Related papers: Automatic Language Identification for Celtic Texts

We evaluate cognitive impairment (CI) classification from transcripts of speech in English, Slovene, and Korean. We compare zero-shot large language models (LLMs) used as direct classifiers under three input settings -- transcript-only,…

We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves…

Social media has effectively become the prime hub of communication and digital marketing. As these platforms enable the free manifestation of thoughts and facts in text, images and video, there is an extensive need to screen them to protect…

In recent years, sentiment analysis has gained significant importance in natural language processing. However, most existing models and datasets for sentiment analysis are developed for high-resource languages, such as English and Chinese,…

Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed feature schemas. We formulate feature discovery as a…

The difficulty of acquiring abundant, high-quality data, especially in multi-lingual contexts, has sparked interest in addressing low-resource scenarios. Moreover, current literature rely on fixed expressions from language IDs, which…

3D visual grounding is a challenging task that often requires direct and dense supervision, notably the semantic label for each object in the scene. In this paper, we instead study the naturally supervised setting that learns from only 3D…

We address the problem of efficient acoustic-model refinement (continuous retraining) using semi-supervised and active learning for a low resource Indian language, wherein the low resource constraints are having i) a small labeled corpus…

In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some…

In this paper, we propose a new text recognition model based on measuring the visual similarity of text and predicting the content of unlabeled texts. First a Siamese convolutional network is trained with deep supervision on a labeled…

The rapid evolution of large language models (LLMs) has revolutionized various fields, including the identification and discovery of human values within text data. While traditional NLP models, such as BERT, have been employed for this…

This paper presents an ensemble system combining the output of multiple SVM classifiers to native language identification (NLI). The system was submitted to the NLI Shared Task 2017 fusion track which featured students essays and spoken…

Large language models (LLMs) have shown impressive capabilities across various tasks, but their performance on domain-specific tasks remains limited. While methods like retrieval augmented generation and fine-tuning can help to address…

(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the…

Low-resourced data presents a significant challenge for neural machine translation. In most cases, the low-resourced environment is caused by high costs due to the need for domain experts or the lack of language experts. Therefore,…

Most research on hate speech detection has focused on English where a sizeable amount of labeled training data is available. However, to expand hate speech detection into more languages, approaches that require minimal training data are…

Expanding new functionalities efficiently is an ongoing challenge for single-turn task-oriented dialogue systems. In this work, we explore functionality-specific semi-supervised learning via self-training. We consider methods that augment…

Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three…

Training models on low-resource named entity recognition tasks has been shown to be a challenge, especially in industrial applications where deploying updated models is a continuous effort and crucial for business operations. In such cases…

Decoder-only large language models (LLMs) excel in high-resource languages across various tasks through few-shot or even zero-shot in-context learning (ICL). However, their performance often does not transfer well to low-resource languages,…