We tackle societal bias in image-text datasets by removing spurious correlations between protected groups and image attributes. Traditional methods only target labeled attributes, ignoring biases from unlabeled ones. Using text-guided inpainting models, our approach ensures protected group independence from all attributes and mitigates inpainting biases through data filtering. Evaluations on multi-label image classification and image captioning tasks show our method effectively reduces bias without compromising performance across various models. Specifically, we achieve an average societal bias reduction of 46.1% in leakage-based bias metrics for multi-label classification and 74.8% for image captioning.

Large language models (LLMs) have enhanced the capacity of vision-language models to caption visual text. This generative approach to image caption enrichment further makes textual captions more descriptive, improving alignment with the visual context. However, while many studies focus on the benefits of generative caption enrichment (GCE), are there any negative side effects? We compare standard-format captions and recent GCE processes from the perspectives of gender bias and hallucination, showing that enriched captions suffer from increased gender bias and hallucination. Furthermore, models trained on these enriched captions amplify gender bias by an average of 30.9% and increase hallucination by 59.5%. This study serves as a caution against the trend of making captions more descriptive.

We annotate 35,000 SNS posts with both the writer’s subjective sentiment polarity labels and the reader’s objective ones to construct a Japanese sentiment analysis dataset. Our dataset includes intensity labels (none, weak, medium, and strong) for each of the eight basic emotions by Plutchik (joy, sadness, anticipation, surprise, anger, fear, disgust, and trust) as well as sentiment polarity labels (strong positive, positive, neutral, negative, and strong negative). Previous studies on emotion analysis have studied the analysis of basic emotions and sentiment polarity independently. In other words, there are few corpora that are annotated with both basic emotions and sentiment polarity. Our dataset is the first large-scale corpus to annotate both of these emotion labels, and from both the writer’s and reader’s perspectives. In this paper, we analyze the relationship between basic emotion intensity and sentiment polarity on our dataset and report the results of benchmarking sentiment polarity classification.

We propose a method for personalized emotional intensity estimation based on a writer’s personality test for Japanese SNS posts. Existing emotion analysis models are difficult to accurately estimate the writer’s subjective emotions behind the text. We personalize the emotion analysis using not only the text but also the writer’s personality information. Experimental results show that personality information improves the performance of emotional intensity estimation. Furthermore, a hybrid model combining the existing personalized method with ours achieved state-of-the-art performance.

The impressive performances of pre-trained visually grounded language models have motivated a growing body of research investigating what has been learned during the pre-training. As a lot of these models are based on Transformers, several studies on the attention mechanisms used by the models to learn to associate phrases with their visual grounding in the image have been conducted. In this work, we investigate how supervising attention directly to learn visual grounding can affect the behavior of such models. We compare three different methods on attention supervision and their impact on the performances of a state-of-the-art visually grounded language model on two popular vision-and-language tasks.

We annotate 17,000 SNS posts with both the writer’s subjective emotional intensity and the reader’s objective one to construct a Japanese emotion analysis dataset. In this study, we explore the difference between the emotional intensity of the writer and that of the readers with this dataset. We found that the reader cannot fully detect the emotions of the writer, especially anger and trust. In addition, experimental results in estimating the emotional intensity show that it is more difficult to estimate the writer’s subjective labels than the readers’. The large gap between the subjective and objective emotions imply the complexity of the mapping from a post to the subjective emotion intensities, which also leads to a lower performance with machine learning models.

We introduce the IDSOU submission for the WNUT-2020 task 2: identification of informative COVID-19 English Tweets. Our system is an ensemble of pre-trained language models such as BERT. We ranked 16th in the F1 score.

In this paper, we propose a full pipeline of analysis of a large corpus about a century of public meeting in historical Australian news papers, from construction to visual exploration. The corpus construction method is based on image processing and OCR. We digitize and transcribe texts of the specific topic of public meeting. Experiments show that our proposed method achieves a F-score of 87.8% for corpus construction. As a result, we built a content search tool for temporal and semantic content analysis.

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.