SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Ziyao, Wang, Houfeng
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929421130137600
author Xu, Ziyao
Wang, Houfeng
author_facet Xu, Ziyao
Wang, Houfeng
contents Compositional generalization is an important ability of language models and has many different manifestations. For data-to-text generation, previous research on this ability is limited to a single manifestation called Systematicity and lacks consideration of large language models (LLMs), which cannot fully cover practical application scenarios. In this work, we propose SPOR, a comprehensive and practical evaluation method for compositional generalization in data-to-text generation. SPOR includes four aspects of manifestations (Systematicity, Productivity, Order invariance, and Rule learnability) and allows high-quality evaluation without additional manual annotations based on existing datasets. We demonstrate SPOR on two different datasets and evaluate some existing language models including LLMs. We find that the models are deficient in various aspects of the evaluation and need further improvement. Our work shows the necessity for comprehensive research on different manifestations of compositional generalization in data-to-text generation and provides a framework for evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10650
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation
Xu, Ziyao
Wang, Houfeng
Computation and Language
Compositional generalization is an important ability of language models and has many different manifestations. For data-to-text generation, previous research on this ability is limited to a single manifestation called Systematicity and lacks consideration of large language models (LLMs), which cannot fully cover practical application scenarios. In this work, we propose SPOR, a comprehensive and practical evaluation method for compositional generalization in data-to-text generation. SPOR includes four aspects of manifestations (Systematicity, Productivity, Order invariance, and Rule learnability) and allows high-quality evaluation without additional manual annotations based on existing datasets. We demonstrate SPOR on two different datasets and evaluate some existing language models including LLMs. We find that the models are deficient in various aspects of the evaluation and need further improvement. Our work shows the necessity for comprehensive research on different manifestations of compositional generalization in data-to-text generation and provides a framework for evaluation.
title SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation
topic Computation and Language
url https://arxiv.org/abs/2405.10650