papers

Publications (23)

eess.IV2021

Coarse-to-fine Airway Segmentation Using Multi information Fusion Network and CNN-based Region Growing

Jinquan Guo, Rongda Fu, Lin Pan +4

Automatic airway segmentation from chest computed tomography (CT) scans plays an important role in pulmonary disease diagnosis and computer-assisted therapy. However, low contrast…

cs.CL2019

Ensembling Strategies for Answering Natural Questions

Anthony Ferritto, Lin Pan, Rishav Chakravarti +4

Many of the top question answering systems today utilize ensembling to improve their performance on tasks such as the Stanford Question Answering Dataset (SQuAD) and Natural Questi…

cs.CL2020

CFO: A Framework for Building Production NLP Systems

Rishav Chakravarti, Cezar Pendus, Andrzej Sakrajda +8

This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language…

cs.CL2019

Frustratingly Easy Natural Question Answering

Lin Pan, Rishav Chakravarti, Anthony Ferritto +5

Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa. A…

cond-mat.mes-hall2018

Coexisting surface states in the weak and crystalline topological insulator Bi_2TeI

Nurit Avraham, Andrew Norris, Yan Sun +7

The established diversity of electronic topology classes lends the opportunity to pair them into dual topological complexes. Bulk-surface correspondence then ensures the coexistenc…

eess.SY2022

Composite learning control with application to inverted pendulums

Yongping Pan, Lin Pan, Haoyong Yu

Composite adaptive control (CAC) that integrates direct and indirect adaptive control techniques can achieve smaller tracking errors and faster parameter convergence compared with…

cs.CL2024

Towards a Holistic Evaluation of LLMs on Factual Knowledge Recall

Jiaqing Yuan, Lin Pan, Chung-Wei Hang +5

Large language models (LLMs) have shown remarkable performance on a variety of NLP tasks, and are being rapidly adopted in a wide range of use cases. It is therefore of vital impor…

cs.CL2023

Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness

Shuaichen Chang, Jun Wang, Mingwen Dong +13

Neural text-to-SQL models have achieved remarkable performance in translating natural language questions into SQL queries. However, recent studies reveal that text-to-SQL models ar…

cs.CL2022

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing

Yiyun Zhao, Jiarong Jiang, Yiqun Hu +14

Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and di…

cs.CL2026

PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries

Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu +9

Previous text-to-SQL datasets and systems have primarily focused on user questions with clear intentions that can be answered. However, real user questions can often be ambiguous w…

cs.CL2020

Span Selection Pre-training for Question Answering

Michael Glass, Alfio Gliozzo, Rishav Chakravarti +5

BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a…

cs.CL2022

Improved Text Classification via Contrastive Adversarial Training

Lin Pan, Chung-Wei Hang, Avirup Sil +1

We propose a simple and general method to regularize the fine-tuning of Transformer-based encoders for text classification tasks. Specifically, during fine-tuning we generate adver…

cs.CL2020

Multilingual Transfer Learning for QA Using Translation as Data Augmentation

Mihaela Bornea, Lin Pan, Sara Rosenthal +2

Prior work on multilingual question answering has mostly focused on using large multilingual pre-trained language models (LM) to perform zero-shot language-wise learning: train a Q…

eess.IV2021

Automatic Pulmonary Artery-Vein Separation in CT Images using Twin-Pipe Network and Topology Reconstruction

Lin Pan, Yaoyong Zheng, Liqin Huang +5

With the development of medical computer-aided diagnostic systems, pulmonary artery-vein(A/V) separation plays a crucial role in assisting doctors in preoperative planning for lung…

cs.CL2019

Multi-Granular Text Encoding for Self-Explaining Categorization

Zhiguo Wang, Yue Zhang, Mo Yu +5

Self-explaining text categorization requires a classifier to make a prediction along with supporting evidence. A popular type of evidence is sub-sequences extracted from the input…

cs.CL2021

Multilingual BERT Post-Pretraining Alignment

Lin Pan, Chung-Wei Hang, Haode Qi +3

We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Usi…

cs.CL2019

The TechQA Dataset

Vittorio Castelli, Rishav Chakravarti, Saswati Dana +18

We introduce TechQA, a domain-adaptation question answering dataset for the technical support domain. The TechQA corpus highlights two real-world issues from the automated customer…

cond-mat.mtrl-sci2016

The role of ionized impurity scattering on the thermoelectric performances of rock salt AgPbmSnSe2+m

Lin Pan, Sunanda Mitra, Li-Dong Zhao +4

We report on the successful synthesis and on the properties of polycrystalline AgPbmSnSe2+m (m = ++++, 100, 50, 25) samples with a rock salt structure. Between 160 K and 400 K, the…

cond-mat.mes-hall2006

Geometric, electronic properties and the thermodynamics of pure and Al--doped Li clusters

Mal--Soon Lee, S. Gowtham, Haiying He +3

The first--principles density functional molecular dynamics simulations have been carried out to investigate the geometric, the electronic, and the finite temperature properties of…

eess.IV2023

Curvilinear object segmentation in medical images based on ODoS filter and deep learning network

Yuanyuan Peng, Lin Pan, Pengpeng Luan +2

Automatic segmentation of curvilinear objects in medical images plays an important role in the diagnosis and evaluation of human diseases, yet it is a challenging uncertainty in th…

cs.CL2023

UNITE: A Unified Benchmark for Text-to-SQL Evaluation

Wuwei Lan, Zhiguo Wang, Anuj Chauhan +15

A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures. To comprehensively e…

cs.CL2021

Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations

Haode Qi, Lin Pan, Atin Sood +4

Intent detection is a key component of modern goal-oriented dialog systems that accomplish a user task by predicting the intent of users' text input. There are three primary challe…

eess.IV2021

Interpretative Computer-aided Lung Cancer Diagnosis: from Radiology Analysis to Malignancy Evaluation

Shaohua Zheng, Zhiqiang Shen, Chenhao Peia +6

Background and Objective:Computer-aided diagnosis (CAD) systems promote diagnosis effectiveness and alleviate pressure of radiologists. A CAD system for lung cancer diagnosis inclu…