no code implementations • LREC 2020 • Erion {\c{C}}ano, Ond{\v{r}}ej Bojar
Recent developments in sequence-to-sequence learning with neural networks have considerably improved the quality of automatically generated text summaries and document keywords, stipulating the need for even bigger training corpora.
no code implementations • WS 2019 • Erion {\c{C}}ano, Ond{\v{r}}ej Bojar
Using data-driven models for solving text summarization or similar tasks has become very common in the last years.
no code implementations • NAACL 2019 • Erion {\c{C}}ano, Ond{\v{r}}ej Bojar
Most of the proposed supervised and unsupervised methods for keyphrase generation are unable to produce terms that are valuable but do not appear in the text.