraction task.
4 code implementations • 20 Jun 2020 • Nicolay Rusnachenko, Natalia Loukachevitch
In this paper, we provide a study on attention-based context encoders in the sentiment attitude extraction task.
1 code implementation • 19 Jun 2020 • Natalia Loukachevitch, Nicolay Rusnachenko
Texts can convey several types of inter-related information concerning opinions and attitudes.
no code implementations • RANLP 2019 • Nicolay Rusnachenko, Natalia Loukachevitch, Elena Tutubalina
News articles often convey attitudes between the mentioned subjects, which is essential for understanding the described situation.
2 code implementations • 27 Aug 2018 • Natalia Loukachevitch, Nicolay Rusnachenko
In this paper we present the RuSentRel corpus including analytical texts in the sphere of international relations.