We analyze the behaviors of open large language models (LLMs) on the task of data-to-text
(D2T) generation, ie, generating coherent and relevant text from structured data. To avoid …

LLMs like GPT are great at tasks involving English which dominates in their training data. In
this paper, we look at how they cope with tasks involving languages that are severely under …

We investigate to which extent open large language models (LLMs) can generate coherent
and relevant text from structured data. To prevent bias from benchmarks leaked into LLM …

The performance of NLP methods for severely under-resourced languages cannot currently
hope to match the state of the art in NLP methods for well resourced languages. We explore …

Curriculum learning has been used to improve the quality of text generation systems by
ordering the training samples according to a particular schedule in various tasks. In the …

While the WebNLG dataset has prompted much research on generation from knowledge
graphs, little work has examined how well models trained on the WebNLG data generalise …

In this paper, we present our approach to the GEM Shared Task at the INLG'24 Generation
Challenges, which focuses on generating data-to-text in multiple languages, including low …

This paper describes the DipInfo-UniTo system participating to the GEM shared task 2024.
We participate only to the Data-to-Text (D2T) task. The DipInfo-UniTo system is based on …

A relatively under-explored area in research on neural natural language generation is the
impact of the data representation on text quality. Here we report experiments on two leading …

Data-to-text generation systems need to produce texts with high levels of seman-tic
accuracy. Rule-based systems can guarantee this aspect, but their fluency and adaptability …