# Neural Generation for Czech: Data and Baselines

arXiv: https://arxiv.org/abs/1910.05298 · HTML: https://mlsanity.com/paper/1910.05298/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2019.

## Built on by (most cited first, 13 of 13)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding](https://mlsanity.com/paper/2211.07634/) (2022)
- [GEMv2: Multilingual NLG Benchmarking in a Single Line of Code](https://mlsanity.com/paper/2206.11249/) (2022)
- [CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems](https://mlsanity.com/paper/2109.04645/) (2021)
- [Improving Compositional Generalization with Self-Training for Data-to-Text Generation](https://mlsanity.com/paper/2110.08467/) (2021)
- [Automatic Construction of Evaluation Suites for Natural Language Generation Datasets](https://mlsanity.com/paper/2106.09069/) (2021)
- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [TaTa: A Multilingual Table-to-Text Dataset for African Languages](https://mlsanity.com/paper/2211.00142/) (2022)
- [BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation](https://mlsanity.com/paper/2110.09147/) (2021)
- [Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation](https://mlsanity.com/paper/2403.07567/) (2024)
- [CLSE: Corpus of Linguistically Significant Entities](https://mlsanity.com/paper/2211.02423/) (2022)
- [CUNI Submission in WMT22 General Task](https://mlsanity.com/paper/2211.16174/) (2022)

## Abstract (arXiv)

We present the first dataset targeted at end-to-end NLG in Czech in the restaurant domain, along with several strong baseline models using the sequence-to-sequence approach. While non-English NLG is under-explored in general, Czech, as a morphologically rich language, makes the task even harder: Since Czech requires inflecting named entities, delexicalization or copy mechanisms do not work out-of-the-box and lexicalizing the generated outputs is non-trivial. In our experiments, we present two different approaches to this this problem: (1) using a neural language model to select the correct inflected form while lexicalizing, (2) a two-step generation setup: our sequence-to-sequence model generates an interleaved sequence of lemmas and morphological tags, which are then inflected by a morphological generator.