Self-Supervised Summarization via Reinforcement Learning
| Název práce v češtině: | Automatická sumarizace z neanotovaných dat pomocí zpětnovazebního učení |
|---|---|
| Název v anglickém jazyce: | Self-Supervised Summarization via Reinforcement Learning |
| Klíčová slova: | summarization|reinforcement learning|language model|self-supervision |
| Klíčová slova anglicky: | sumarizace|zpětnovazební učení|jazykový model|učení s vlastním dohledem |
| Akademický rok vypsání: | 2023/2024 |
| Typ práce: | diplomová práce |
| Jazyk práce: | angličtina |
| Ústav: | Ústav formální a aplikované lingvistiky (32-UFAL) |
| Vedoucí / školitel: | doc. RNDr. Ondřej Bojar, Ph.D. |
| Řešitel: | skrytý - zadáno a potvrzeno stud. odd. |
| Datum přihlášení: | 21.12.2023 |
| Datum zadání: | 21.12.2023 |
| Datum potvrzení stud. oddělením: | 21.12.2023 |
| Datum a čas obhajoby: | 10.06.2024 09:00 |
| Datum odevzdání elektronické podoby: | 02.05.2024 |
| Datum odevzdání tištěné podoby: | 02.05.2024 |
| Datum proběhlé obhajoby: | 10.06.2024 |
| Oponenti: | RNDr. Milan Straka, Ph.D. |
| Konzultanti: | Mgr. Aleš Tamchyna, Ph.D. |
| Zásady pro vypracování |
| The goal of the master thesis is to explore the approach of reinforcement learning (RL) for automatic text summarization.
Text summarization datasets (a large collection of pairs of long texts and their abridged counterparts) are expensive to create and thus often consist of already existing data pairs like paper-abstract or news article-highlight paragraph, which semantically differ from summarization. The thesis will design, implement and experiment with a learning approach that reduces the need for supervised training data by self-supervision: one part of the model (“summarizer”) will try to learn to summarize and another part of the model (“predictor”) will be assessing the usefulness of each token for this summarization, thus providing signal for the first part. Notably, this signal is not a direct indication on how to generate the summary, so it needs to be processed in the framework of reinforcement learning (RL). An inherent part of the exploration is how to best combine this RL signal with the standard supervised summarization objective. As a starting point, the predictor will be trained once and fixed throughout the training of the summarizer. As an extension, the thesis may explore the option of joint or iterative training. |
| Seznam odborné literatury |
| Fabbri, Alexander R., et al. "Summeval: Re-evaluating summarization evaluation." Transactions of the Association for Computational Linguistics 9 (2021): 391-409.
Nallapati, Ramesh, et al. "Abstractive text summarization using sequence-to-sequence RNNs and beyond." arXiv preprint arXiv:1602.06023 (2016). Paszke, Adam, et al. "Pytorch: An imperative style, high-performance deep learning library." Advances in neural information processing systems 32 (2019). Gao, Yang, Wei Zhao, and Steffen Eger. "SUPERT: Towards new frontiers in unsupervised evaluation metrics for multi-document summarization." arXiv preprint arXiv:2005.03724 (2020). Dessì, Roberto, et al. "Cross-Domain Image Captioning with Discriminative Finetuning." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023. |