Role of temporal inference in the recognition of textual inference
This work addresses a specific challenge in natural language processing for text understanding, but appears incremental as it builds on existing inference detection systems by adding a temporal module.
The researchers tackled the problem of recognizing textual inference by developing TIMINF, a system that detects whether one text can be semantically deduced from another, with a focus on temporal inference. They evaluated TIMINF on a test corpus using RTE challenge strategies, though no specific performance numbers were provided.
This project is a part of nature language processing and its aims to develop a system of recognition inference text-appointed TIMINF. This type of system can detect, given two portions of text, if a text is semantically deducted from the other. We focused on making the inference time in this type of system. For that we have built and analyzed a body built from questions collected through the web. This study has enabled us to classify different types of times inferences and for designing the architecture of TIMINF which seeks to integrate a module inference time in a detection system inference text. We also assess the performance of sorties TIMINF system on a test corpus with the same strategy adopted in the challenge RTE.