Publications (20)
AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry
Yannis Katsis, Saneem Chemmengath, Vishwajeet Kumar +8
Recent advances in transformers have enabled Table Question Answering (Table QA) systems to achieve high accuracy and SOTA results on open domain datasets like WikiTableQuestions a…
Retrieval-Based Transformer for Table Augmentation
Michael Glass, Xueqing Wu, Ankita Rajaram Naik +2
Data preparation, also called data wrangling, is considered one of the most expensive and time-consuming steps when performing analytics or building machine learning models. Prepar…
SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models
Debarun Bhattacharjya, Balaji Ganesan, Junkyu Lee +4
When does a large language model (LLM) know what it does not know? Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the confidence in an LLM…
Rationalization Models for Text-to-SQL
Gaetano Rossiello, Nhan Pham, Michael Glass +2
We introduce a framework for generating Chain-of-Thought (CoT) rationales to enhance text-to-SQL model fine-tuning. These rationales consist of intermediate SQL statements and expl…
Extractive Schema Linking for Text-to-SQL
Michael Glass, Mustafa Eyceoz, Dharmashankar Subramanian +3
Text-to-SQL is emerging as a practical interface for real world databases. The dominant paradigm for Text-to-SQL is cross-database or schema-independent, supporting application sch…
Multi-Objective Design Space Exploration for the Optimization of the HEVC Mode Decision Process
Christian Herglotz, Rafael Rosales, Michael Glass +2
Finding the best possible encoding decisions for compressing a video sequence is a highly complex problem. In this work, we propose a multi-objective Design Space Exploration (DSE)…
Scalable Hierarchical Clustering with Tree Grafting
Nicholas Monath, Ari Kobren, Akshay Krishnamurthy +2
We introduce Grinch, a new algorithm for large-scale, non-greedy hierarchical clustering with general linkage functions that compute arbitrary similarity between two point sets. Th…
Zero-shot Slot Filling with DPR and RAG
Michael Glass, Gaetano Rossiello, Alfio Gliozzo
The ability to automatically extract Knowledge Graphs (KG) from a given collection of documents is a long-standing problem in Artificial Intelligence. One way to assess this capabi…
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…
Robust Retrieval Augmented Generation for Zero-shot Slot Filling
Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury +1
Automatically inducing high quality knowledge graphs from a given collection of documents still remains a challenging problem in AI. One way to make headway for this problem is thr…
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…
The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
Quan Xiao, Debarun Bhattacharjya, Balaji Ganesan +5
Estimating the confidence of large language model (LLM) outputs is essential for real-world applications requiring high user trust. Black-box uncertainty quantification (UQ) method…
Open Government Data Corpus for Table Search
Michael Glass, Sugato Bagchi, Oktie Hassanzadeh +2
Increasing amounts of structured data can provide value for research and business if the relevant data can be located. Often the data is in a data lake without a consistent schema,…
Capturing Row and Column Semantics in Transformer Based Question Answering over Tables
Michael Glass, Mustafa Canim, Alfio Gliozzo +7
Transformer based architectures are recently used for the task of answering questions over tables. In order to improve the accuracy on this task, specialized pre-training technique…
End-to-End Table Question Answering via Retrieval-Augmented Generation
Feifei Pan, Mustafa Canim, Michael Glass +2
Most existing end-to-end Table Question Answering (Table QA) models consist of a two-stage framework with a retriever to select relevant table candidates from a corpus and a reader…
KGI: An Integrated Framework for Knowledge Intensive Language Tasks
Md Faisal Mahbub Chowdhury, Michael Glass, Gaetano Rossiello +2
In this paper, we present a system to showcase the capabilities of the latest state-of-the-art retrieval augmented generation models trained on knowledge-intensive language tasks,…
Applying a Generic Sequence-to-Sequence Model for Simple and Effective Keyphrase Generation
Md Faisal Mahbub Chowdhury, Gaetano Rossiello, Michael Glass +2
In recent years, a number of keyphrase generation (KPG) approaches were proposed consisting of complex model architectures, dedicated training paradigms and decoding strategies. In…
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…
CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering
Feifei Pan, Mustafa Canim, Michael Glass +2
We present the first end-to-end, transformer-based table question answering (QA) system that takes natural language questions and massive table corpus as inputs to retrieve the mos…
Re2G: Retrieve, Rerank, Generate
Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury +3
As demonstrated by GPT-3 and T5, transformers grow in capability as parameter spaces become larger and larger. However, for tasks that require a large amount of knowledge, non-para…