Related papers: MaTableGPT: GPT-based Table Data Extractor from Ma…

Advances in machine learning research drive progress in real-world applications. To ensure this progress, it is important to understand the potential pitfalls on the way from a novel method's success on academic benchmarks to its practical…

Huge amount of data is the key of the success of deep learning, however, redundant information impairs the generalization ability of the model and increases the burden of calculation. Dataset Distillation (DD) compresses the original…

Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting. Replay-based methods address this by maintaining a small memory buffer…

Efficient and adaptable deep learning models are an important area of deep learning research, driven by the need for highly efficient models on edge devices. Few-shot learning enables the use of deep learning models in low-data regimes, a…

There is an increasing interest in leveraging Large Language Models (LLMs) for managing structured data and enhancing data science processes. Despite the potential benefits, this integration poses significant questions regarding their…

This paper introduces a novel approach for efficiently distilling LLMs into smaller, application-specific models, significantly reducing operational costs and manual labor. Addressing the challenge of deploying computationally intensive…

Automatic extraction of medical information from clinical documents poses several challenges: high costs of required clinical expertise, limited interpretability of model predictions, restricted computational resources and privacy…

The task of natural language table retrieval (NLTR) seeks to retrieve semantically relevant tables based on natural language queries. Existing learning systems for this task often treat tables as plain text based on the assumption that…

While Pairwise Ranking Prompting (PRP) with Large Language Models (LLMs) is one of the most effective zero-shot document ranking methods, it has a quadratic computational complexity with respect to the number of documents to be ranked, as…

Structured pruning of Generative Pre-trained Transformers (GPTs) offers a promising path to efficiency but often suffers from irreversible performance degradation due to the discarding of transformer blocks. In this paper, we introduce…

Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality. In this paper, we propose a knowledge distillation based decision trees extension, dubbed rectified…

In recent times, transformer networks have achieved state-of-the-art performance in a wide range of natural language processing tasks. Here we present a workflow based on the fine-tuning of BERT models for different downstream tasks, which…

Text data augmentation is an effective strategy for overcoming the challenge of limited sample sizes in many natural language processing (NLP) tasks. This challenge is especially prominent in the few-shot learning scenario, where the data…

Relation extraction is an efficient way of mining the extraordinary wealth of human knowledge on the Web. Existing methods rely on domain-specific training data or produce noisy outputs. We focus here on extracting targeted relations from…

Extracting specific items from 10-K reports is challenging due to variations in document formats and item presentation. To improve over traditional rule-based approaches, this study introduces and compares two advanced item segmentation…

In this work, we address question answering (QA) over a hybrid of tabular and textual data that are very common content on the Web (e.g. SEC filings), where discrete reasoning capabilities are often required. Recently, large language models…

Scientific documents contain tables that list important information in a concise fashion. Structure and content extraction from tables embedded within PDF research documents is a very challenging task due to the existence of visual features…

Applications of machine learning techniques in materials science are often based on two key ingredients, a set of empirical descriptors and a database of a particular material property of interest. The advent of graph neural networks, such…

Qualitative research delves deeply into individual complex perspectives on technology and various phenomena. However, a meticulous analysis of qualitative data often requires a significant amount of time, especially during the crucial…

Structured (tabular) data in the preclinical and clinical domains contains valuable information about individuals and an efficient table-to-text summarization system can drastically reduce manual efforts to condense this data into reports.…