Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Dušek, Ondřej"'
Existing explanation methods for image classification struggle to provide faithful and plausible explanations. This paper addresses this issue by proposing a post-hoc natural language explanation method that can be applied to any CNN-based classifier
Externí odkaz:
http://arxiv.org/abs/2407.20899
Autor:
Helcl, Jindřich, Kasner, Zdeněk, Dušek, Ondřej, Limisiewicz, Tomasz, Macháček, Dominik, Musil, Tomáš, Libovický, Jindřich
This paper presents teaching materials, particularly assignments and ideas for classroom activities, from a new course on large language models (LLMs) taught at Charles University. The assignments include experiments with LLM inference for weather re
Externí odkaz:
http://arxiv.org/abs/2407.19798
We present factgenie: a framework for annotating and visualizing word spans in textual model outputs. Annotations can capture various span-based phenomena such as semantic inaccuracies or irrelevant text. With factgenie, the annotations can be collec
Externí odkaz:
http://arxiv.org/abs/2407.17863
Text style transfer (TST) is an important task in controllable text generation, which aims to control selected attributes of language use, such as politeness, formality, or sentiment, without altering the style-independent content of the text. The fi
Externí odkaz:
http://arxiv.org/abs/2407.16737
Autor:
Mukherjee, Sourabrata, Dušek, Ondrej
Text Style Transfer (TST) is a pivotal task in natural language generation to manipulate text style attributes while preserving style-independent content. The attributes targeted in TST can vary widely, including politeness, authorship, mitigation of
Externí odkaz:
http://arxiv.org/abs/2407.14822
We analyze the performance of large language models (LLMs) on Text Style Transfer (TST), specifically focusing on sentiment transfer and text detoxification across three languages: English, Hindi, and Bengali. Text Style Transfer involves modifying t
Externí odkaz:
http://arxiv.org/abs/2406.05885
Autor:
Mukherjee, Sourabrata, Ojha, Atul Kr., Bansal, Akanksha, Alok, Deepak, McCrae, John P., Dušek, Ondřej
Text style transfer (TST) involves altering the linguistic style of a text while preserving its core content. This paper focuses on sentiment transfer, a vital TST subtask (Mukherjee et al., 2022a), across a spectrum of Indian languages: Hindi, Magah
Externí odkaz:
http://arxiv.org/abs/2405.20805
This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where the text s
Externí odkaz:
http://arxiv.org/abs/2402.07767
Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details, especially regardin
Externí odkaz:
http://arxiv.org/abs/2402.03927
Autor:
Kasner, Zdeněk, Dušek, Ondřej
We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation, i.e., generating coherent and relevant text from structured data. To avoid the issue of LLM training data contamination with standard benchmar
Externí odkaz:
http://arxiv.org/abs/2401.10186