Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[Paper](https://hlt.bme.hu/en/publ/foszt2oszt)
|
2 |
+
|
3 |
+
We publish an abstractive summarizer for Hungarian, an
|
4 |
+
encoder-decoder model initialized with [huBERT](huggingface.co/SZTAKI-HLT/hubert-base-cc), and fine-tuned on the
|
5 |
+
[ELTE.DH](https://elte-dh.hu/) corpus of former Hungarian news portals. The model produces fluent output in the correct topic, but it hallucinates frequently.
|
6 |
+
Our quantitative evaluation on automatic and human transcripts of news
|
7 |
+
(with automatic and human-made punctuation, [Tündik et al. (2019)](https://www.isca-speech.org/archive/interspeech_2019/tundik19_interspeech.html), [Tündik and Szaszák (2019)](https://www.isca-speech.org/archive/interspeech_2019/szaszak19_interspeech.html)) shows that the model is
|
8 |
+
robust with respect to errors in either automatic speech recognition or
|
9 |
+
automatic punctuation restoration.
|