Ampomah, Isaac and Burton, James and Enshaei, Amir and Al Moubayed, Noura (2022) 'Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task.', Language Resources and Evaluation Conference 2022 Marseille, France, 20-25 June 2022.
Numerical tables are widely employed to communicate or report the classification performance of machine learning (ML) models with respect to a set of evaluation metrics. For non-experts, domain knowledge is required to fully understand and interpret the information presented by numerical tables. This paper proposes a new natural language generation (NLG) task where neural models are trained to generate textual explanations, analytically describing the classification performance of ML models based on the metrics’ scores reported in the tables. Presenting the generated texts along with the numerical tables will allow for a better understanding of the classification performance of ML models. We constructed a dataset comprising numerical tables paired with their corresponding textual explanations written by experts to facilitate this NLG task. Experiments on the dataset are conducted by fine-tuning pre-trained language models (T5 and BART) to generate analytical textual explanations conditioned on the information in the tables. Furthermore, we propose a neural module, Metrics Processing Unit (MPU), to improve the performance of the baselines in terms of correctly verbalising the information in the corresponding table. Evaluation and analysis conducted indicate, that exploring pre-trained models for data-to-text generation leads to better generalisation performance and can produce high-quality textual explanations.
|Item Type:||Conference item (Paper)|
|Full text:||(AM) Accepted Manuscript|
Download PDF (945Kb)
|Publisher Web site:||http://www.lrec-conf.org/proceedings/|
|Date accepted:||No date available|
|Date deposited:||27 April 2022|
|Date of first online publication:||20 June 2022|
|Date first made open access:||26 June 2022|
Save or Share this output
|Look up in GoogleScholar|