no code implementations • 4 Apr 2024 • Tinatin Osmonova, Alexey Tikhonov, Ivan P. Yamshchikov
With the rise of computational social science, many scholars utilize data analysis and natural language processing tools to analyze social media, news articles, and other accessible data sources for examining political and social discourse.
no code implementations • 28 Mar 2024 • Aleksandra Sorokovikova, Michael Becker, Ivan P. Yamshchikov
This paper investigates the communication styles and structures of Twitter (X) communities within the vaccination context.
no code implementations • 22 Feb 2024 • Maxim K. Surkov, Ivan P. Yamshchikov
The core idea of this similarity measure is that it is based on relative performance of the "students" on a given task, rather that on the properties of the task itself.
no code implementations • 31 Jan 2024 • Christeena Varghese, Sergey Koshelev, Ivan P. Yamshchikov
This study explores four methods of generating paraphrases in Malayalam, utilizing resources available for English paraphrasing and pre-trained Neural Machine Translation (NMT) models.
no code implementations • 31 Jan 2024 • Aleksandra Sorokovikova, Natalia Fedorova, Sharwin Rezagholi, Ivan P. Yamshchikov
An empirical investigation into the simulation of the Big Five personality traits by large language models (LLMs), namely Llama2, GPT4, and Mixtral, is presented.
no code implementations • 3 Nov 2023 • Alexey Tikhonov, Ivan P. Yamshchikov
In the rapidly evolving landscape of Large Language Models (LLMs), introduction of well-defined and standardized evaluation methodologies remains a crucial challenge.
1 code implementation • 9 Feb 2023 • Anna Bykova, Nikolay Filippov, Ivan P. Yamshchikov
This paper presents a large anonymized dataset of homelessness alongside insights into the data-driven rehabilitation of homeless people.
no code implementations • 20 Nov 2022 • Elizaveta Zhemchuzhina, Nikolai Filippov, Ivan P. Yamshchikov
This paper studies the limits of language models' statistical learning in the context of Zipf's law.
no code implementations • 10 Nov 2022 • Ivan P. Yamshchikov, Alexey Tikhonov, Yorgos Pantis, Charlotte Schubert, Jürgen Jost
In particular, the Placita Philosophorum, together with one of the other Pseudo-Plutarch texts, shows similarities with the texts written by authors from an Alexandrian context (2nd/3rd century CE).
no code implementations • 9 Nov 2022 • Ivan P. Yamshchikov, Alexey Tikhonov
This paper argues that a deeper understanding of narrative and the successful generation of longer subjectively interesting texts is a vital bottleneck that hinders the progress in modern Natural Language Processing (NLP) and may even be in the whole field of Artificial Intelligence.
no code implementations • 4 Aug 2022 • Vladislav D. Mosin, Ivan P. Yamshchikov
Vocabulary transfer is a transfer learning subtask in which language models fine-tune with the corpus-specific tokenization instead of the default one, which is being used during pretraining.
no code implementations • 7 Feb 2022 • Ilya Smirnov, Ivan P. Yamshchikov
The word mover's distance (WMD) is a popular semantic similarity metric for two texts.
1 code implementation • 29 Dec 2021 • Vladislav Mosin, Igor Samenko, Alexey Tikhonov, Borislav Kozlovskii, Ivan P. Yamshchikov
Transformers are responsible for the vast majority of recent advances in natural language processing.
no code implementations • 13 Dec 2021 • Maxim K. Surkov, Vladislav D. Mosin, Ivan P. Yamshchikov
Current state-of-the-art NLP systems use large neural networks that require lots of computational resources for training.
no code implementations • EMNLP (Eval4NLP) 2021 • Alexey Tikhonov, Igor Samenko, Ivan P. Yamshchikov
Every language includes 500+ stories.
1 code implementation • 28 Sep 2021 • Alexey Tikhonov, Ivan P. Yamshchikov
This paper presents a new natural language processing task - Actionable Entities Recognition (AER) - recognition of entities that protagonists could interact with for further plot development.
no code implementations • 24 Sep 2021 • Shaul Solomon, Adam Cohn, Hernan Rosenblum, Chezi Hershkovitz, Ivan P. Yamshchikov
Estimation of semantic similarity is crucial for a variety of natural language processing (NLP) tasks.
no code implementations • 26 Jul 2021 • Anastasia Malysheva, Alexey Tikhonov, Ivan P. Yamshchikov
Narrative generation and analysis are still on the fringe of modern natural language processing yet are crucial in a variety of applications.
no code implementations • 13 Jul 2020 • Alexey Tikhonov, Ivan P. Yamshchikov
It suggests a very simple workaround for this challenge, namely, generation of a drum pattern that could be further used as a foundation for melody generation.
1 code implementation • 13 Jul 2020 • Yana Agafonova, Alexey Tikhonov, Ivan P. Yamshchikov
We describe technical details of the generative system, provide examples of output and discuss the impact of receptive theory, chance discovery and simulation of fringe mental state on the understanding of computational creativity.
1 code implementation • 27 Apr 2020 • Igor Samenko, Alexey Tikhonov, Ivan P. Yamshchikov
This paper shows that, modern word embeddings contain information that distinguishes synonyms and antonyms despite small cosine similarities between corresponding vectors.
no code implementations • 10 Apr 2020 • Ivan P. Yamshchikov, Viacheslav Shibaev, Nikolay Khlebnikov, Alexey Tikhonov
The rapid development of such natural language processing tasks as style transfer, paraphrase, and machine translation often calls for the use of semantic similarity metrics.
no code implementations • 12 Mar 2020 • Ivan P. Yamshchikov, Cyrille Merleau Nono Saha, Igor Samenko, Jürgen Jost
This position paper looks into the formation of language and shows ties between structural properties of the words in the English language and their polysemy.
no code implementations • WS 2019 • Ivan P. Yamshchikov, Viacheslav Shibaev, Aleksander Nagaev, Jürgen Jost, Alexey Tikhonov
This paper focuses on latent representations that could effectively decompose different aspects of textual information.
1 code implementation • IJCNLP 2019 • Alexey Tikhonov, Viacheslav Shibaev, Aleksander Nagaev, Aigul Nugmanova, Ivan P. Yamshchikov
Second, starting with certain values of bilingual evaluation understudy (BLEU) between input and output and accuracy of the sentiment transfer the optimization of these two standard metrics diverge from the intuitive goal of the style transfer task.
Ranked #1 on Text Style Transfer on Yelp Review Dataset (Small)
no code implementations • 13 Aug 2018 • Alexey Tikhonov, Ivan P. Yamshchikov
A number of recent machine learning papers work with an automated style transfer for texts and, counter to intuition, demonstrate that there is no consensus formulation of this NLP task.
no code implementations • 17 Jul 2018 • Alexey Tikhonov, Ivan P. Yamshchikov
This paper addresses the problem of stylized text generation in a multilingual setup.