Shrnutí napříč jazyky

• Thesis title in Czech: Shrnutí napříč jazyky
• Thesis title in English: Cross-Language Summarization
• Key words: shrnutí|CLS|XLS|NLP
• English key words: Summarization|CLS|XLS|NLP
• Academic year of topic announcement: 2024/2025
• Thesis type: diploma thesis
• Thesis language: čeština
• Department: Institute of Formal and Applied Linguistics (32-UFAL)
• Supervisor: RNDr. Jiří Hana, Ph.D.
• Author: hidden - assigned by the advisor
• Date of registration: 14.05.2024
• Date of assignment: 16.05.2024

Guidelines

The thesis should explore the methods for cross-language summarization (CLS).
CLS is a task when a document in one language is summarized in another language. Typically, this task involves machine translation before or after summarization, but there are also end-to-end methods.

As part of the thesis, a prototype system should be developed and evaluated. It should summarize documents in a low-resource language, such as Maltese, in another language, for example, English.

References

Wang, J. et al (2022) A Survey on Cross-Lingual Summarization. Transactions of the Association for Computational Linguistics 2022; 10 1304–1323. doi: https://doi.org/10.1162/tacl_a_00520

Bhattacharjee, A. et al (2021). CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs. arXiv:2112.08804.

Huot, F.et al (2023). μPLAN: Summarizing using a Content Plan as Cross-Lingual Bridge. arXiv:2305.14205.

Wan, X. et al (2010). Cross-language document summarization based on machine translation quality prediction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (pp. 917-926).

Ladhak, F. et al (2020). WikiLingua: A new benchmark dataset for cross-lingual abstractive summarization. arXiv:2010.03093.