Reproducing Omitted Temporal Expressions in Japanese News for Retrieval-Augmented Applications

Researchers introduced jaROTE, a rule-based pipeline that reproduces omitted temporal expressions in Japanese news articles as concrete dates or intervals using the publication date as external context before indexing for search and retrieval-augmented generation (RAG) systems. Experiments on two news corpora showed jaROTE achieves high performance and remains competitive with large language models while offering a fast, low-cost pipeline, and temporal reproduction improved time-constrained lexical retrieval. The work, published as arXiv:2609.09569v1, addresses temporal mismatches and unstable LLM interpretation caused by day-only or month-only mentions in standalone article text.

arXiv:2609.09569v1 Announce Type: new Abstract: News articles often contain omitted temporal expressions, such as day-only or month-only mentions, which must be interpreted with reference to the publication date. When such articles are indexed or processed as standalone text in search and retrieval-augmented generation RAG systems, these omissions can cause temporal mismatches and unstable interpretation by large language models. We focus on reproducing omitted temporal expressions as concrete dates or intervals using the publication date as external context before the articles are indexed for search and RAG applications. Specifically, building on established temporal-expression extraction and normalization techniques and informed by a manual analysis of Japanese news articles, we propose jaROTE, a rule-based pipeline for Japanese news. Experiments on two news corpora demonstrate that jaROTE achieves high performance, and remains competitive with LLMs while providing a fast, low-cost pipeline. We further show that temporal reproduction improves time-constrained lexical retrieval, demonstrating the practical value of publication-date-grounded normalization for Japanese news retrieval.