Publications (23)
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…