Related papers: Auxiliary-Hyperparameter-Free Sampling: Entropy Eq…

The use of Natural Language Processing (NLP) for Automated Essay Scoring (AES) has been well explored in the English language, with benchmark models exhibiting performance comparable to human scorers. However, AES in Hindi and other…

Text-image alignment constitutes a foundational challenge in multimedia content understanding, where effective modeling of cross-modal semantic correspondences critically enhances retrieval system performance through joint embedding space…

Current abstractive summarization systems outperform their extractive counterparts, but their widespread adoption is inhibited by the inherent lack of interpretability. To achieve the best of both worlds, we propose EASE, an…

Text classification is a fundamental task for natural language processing, and adapting text classification models across domains has broad applications. Self-training generates pseudo-examples from the model's predictions and iteratively…

Alignment of Large Language Models (LLMs) typically relies on Reinforcement Learning from Human Feedback (RLHF) with gradient-based optimizers such as Proximal Policy Optimization (PPO) or Group Relative Policy Optimization (GRPO). While…

Large Language Models (LLMs) have been found to memorize and recite some of the textual sequences from their training set verbatim, raising broad concerns about privacy and copyright issues when using LLMs. This Textual Sequence…

Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…

The task of Text-to-SQL enables anyone to retrieve information from SQL databases using natural language. While this task has made substantial progress, the two primary evaluation metrics - Execution Accuracy (EXE) and Exact Set Matching…

Entropic Outlier Sparsification (EOS) is proposed as a robust computational strategy for the detection of data anomalies in a broad class of learning methods, including the unsupervised problems (like detection of non-Gaussian outliers in…

Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea…

We consider the linear regression problem under semi-supervised settings wherein the available data typically consists of: (i) a small or moderate sized 'labeled' data, and (ii) a much larger sized 'unlabeled' data. Such data arises…

Recent works have empirically shown the effectiveness of data augmentation (DA) in NLP tasks, especially for those suffering from data scarcity. Intuitively, given the size of generated data, their diversity and quality are crucial to the…

The proliferation of digital interactions across diverse domains, such as healthcare, e-commerce, gaming, and finance, has resulted in the generation of vast volumes of event stream (ES) data. ES data comprises continuous sequences of…

The maximum entropy principle (MEP) apparently allows us to derive, or justify, fundamental results of equilibrium statistical mechanics. Because of this, a school of thought considers the MEP as a powerful and elegant way to make…

Alignment of large language models (LLMs) with human preferences typically relies on supervised reward models or external judges that demand abundant annotations. However, in fields that rely on professional knowledge, such as medicine and…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient. In this work, we propose learning both the energy function and an amortized approximate sampling…

Large language models (LLMs) are widely recognized for their exceptional capacity to capture semantics meaning. Yet, there remains no established metric to quantify this capability. In this work, we introduce a quantitative metric,…

Automatic Essay Scoring (AES) is a well-established educational pursuit that employs machine learning to evaluate student-authored essays. While much effort has been made in this area, current research primarily focuses on either (i)…

This paper presents a novel sampling scheme for masked non-autoregressive generative modeling. We identify the limitations of TimeVQVAE, MaskGIT, and Token-Critic in their sampling processes, and propose Enhanced Sampling Scheme (ESS) to…