# iParaphrasing: Extracting Visually Grounded Paraphrases via an Image

Source: [iParaphrasing: Extracting Visually Grounded Paraphrases via an Image](<https://www.sota2.com/research/paper/68fa64811e209131cea04eff>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:05:03.439Z

Authors: Chenhui Chu, Mayu Otani, Yuta Nakashima

Published: 2018-06-12T00:58:59.000Z

## Abstract

A paraphrase is a restatement of the meaning of a text in other words. Paraphrases have been studied to enhance the performance of many natural language processing tasks. In this paper, we propose a novel task iParaphrasing to extract visually grounded paraphrases (VGPs), which are different phrasal expressions describing the same visual concept in an image. These extracted VGPs have the potential to improve language and image multimodal tasks such as visual question answering and image captioning. How to model the similarity between VGPs is the key of iParaphrasing. We apply various existing methods as well as propose a novel neural network-based method with image attention, and report the results of the first attempt toward iParaphrasing.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1806.04284>)

[PDF](<https://arxiv.org/pdf/1806.04284.pdf>)
