Related papers: LAQP: Learning-based Approximate Query Processing

Approximate nearest neighbor (ANN) search has achieved great success in many tasks. However, existing popular methods for ANN search, such as hashing and quantization methods, are designed for static databases only. They cannot handle well…

Recent advances in open-domain question answering over tables have widely adopted large language models (LLMs) under the Retriever-Reader architecture. Prior works have effectively leveraged LLMs to tackle the complex reasoning demands of…

Analyzing large datasets requires responsive query execution, but executing SQL queries on massive datasets can be slow. This paper explores whether query execution can begin even before the user has finished typing, allowing results to…

The quality of data driven learning algorithms scales significantly with the quality of data available. One of the most straight-forward ways to generate good data is to sample or explore the data source intelligently. Smart sampling can…

Creating multiple-choice questions to assess reading comprehension of a given article involves generating question-answer pairs (QAPs) and adequate distractors. We present two methods to tackle the challenge of QAP generations: (1) A…

We propose an algorithm for next query recommendation in interactive data exploration settings, like knowledge discovery for information gathering. The state-of-the-art query recommendation algorithms are based on sequence-to-sequence…

We build on the dynamical systems approach to deep learning, where deep residual networks are idealized as continuous-time dynamical systems, from the approximation perspective. In particular, we establish general sufficient conditions for…

Question Generation (QG) is a fundamental NLP task for many downstream applications. Recent studies on open-book QG, where supportive answer-context pairs are provided to models, have achieved promising progress. However, generating natural…

Classification tasks are typically handled using Machine Learning (ML) models, which lack a balance between accuracy and interpretability. This paper introduces a new approach for classification tasks using Large Language Models (LLMs) in…

Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown how to effectively…

Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or…

We consider the problem of evaluating certain types of functional aggregation queries on relational data subject to additive inequalities. Such aggregation queries, with a smallish number of additive inequalities, arise naturally/commonly…

We propose a versatile approach to lightweight, approximate query processing by creating compact but tunably precise representations of larger quantities of original tuples, coined bubbles. Instead of working with tables of tuples, the…

This paper introduces \textbf{Q-tuning}, a novel approach for continual prompt tuning that enables the lifelong learning of a pre-trained language model. When learning a new task, Q-tuning trains a task-specific prompt by adding it to a…

Question Answering (QA) over Knowledge Base (KB) aims to automatically answer natural language questions via well-structured relation information between entities stored in knowledge bases. In order to make KBQA more applicable in actual…

The study of unsupervised learning can be generally divided into two categories: imitation learning and reinforcement learning. In imitation learning the machine learns by mimicking the behavior of an expert system whereas in reinforcement…

Automatically extracting effective queries is challenging in information retrieval, especially in toxic content exploration, as such content is likely to be disguised. With the recent achievements in generative Large Language Model (LLM),…

Intelligent motion planning is one of the core components in automated vehicles, which has received extensive interests. Traditional motion planning methods suffer from several drawbacks in terms of optimality, efficiency and generalization…

Question-answering (QA) is an important application of Information Retrieval (IR) and language models, and the latest trend is toward pre-trained large neural networks with embedding parameters. Augmenting QA performances with these LLMs…

Over the last twenty years, significant progress has been made in designing and implementing Question Answering (QA) systems. However, addressing complex questions, the answers to which are spread across multiple documents, remains a…