Related papers: Zero-shot Code-Mixed Offensive Span Identification…

Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In this work, we show that the effectiveness of zero-shot…

The advent of Large Language Models (LLMs) has advanced the benchmark in various Natural Language Processing (NLP) tasks. However, large amounts of labelled training data are required to train LLMs. Furthermore, data annotation and training…

Instruction-tuned Large Language Models (LLMs) have exhibited impressive language understanding and the capacity to generate responses that follow specific prompts. However, due to the computational demands associated with training these…

Out-of-distribution (OOD) detection has seen significant advancements with zero-shot approaches by leveraging the powerful Vision-Language Models (VLMs) such as CLIP. However, prior research works have predominantly focused on enhancing…

Recent advancement in large language models (LLMs) has offered a strong potential for natural language systems to process informal language. A representative form of informal language is slang, used commonly in daily conversations and…

Large Language Models (LLMs) have shown strong performance on NLP classification tasks. However, they typically rely on aggregated labels-often via majority voting-which can obscure the human disagreement inherent in subjective annotations.…

In this paper we investigate the use of decoder-based generative transformers for extracting sentiment towards the named entities in Russian news articles. We study sentiment analysis capabilities of instruction-tuned large language models…

Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and prediction results.…

Masked language models (MLMs) are pre-trained with a denoising objective that is in a mismatch with the objective of downstream fine-tuning. We propose pragmatic masking and surrogate fine-tuning as two complementing strategies that exploit…

Large-scale vision-language models (VLMs), such as CLIP, have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets. However, these methods often lack interpretability, as they compute…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple…

This paper describes the system submitted to Dravidian-Codemix-HASOC2021: Hate Speech and Offensive Language Identification in Dravidian Languages (Tamil-English and Malayalam-English). This task aims to identify offensive content in…

Large language models (LLMs) and high-capacity encoders have advanced zero and few-shot classification, but their inference cost and latency limit practical deployment. We propose training lightweight text classifiers using dynamically…

Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for…

The use of derogatory terms in languages that employ code mixing, such as Roman Urdu, presents challenges for Natural Language Processing systems due to unstated grammar, inconsistent spelling, and a scarcity of labeled data. In this work,…

We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the…

Bangla-English code-mixing is widespread across South Asian social media, yet resources for implicit meaning identification in this setting remain scarce. Existing sentiment and sarcasm models largely focus on monolingual English or…

Large language models (LLMs) combined with instruction tuning have shown significant progress in information extraction (IE) tasks, exhibiting strong generalization capabilities to unseen datasets by following annotation guidelines.…

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…