Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation

Meyer, Francois and Buys, Jan (2024) Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation, Proceedings of Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024),, Turin, Italy.

Text 2024.lrec-main.1464.pdf Download (313kB)

Abstract

Most data-to-text datasets are for English, so the difficulties of modelling data-to-text for low-resource languages are largely unexplored. In this paper we tackle data-to-text for isiXhosa, which is low-resource and agglutinative. We introduce Triples-to-isiXhosa (T2X), a new dataset based on a subset of WebNLG, which presents a new linguistic context that shifts modelling demands to subword-driven techniques. We also develop an evaluation framework for T2X that measures how accurately generated text describes the data. This enables future users of T2X to go beyond surface-level metrics in evaluation. On the modelling side we explore two classes of methods --- dedicated data-to-text models trained from scratch and pretrained language models (PLMs). We propose a new dedicated architecture aimed at agglutinative data-to-text, the Subword Segmental Pointer Generator (SSPG). It jointly learns to segment words and copy entities, and outperforms existing dedicated models for 2 agglutinative languages (isiXhosa and Finnish). We investigate pretrained solutions for T2X, which reveals that standard PLMs come up short. Fine-tuning machine translation models emerges as the best method overall. These findings underscore the distinct challenge presented by T2X: neither well-established data-to-text architectures nor customary pretrained methodologies prove optimal. We conclude with a qualitative analysis of generation errors and an ablation study.

Item Type:	Conference paper
Subjects:	Computing methodologies > Artificial intelligence > Natural language processing Computing methodologies > Artificial intelligence > Natural language processing > Natural language generation Computing methodologies > Artificial intelligence > Natural language processing > Phonology / morphology
Date Deposited:	08 Aug 2024 08:48
Last Modified:	08 Aug 2024 08:48
URI:	https://pubs.cs.uct.ac.za/id/eprint/1668

Actions (login required)

View Item