Related papers: Does Your Model Classify Entities Reasonably? Diag…

Predictive models -- learned from observational data not covering the complete data distribution -- can rely on spurious correlations in the data for making predictions. These correlations make the models brittle and hinder generalization.…

Entity extraction is fundamental to many text mining tasks such as organisation name recognition. A popular approach to entity extraction is based on matching sub-string candidates in a document against a dictionary of entities. To handle…

In medical documents, it is possible that an entity of interest not only contains a discontiguous sequence of words but also overlaps with another entity. Entities of such structures are intrinsically hard to recognize due to the large…

Instance features in images exhibit spurious correlations with background features, affecting the training process of deep neural classifiers. This leads to insufficient attention to instance features by the classifier, resulting in…

Entity-aware image captioning aims to describe named entities and events related to the image by utilizing the background knowledge in the associated article. This task remains challenging as it is difficult to learn the association between…

Stance detection is typically framed as predicting the sentiment in a given text towards a target entity. However, this setup overlooks the importance of the source entity, i.e., who is expressing the opinion. In this paper, we emphasize…

The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the…

Spurious correlations are a threat to the trustworthiness of natural language processing systems, motivating research into methods for identifying and eliminating them. However, addressing the problem of spurious correlations requires more…

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on…

We present an ensemble approach for categorizing search query entities in the recruitment domain. Understanding the types of entities expressed in a search query (Company, Skill, Job Title, etc.) enables more intelligent information…

Entity typing (ET) is the problem of assigning labels to given entity mentions in a sentence. Existing works for ET require knowledge about the domain and target label set for a given test instance. ET in the absence of such knowledge is a…

Multimodal Large Language Models (MLLMs) have shown substantial capabilities in integrating visual and textual information, yet frequently rely on spurious correlations, undermining their robustness and generalization in complex multimodal…

Deep neural classifiers tend to rely on spurious correlations between spurious attributes of inputs and targets to make predictions, which could jeopardize their generalization capability. Training classifiers robust to spurious…

The prevailing approach for training and evaluating paraphrase identification models is constructed as a binary classification problem: the model is given a pair of sentences, and is judged by how accurately it classifies pairs as either…

Salience Estimation aims to predict term importance in documents. Due to few existing human-annotated datasets and the subjective notion of salience, previous studies typically generate pseudo-ground truth for evaluation. However, our…

Entity summarization aims at creating brief but informative descriptions of entities from knowledge graphs. While previous work mostly focused on traditional techniques such as clustering algorithms and graph models, we ask how to apply…

Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is generalization from a small amount of…

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…

Deep neural networks often learn and rely on spurious correlations, i.e., superficial associations between non-causal features and the targets. For instance, an image classifier may identify camels based on the desert backgrounds. While it…

Current topic models often suffer from discovering topics not matching human intuition, unnatural switching of topics within documents and high computational demands. We address these concerns by proposing a topic model and an inference…