arXiv subjects

AnHai Doan

Publications and source records attributed to AnHai Doan.

12 recordsLinked to original sources

arXiv2026

Polaris: Learning to Generate Table Descriptions from Retrieval Feedback

Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections using keyword search. Recent work uses LLMs to generate natural-language table descriptions to improve retrieval, but they are typically optimized for fluency rather than retrieval effectiveness. We present Polaris, a system that trains an LLM to generate table descriptions directly from retrieval feedback. Our key insight is that existing table retrieval benchmarks already contain the supervision needed for this task: given query-table relevance judgments, we generate multiple candidate descriptions for each table, rank them by their BM25 retrieval effectiveness, and use the resulting preference pairs to fine-tune the LLM with Direct Preference Optimization (DPO). Polaris further expands abbreviated table and column names before generation to reduce vocabulary mismatch. Extensive experiments show that Polaris outperforms the state-of-the-art AutoDDG solution, often by a significant margin. More broadly, our results demonstrate that retrieval benchmarks can be repurposed as supervision for training LLMs to generate retrieval-oriented metadata.

cs.CL↗

arXiv2025

Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models

Expanding the abbreviated column names of tables, such as "esal" to "employee salary", is critical for many downstream NLP tasks for tabular data, such as NL2SQL, table QA, and keyword search. This problem arises in enterprises, domain sciences, government agencies, and more. In this paper, we make three contributions that significantly advance the state of the art. First, we show that the synthetic public data used by prior work has major limitations, and we introduce four new datasets in enterprise/science domains, with real-world abbreviations. Second, we show that accuracy measures used by prior work seriously undercount correct expansions, and we propose new synonym-aware measures that capture accuracy much more accurately. Finally, we develop Columbo, a powerful LLM-based solution that exploits context, rules, chain-of-thought reasoning, and token-level analysis. Extensive experiments show that Columbo significantly outperforms NameGuess, the current most advanced solution, by 4-29%, over five datasets. Columbo has been used in production on EDI, a major data lake for environmental sciences.

cs.CL↗

arXiv2021

Toward Data Cleaning with a Target Accuracy: A Case Study for Value Normalization

Many applications need to clean data with a target accuracy. As far as we know, this problem has not been studied in depth. In this paper we take the first step toward solving it. We focus on value normalization (VN), the problem of replacing all string that refer to the same entity with a unique string. VN is ubiquitous, and we often want to do VN with 100% accuracy. This is typically done today in industry by automatically clustering the strings then asking a user to verify and clean the clusters, until reaching 100% accuracy. This solution has significant limitations. It does not tell the users how to verify and clean the clusters. This part also often takes a lot of time, e.g., days. Further, there is no effective way for multiple users to collaboratively verify and clean. In this paper we address these challenges. Overall, our work advances the state of the art in data cleaning by introducing a novel cleaning problem and describing a promising solution template.

cs.DB↗

arXiv2020

Deep Entity Matching with Pre-Trained Language Models

We present Ditto, a novel entity matching system based on pre-trained Transformer-based language models. We fine-tune and cast EM as a sequence-pair classification problem to leverage such models with a simple architecture. Our experiments show that a straightforward application of language models such as BERT, DistilBERT, or RoBERTa pre-trained on large text corpora already significantly improves the matching quality and outperforms previous state-of-the-art (SOTA), by up to 29% of F1 score on benchmark datasets. We also developed three optimization techniques to further improve Ditto's matching capability. Ditto allows domain knowledge to be injected by highlighting important pieces of input information that may be of interest when making matching decisions. Ditto also summarizes strings that are too long so that only the essential information is retained and used for EM. Finally, Ditto adapts a SOTA technique on data augmentation for text to EM to augment the training data with (difficult) examples. This way, Ditto is forced to learn "harder" to improve the model's matching capability. The optimizations we developed further boost the performance of Ditto by up to 9.8%. Perhaps more surprisingly, we establish that Ditto can achieve the previous SOTA results with at most half the number of labeled data. Finally, we demonstrate Ditto's effectiveness on a real-world large-scale EM task. On matching two company datasets consisting of 789K and 412K records, Ditto achieves a high F1 score of 96.5%.

cs.DB↗

arXiv2019

Data Curation with Deep Learning [Vision]

Data curation - the process of discovering, integrating, and cleaning data - is one of the oldest, hardest, yet inevitable data management problems. Despite decades of efforts from both researchers and practitioners, it is still one of the most time consuming and least enjoyable work of data scientists. In most organizations, data curation plays an important role so as to fully unlock the value of big data. Unfortunately, the current solutions are not keeping up with the ever-changing data ecosystem, because they often require substantially high human cost. Meanwhile, deep learning is making strides in achieving remarkable successes in multiple areas, such as image recognition, natural language processing, and speech recognition. In this vision paper, we explore how some of the fundamental innovations in deep learning could be leveraged to improve existing data curation solutions and to help build new ones. In particular, we provide a thorough overview of the current deep learning landscape, and identify interesting research opportunities and dispel common myths. We hope that the synthesis of these important domains will unleash a series of research activities that will lead to significantly improved solutions for many data curation tasks.

