Related papers: Sentiment Tagging with Partial Labels using Modula…

Task semantics can be expressed by a set of input-output examples or a piece of textual instruction. Conventional machine learning approaches for natural language processing (NLP) mainly rely on the availability of large-scale sets of…

Natural language processing (NLP) applied to information retrieval (IR) and filtering problems may assign part-of-speech tags to terms and, more generally, modify queries and documents. Analytic models can predict the performance of a text…

Classification is an important task in many fields including biomedical research and machine learning. Traditionally, a classification rule is constructed based a bunch of labeled data. Recently, due to technological innovation and…

We propose a meta-learning method for semi-supervised learning that learns from multiple tasks with heterogeneous attribute spaces. The existing semi-supervised meta-learning methods assume that all tasks share the same attribute space,…

The task of predicting affective information in the wild such as seven basic emotions or action units from human faces has gradually become more interesting due to the accessibility and availability of massive annotated datasets. In this…

Supervised models of NLP rely on large collections of text which closely resemble the intended testing setting. Unfortunately matching text is often not available in sufficient quantity, and moreover, within any domain of text, data is…

Understanding sentiment in multimodal conversations is a complex yet crucial challenge toward building emotionally intelligent AI systems. The Multimodal Conversational Aspect-based Sentiment Analysis (MCABSA) Challenge invited participants…

Existing approaches to few-shot learning in NLP rely on large language models (LLMs) and/or fine-tuning of these to generalise on out-of-distribution data. In this work, we propose a novel few-shot learning approach based on soft-label…

Understanding emotions in videos is a challenging task. However, videos contain several modalities which make them a rich source of data for machine learning and deep learning tasks. In this work, we aim to improve video sentiment…

Partial label learning (PLL) is a significant weakly supervised learning framework, where each training example corresponds to a set of candidate labels and only one label is the ground-truth label. For the first time, this paper…

Despite multimodal sentiment analysis being a fertile research ground that merits further investigation, current approaches take up high annotation cost and suffer from label ambiguity, non-amicable to high-quality labeled data acquisition.…

We propose a sequence labeling framework with a secondary training objective, learning to predict surrounding words for every word in the dataset. This language modeling objective incentivises the system to learn general-purpose patterns of…

In the problem of learning with label proportions, which we call LLP learning, the training data is unlabeled, and only the proportions of examples receiving each label are given. The goal is to learn a hypothesis that predicts the…

NLP tasks are often limited by scarcity of manually annotated data. In social media sentiment analysis and related tasks, researchers have therefore used binarized emoticons and specific hashtags as forms of distant supervision. Our paper…

Obtaining annotations for 3D medical images is expensive and time-consuming, despite its importance for automating segmentation tasks. Although multi-task learning is considered an effective method for training segmentation models using…

In this paper, we propose a capsule-based neural network model to solve the semantic segmentation problem. By taking advantage of the extractable part-whole dependencies available in capsule layers, we derive the probabilities of the class…

Deep learning systems thrive on abundance of labeled training data but such data is not always available, calling for alternative methods of supervision. One such method is expectation regularization (XR) (Mann and McCallum, 2007), where…

Multimodal sentiment analysis (MSA) identifies individuals' sentiment states in videos by integrating visual, audio, and text modalities. Despite progress in existing methods, the inherent modality heterogeneity limits the effective capture…

In this paper, we present the first experiments using neural network models for the task of error detection in learner writing. We perform a systematic comparison of alternative compositional architectures and propose a framework for error…

Semantic composition functions have been playing a pivotal role in neural representation learning of text sequences. In spite of their success, most existing models suffer from the underfitting problem: they use the same shared…