Related papers: Feature Generation for Robust Semantic Role Labeli…

Neural network based approaches to data-to-text natural language generation (NLG) have gained popularity in recent years, with the goal of generating a natural language prompt that accurately realizes an input meaning representation. To…

The quality of Machine Learning (ML) models strongly depends on the input data, as such Feature Engineering (FE) is often required in ML. In addition, with the proliferation of ML-powered systems, especially in critical contexts, the need…

Recent work leverages the expressive power of generative adversarial networks (GANs) to generate labeled synthetic datasets. These dataset generation methods often require new annotations of synthetic images, which forces practitioners to…

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This…

Feature selection aims to identify the optimal feature subset for enhancing downstream models. Effective feature selection can remove redundant features, save computational resources, accelerate the model learning process, and improve the…

To achieve a flexible and adaptable system, capability ontologies are increasingly leveraged to describe functions in a machine-interpretable way. However, modeling such complex ontological descriptions is still a manual and error-prone…

Large language models (LLMs) are increasingly deployed as agents, expected to decompose goals, invoke tools, and verify results in dynamic environments. Realizing these capabilities requires access to agentic data-structured interaction…

This paper studies the use of language models as a source of synthetic unlabeled text for NLP. We formulate a general framework called ``generate, annotate, and learn (GAL)'' to take advantage of synthetic text within knowledge…

Feature transformation involves generating a new set of features from the original dataset to enhance the data's utility. In certain domains like material performance screening, dimensionality is large and collecting labels is expensive and…

Using Large Language Models (LLMs) to generate synthetic data for model training has become increasingly popular in recent years. While LLMs are capable of producing realistic training data, the effectiveness of data generation is…

This paper contributes to speeding up the design and deployment of engineering dynamical systems by proposing a strategy for exploiting domain and expert knowledge for the automated generation of a dynamical system computational model…

Most NLP datasets are manually labeled, so suffer from inconsistent labeling or limited size. We propose methods for automatically improving datasets by viewing them as graphs with expected semantic properties. We construct a paraphrase…

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

Existing feature engineering methods based on large language models (LLMs) have not yet been applied to multi-label learning tasks. They lack the ability to model complex label dependencies and are not specifically adapted to the…

Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current…

The quality of Machine Learning (ML) models strongly depends on the input data, as such generating high-quality features is often required to improve the predictive accuracy. This process is referred to as Feature Engineering (FE). However,…

Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that synthesize weak…

Detecting semantic types of columns in data lake tables is an important application. A key bottleneck in semantic type detection is the availability of human annotation due to the inherent complexity of data lakes. In this paper, we propose…

We propose a generative framework for joint sequence labeling and sentence-level classification. Our model performs multiple sequence labeling tasks at once using a single, shared natural language output space. Unlike prior discriminative…

Knowledge graphs can represent information about the real-world using entities and their relations in a structured and semantically rich manner and they enable a variety of downstream applications such as question-answering, recommendation…