NLG Challenge : Neural Models vs . Templates

By Yevgeniy Puzikov. 2018

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Generation

Citations in the corpus

LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention (2023, background): “Prompt tuning appends a collection of trainable prompt tokens to pre-trained large models, which are inserted either to the input embeddings only [30, 39], or to all of the intermediate layers [35, 38].”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, neutral): “♠TUDA (Puzikov and Gurevych, 2018) templates all implied by architecture”
Handling Rare Items in Data-to-Text Generation (2018, background): “Among them, six teams applied delexi-calisation (Chen et al., 2018; Davoodi et al., 2018; Juraska et al., 2018; Puzikov and Gurevych, 2018; Trisedya et al., 2018; van der Lee et al., 2017), three resorted to the copy mechanism (Chen, 2018; Elder et al., 2018; Gehrmann et al., 2018), two developed…”
A Good Sample is Hard to Find: Noise Injection Sampling and Self-Training for Neural Language Generation Models (2019, methodology): “We compare our models to the best sequence-to-sequence DNN model, Slug (Juraska et al., 2018 (Puzikov and Gurevych, 2018), as determined during the shared task evaluation (Duˇsek et al., 2019).”
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation (2019, result): “When compared to template-based methods, the neural systems win in ﬂuency but fall short regarding content selection and faith-fulness to the input (Puzikov and Gurevych, 2018).”
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence (2020, methodology): “Each target text is split into meaningful fragments and aligned with corresponding data records, either by hand-engineered rules (Kukich, 1983; McKeown, 1992) or statistical induction (Liang et al., 2009; Koncel-Kedziorski et al., 2014; Qin et al., 2018).”