Related papers: Analyzing Text Representations under Tight Annotat…

Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and inefficient-motivating the need for efficient data selection methods that reduce annotation costs…

In lifelong learning, a learner faces a sequence of tasks with shared structure and aims to identify and leverage it to accelerate learning. We study the setting where such structure is captured by a common representation of data. Unlike…

Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming. Coarse annotations (e.g., scribbles, coarse polygons) offer an economical…

Despite deep recurrent neural networks (RNNs) demonstrate strong performance in text classification, training RNN models are often expensive and requires an extensive collection of annotated data which may not be available. To overcome the…

Text line segmentation is one of the key steps in historical document understanding. It is challenging due to the variety of fonts, contents, writing styles and the quality of documents that have degraded through the years. In this paper,…

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…

Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a…

The development lifecycle of generative AI systems requires continual evaluation, data acquisition, and annotation, which is costly in both resources and time. In practice, rapid iteration often makes it necessary to rely on synthetic…

Automated fact-checking based on machine learning is a promising approach to identify false information distributed on the web. In order to achieve satisfactory performance, machine learning methods require a large corpus with reliable…

Methods and applications are inextricably linked in science, and in particular in the domain of text-as-data. In this paper, we examine one such text-as-data application, an established economic index that measures economic policy…

The lack of contextual information in text data can make the annotation process of text-based emotion classification datasets challenging. As a result, such datasets often contain labels that fail to consider all the relevant emotions in…

Multi-task learning leverages structural similarities between multiple tasks to learn despite very few samples. Motivated by the recent success of neural networks applied to data-scarce tasks, we consider a linear low-dimensional shared…

Despite the successes of language models, their evaluation remains a daunting challenge for new and existing tasks. We consider the task of text simplification, commonly used to improve information accessibility, where evaluation faces two…

Representation learning aims to extract meaningful lower-dimensional embeddings from data, known as representations. Despite its widespread application, there is no established definition of a ``good'' representation. Typically, the…

Text segmentation is important for signaling a document's structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find important information. The problem…

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

Large deep-learning models for music, including those focused on learning general-purpose music audio representations, are often assumed to require substantial training data to achieve high performance. If true, this would pose challenges…

Incorporating every annotator's perspective is crucial for unbiased data modeling. Annotator fatigue and changing opinions over time can distort dataset annotations. To combat this, we propose to learn a more accurate representation of…

Most machine learning and data analytics applications, including performance engineering in software systems, require a large number of annotations and labelled data, which might not be available in advance. Acquiring annotations often…

We consider the task of generating structured representations of text using large language models (LLMs). We focus on tables and mind maps as representative modalities. Tables are more organized way of representing data, while mind maps…