To Drop or Not to Drop? Predicting Argument Ellipsis Judgments: A Case Study in Japanese
This work addresses the problem of understanding human discourse processing and improving writing assistance for argument ellipsis in pro-drop languages like Japanese, though it is incremental as it builds on existing linguistic and computational methods.
This study investigates the factors influencing native speakers' decisions to omit arguments in Japanese sentences, using over 2,000 annotated data points to identify common criteria and quantitative characteristics, and examines the performance of a language model-based prediction system, revealing gaps in specific linguistic aspects.
Speakers sometimes omit certain arguments of a predicate in a sentence; such omission is especially frequent in pro-drop languages. This study addresses a question about ellipsis -- what can explain the native speakers' ellipsis decisions? -- motivated by the interest in human discourse processing and writing assistance for this choice. To this end, we first collect large-scale human annotations of whether and why a particular argument should be omitted across over 2,000 data points in the balanced corpus of Japanese, a prototypical pro-drop language. The data indicate that native speakers overall share common criteria for such judgments and further clarify their quantitative characteristics, e.g., the distribution of related linguistic factors in the balanced corpus. Furthermore, the performance of the language model-based argument ellipsis judgment model is examined, and the gap between the systems' prediction and human judgments in specific linguistic aspects is revealed. We hope our fundamental resource encourages further studies on natural human ellipsis judgment.