| Summary: | In this work, we introduce a software testbed for temporal processing of Portuguese texts, composed by several building blocks: identification, classification and resolution of temporal expressions and temporal text segmentation. Starting from a simple document, we can reach a set of temporally annotated segments, which enables the establishment of relationships between words and time. This tem- porally enriched information is then placed into an Information Retrieval system. This work represents a step forward for Portuguese language processing, with noto- rious lack of tools. Its main novelty is temporal segmentation of texts. Even with target application in temporal aware Information Retrieval, the described software tools can be used in other application scenarios.
|
|---|