Related papers: Language Variety Identification with True Labels

Performance in Speech Emotion Recognition (SER) on a single language has increased greatly in the last few years thanks to the use of deep learning techniques. However, cross-lingual SER remains a challenge in real-world applications due to…

Multi-task Learning (MTL) for classification with disjoint datasets aims to explore MTL when one task only has one labeled dataset. In existing methods, for each task, the unlabeled datasets are not fully exploited to facilitate this task.…

Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…

Access to sign language data is far from adequate. We show that it is possible to collect the data from social networking services such as TikTok, Instagram, and YouTube by applying data filtering to enforce quality standards and by…

Stylistic variation in text needs to be studied with different aspects including the writer's personal traits, interpersonal relations, rhetoric, and more. Despite recent attempts on computational modeling of the variation, the lack of…

The performance of large language models (LLMs) is deeply influenced by the quality and composition of their training data. While much of the existing work has centered on English, there remains a gap in understanding how to construct…

Large language models (LLMs) have made significant progress in generating codes from textual prompts. However, existing benchmarks have mainly concentrated on translating English prompts to multilingual codes or have been constrained to…

Advancements in Large Language Models (LLMs) have significantly enhanced instruction-following capabilities. However, most Instruction Fine-Tuning (IFT) datasets are predominantly in English, limiting model performance in other languages.…

We present our shared task on text-based emotion detection, covering more than 30 languages from seven distinct language families. These languages are predominantly low-resource and are spoken across various continents. The data instances…

Semi-supervised learning (SSL) has been extensively studied to improve the generalization ability of deep neural networks for visual recognition. To involve the unlabelled data, most existing SSL methods are based on common density-based…

Human variation in labeling is often considered noise. Annotation projects for machine learning (ML) aim at minimizing human label variation, with the assumption to maximize data quality and in turn optimize and maximize machine learning…

We introduce TextSeal, a state-of-the-art watermark for large language models. Building on Gumbel-max sampling, TextSeal introduces dual-key generation to restore output diversity, along with entropy-weighted scoring and multi-region…

Machine learning (ML) based approaches are increasingly being used in a number of applications with societal impact. Training ML models often require vast amounts of labeled data, and crowdsourcing is a dominant paradigm for obtaining…

Legal multi-label classification is a critical task for organizing and accessing the vast amount of legal documentation. Despite its importance, it faces challenges such as the complexity of legal language, intricate label dependencies, and…

The increase in the use of microblogging came along with the rapid growth on short linguistic data. On the other hand deep learning is considered to be the new frontier to extract meaningful information out of large amount of raw data in an…

How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper establishes four key results. First, we demonstrate, through…

As Large Language Models (LLMs) expand across multilingual domains, evaluating their performance in under-represented languages becomes increasingly important. European Portuguese (pt-PT) is particularly affected, as existing training data…

Automatic speaker verification task has made great achievements using deep learning approaches with the large-scale manually annotated dataset. However, it's very difficult and expensive to collect a large amount of well-labeled data for…

A major challenge of multi-label text classification (MLTC) is to stimulatingly exploit possible label differences and label correlations. In this paper, we tackle this challenge by developing Label-Wise Pre-Training (LW-PT) method to get a…

Dialect differences caused by regional, social, and economic factors cause performance discrepancies for many groups of language technology users. Inclusive and equitable language technology must critically be dialect invariant, meaning…