cs.DB↗

arXiv2017

Toward a System Building Agenda for Data Integration

In this paper we argue that the data management community should devote far more effort to building data integration (DI) systems, in order to truly advance the field. Toward this goal, we make three contributions. First, we draw on our recent industrial experience to discuss the limitations of current DI systems. Second, we propose an agenda to build a new kind of DI systems to address these limitations. These systems guide users through the DI workflow, step by step. They provide tools to address the "pain points" of the steps, and tools are built on top of the Python data science and Big Data ecosystem (PyData). We discuss how to foster an ecosystem of such tools within PyData, then use it to build DI systems for collaborative/cloud/crowd/lay user settings. Finally, we discuss ongoing work at Wisconsin, which suggests that these DI systems are highly promising and building them raises many interesting research challenges.

cs.DB↗

arXiv2013

Abstracting Probabilistic Actions

This paper discusses the problem of abstracting conditional probabilistic actions. We identify two distinct types of abstraction: intra-action abstraction and inter-action abstraction. We define what it means for the abstraction of an action to be correct and then derive two methods of intra-action abstraction and two methods of inter-action abstraction which are correct according to this criterion. We illustrate the developed techniques by applying them to actions described with the temporal action representation used in the DRIPS decision-theoretic planner and we describe how the planner uses abstraction to reduce the complexity of planning.

cs.AI↗

arXiv2013

Efficient Decision-Theoretic Planning: Techniques and Empirical Analysis

This paper discusses techniques for performing efficient decision-theoretic planning. We give an overview of the DRIPS decision-theoretic refinement planning system, which uses abstraction to efficiently identify optimal plans. We present techniques for automatically generating search control information, which can significantly improve the planner's performance. We evaluate the efficiency of DRIPS both with and without the search control rules on a complex medical planning problem and compare its performance to that of a branch-and-bound decision tree algorithm.

cs.AI↗

arXiv2013

Sound Abstraction of Probabilistic Actions in The Constraint Mass Assignment Framework

This paper provides a formal and practical framework for sound abstraction of probabilistic actions. We start by precisely defining the concept of sound abstraction within the context of finite-horizon planning (where each plan is a finite sequence of actions). Next we show that such abstraction cannot be performed within the traditional probabilistic action representation, which models a world with a single probability distribution over the state space. We then present the constraint mass assignment representation, which models the world with a set of probability distributions and is a generalization of mass assignment representations. Within this framework, we present sound abstraction procedures for three types of action abstraction. We end the paper with discussions and related work on sound and approximate abstraction. We give pointers to papers in which we discuss other sound abstraction-related issues, including applications, estimating loss due to abstraction, and automatically generating abstraction hierarchies.

cs.AI↗

arXiv2012

Muppet: MapReduce-Style Processing of Fast Data

MapReduce has emerged as a popular method to process big data. In the past few years, however, not just big data, but fast data has also exploded in volume and availability. Examples of such data include sensor data streams, the Twitter Firehose, and Facebook updates. Numerous applications must process fast data. Can we provide a MapReduce-style framework so that developers can quickly write such applications and execute them over a cluster of machines, to achieve low latency and high scalability? In this paper we report on our investigation of this question, as carried out at Kosmix and WalmartLabs. We describe MapUpdate, a framework like MapReduce, but specifically developed for fast data. We describe Muppet, our implementation of MapUpdate. Throughout the description we highlight the key challenges, argue why MapReduce is not well suited to address them, and briefly describe our current solutions. Finally, we describe our experience and lessons learned with Muppet, which has been used extensively at Kosmix and WalmartLabs to power a broad range of applications in social media and e-commerce.

cs.DB↗

arXiv2011

Tuffy: Scaling up Statistical Inference in Markov Logic Networks using an RDBMS

Markov Logic Networks (MLNs) have emerged as a powerful framework that combines statistical and logical reasoning; they have been applied to many data intensive problems including information extraction, entity resolution, and text mining. Current implementations of MLNs do not scale to large real-world data sets, which is preventing their wide-spread adoption. We present Tuffy that achieves scalability via three novel contributions: (1) a bottom-up approach to grounding that allows us to leverage the full power of the relational optimizer, (2) a novel hybrid architecture that allows us to perform AI-style local search efficiently using an RDBMS, and (3) a theoretical insight that shows when one can (exponentially) improve the efficiency of stochastic local search. We leverage (3) to build novel partitioning, loading, and parallel algorithms. We show that our approach outperforms state-of-the-art implementations in both quality and speed on several publicly available datasets.

cs.DB↗

arXiv2009

The Case for a Structured Approach to Managing Unstructured Data

The challenge of managing unstructured data represents perhaps the largest data management opportunity for our community since managing relational data. And yet we are risking letting this opportunity go by, ceding the playing field to other players, ranging from communities such as AI, KDD, IR, Web, and Semantic Web, to industrial players such as Google, Yahoo, and Microsoft. In this essay we explore what we can do to improve upon this situation. Drawing on the lessons learned while managing relational data, we outline a structured approach to managing unstructured data. We conclude by discussing the potential implications of this approach to managing other kinds of non-relational data, and to the identify of our field.

cs.DB↗