Search Results for author: Lucian Popa

Found 10 papers, 2 papers with code

Learning Structured Representations of Entity Names using ActiveLearning and Weak Supervision

no code implementations EMNLP 2020 Kun Qian, Poornima Chozhiyath Raman, Yunyao Li, Lucian Popa

Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation.

Active Learning

Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming

no code implementations23 Sep 2021 Ayush Maheshwari, KrishnaTeja Killamsetty, Ganesh Ramakrishnan, Rishabh Iyer, Marina Danilevsky, Lucian Popa

These LFs, in turn, have been used to generate a large amount of additional noisy labeled data, in a paradigm that is now commonly referred to as data programming.

Text Classification

LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking

no code implementations ACL 2021 Hang Jiang, Sairam Gurajada, Qiuhao Lu, Sumit Neelam, Lucian Popa, Prithviraj Sen, Yunyao Li, Alexander Gray

Entity linking (EL), the task of disambiguating mentions in text by linking them to entities in a knowledge graph, is crucial for text understanding, question answering or conversational systems.

Entity Linking Question Answering

Learning Structured Representations of Entity Names using Active Learning and Weak Supervision

1 code implementation EMNLP 2020 Kun Qian, Poornima Chozhiyath Raman, Yunyao Li, Lucian Popa

Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation.

Active Learning

Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context

no code implementations1 May 2020 Xinyi Zheng, Doug Burdick, Lucian Popa, Xu Zhong, Nancy Xin Ru Wang

With GTE-Table, we invent a new penalty based on the natural cell containment constraint of tables to train our table network aided by cell location predictions.

Object Detection Table Detection +1

A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching

no code implementations29 Mar 2020 Venkata Vamsikrishna Meduri, Lucian Popa, Prithviraj Sen, Mohamed Sarwat

Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity.

Active Learning

Low-resource Deep Entity Resolution with Transfer and Active Learning

no code implementations ACL 2019 Jungo Kasai, Kun Qian, Sairam Gurajada, Yunyao Li, Lucian Popa

Recent adaptation of deep learning methods for ER mitigates the need for dataset-specific feature engineering by constructing distributed representations of entity records.

Active Learning Entity Resolution +2

Knowledge Refinement via Rule Selection

no code implementations29 Jan 2019 Phokion G. Kolaitis, Lucian Popa, Kun Qian

In this paper, we carry out a systematic complexity-theoretic investigation of the following rule selection problem: given a set of rules specified by Horn formulas, and a pair of an input database and an output database, find a subset of the rules that minimizes the total error, that is, the number of false positive and false negative errors arising from the selected rules.

Entity Resolution

Jellyfish: Networking Data Centers Randomly

no code implementations8 Oct 2011 Ankit Singla, Chi-Yao Hong, Lucian Popa, P. Brighten Godfrey

We present Jellyfish, a high-capacity network interconnect, which, by adopting a random graph topology, yields itself naturally to incremental expansion.

Networking and Internet Architecture

Cannot find the paper you are looking for? You can Submit a new open access paper.