Natural Language Generation

Many domains and tasks in natural language generation (NLG) are inherently ‘low-resource’, where training data, tools and linguistic …

Most NLG is low-resource, even in high-resource languages (Howcroft & Gkatzia 2022). In this talk I will highlight our efforts to develop a data collection paradigm which focuses on question answering conversations and (dialogue) summarisation for low-resource languages.

Human assessment remains the most trusted form of evaluation in natural language generation, among other areas of NLP, but there is huge variation in terms of both what is assessed and how it is assessed.

Human assessment remains the most trusted forrm of evaluation in NLG, but highly diverse approaches and a proliferation of different …

Current standards for designing and reporting human evaluations in NLP mean it is generally unclear which evaluations are comparable …

Neural natural language generation (NNLG) systems are known for their pathological outputs, i.e. generating text which is unrelated to …

At this workshop we highlighted several sources of noise for neural NLG (semantic, typographic, and grammatical) before presenting the impact of semantic noise on the quality of NNLG (in a preview of our INLG paper) and how these different kinds of errors impact human evaluations of perceived text quality.