e-SNLI-VE: Corrected Visual-Textual Entailment with Natural Language Explanations
Published in
(2020)External Links:
TL
TL;DR
This paper presents a data collection effort to correct the class with the highest error rate in SNLI-VE, and re-evaluate an existing model on the corrected corpus, which is called SN LI-VE-2.0, and introduces e-SNLI-UTE, which appends human-written natural language explanations to SNLI -VE- 2.0.
Abstract
The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning. However, the automatic way in which SNLI-VE has been assembled (via combining parts of two related datasets) gives rise to a large number of errors in the labels of this corpus. In this paper, we first present a data collection effort to correct the class with the highest error rate in SNLI-VE. Secondly, we re-evaluate an existing model on the corrected corpus, which we call SNLI-VE-2.0, and provide a quantitative comparison with its performance on the non-corrected corpus. Thirdly, we introduce e-SNLI-VE, which appends human-written natural language explanations to SNLI-VE-2.0. Finally, we train models that learn from these explanations at training time, and output such explanations at testing time.
References15 items
1
e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
2
Multimodal Logical Inference System for Visual-Textual Entailment
3
Visual Entailment: A Novel Task for Fine-Grained Image Understanding
4
e-SNLI: Natural Language Inference with Natural Language Explanations
5