Update README.md

README.md

@@ -10,7 +10,7 @@ license: apache-2.0
 ---
 This is *t5-base* transformer model trained on Lithuanian news summaries for 175 000 steps.
 It was created during the work [**Generating abstractive summaries of Lithuanian
-news articles using a transformer model**](https://arxiv.org/abs/2105.03279).
+news articles using a transformer model**](https://link.springer.com/chapter/10.1007/978-3-030-88304-1_27).
 
 ## Usage
 ```python
@@ -38,14 +38,22 @@ Output from above would be:
 
 Lietuvos krepšinio federacijos (LKF) prezidento Arvydo Sabonio rezultatyvumo vidurkis yra aukščiausias tarp visų Sovietų Sąjungos rinktinėje atstovavusių žaidėjų, skaičiuojant tuos, kurie sužaidė bent po 50 oficialių rungtynių.
 
-### BibTeX entry and citation info
-```bibtex
-@misc{stankevičius2021generating,
-      title={Generating abstractive summaries of Lithuanian news articles using a transformer model}, 
-      author={Lukas Stankevičius and Mantas Lukoševičius},
-      year={2021},
-      eprint={2105.03279},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL}
+
+If you find our work useful, please cite the following paper:
+``` latex
+@InProceedings{10.1007/978-3-030-88304-1_27,
+author="Stankevi{\v{c}}ius, Lukas
+and Luko{\v{s}}evi{\v{c}}ius, Mantas",
+editor="Lopata, Audrius
+and Gudonien{\.{e}}, Daina
+and Butkien{\.{e}}, Rita",
+title="Generating Abstractive Summaries of Lithuanian News Articles Using a Transformer Model",
+booktitle="Information and Software Technologies",
+year="2021",
+publisher="Springer International Publishing",
+address="Cham",
+pages="341--352",
+abstract="In this work, we train the first monolingual Lithuanian transformer model on a relatively large corpus of Lithuanian news articles and compare various output decoding algorithms for abstractive news summarization. We achieve an average ROUGE-2 score 0.163, generated summaries are coherent and look impressive at first glance. However, some of them contain misleading information that is not so easy to spot. We describe all the technical details and share our trained model and accompanying code in an online open-source repository, as well as some characteristic samples of the generated summaries.",
+isbn="978-3-030-88304-1"
 }
 ```