2nd Workshop on Practical LLM-assisted Data-to-Text Generation (Practical D2T 2024)
The 2nd Workshop on Practical LLM-assisted Data-to-Text Generation (Practical D2T 2024) will be held in conjunction with the 24th International Conference on Natural Language Generation (INLG 2024). The workshop aims to bring together researchers working on data-to-text (D2T) systems using large language models (LLMs), with a focus on practical applications and solutions to neural model issues. The workshop will feature a special track for neuro-symbolic D2T approaches and a shared task in D2T evaluation focused on semantic accuracy.
The workshop will be a full-day in-person-only event, and contributions are welcome in the form of long (8 pages) or short (4 pages) papers on various topics related to LLM-assisted D2T systems, including design, implementation, evaluation, cross-domain adaptation, user perceptions, bias and fairness, low-resource languages and domains, error analysis, and human-in-the-loop approaches. The special track on neuro-symbolic D2T will feature papers that combine neural and symbolic approaches to improve explainability and reduce dependence on training data.
The shared task on improving semantic accuracy of D2T systems will involve generating textual reports from various domains using LLM-assisted D2T systems. Participants will receive testing data obtained from public APIs, and will be evaluated based on system robustness and objective evaluation, rather than metrics scores. The system reaching the highest correlation with humans will be declared the winner.
For more information, visit the workshop website or contact the organizer at d2t2024 at googlegroups.com.