Papers by Michael Glass

Copied to clipboard

Debarun Bhattacharjya, Balaji Ganesan, Junkyu Lee, Radu Marinescu, Katya Mirylenka, Michael Glass, Xiao Shou

Challenge:	Uncertainty quantification (UQ) provides measures of uncertainty, such as an estimate of the confidence in an LLM’s generated output.
Approach:	They propose a black-box approach where consistency is used as a proxy for confidence in a model's output.
Outcome:	The proposed methods are primarily but not necessarily entirely black- box, with consistency between output and other sampled generations used as a proxy for confidence in its correctness.

AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry (2022.naacl-industry)

Copied to clipboard

Yannis Katsis, Saneem Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Mustafa Canim, Michael Glass, Alfio Gliozzo, Feifei Pan, Jaydeep Sen, Karthik Sankaranarayanan, Soumen Chakrabarti

Structured Data in NLP

Challenge:	Table Question Answering (Table QA) systems have been shown to be highly accurate when trained and tested on open-domain datasets built on top of Wikipedia tables.
Approach:	They propose a domain-specific Table QA test dataset to test Table Question Answering systems on open-domain datasets built on top of Wikipedia tables.
Outcome:	The proposed methods are highly accurate when tested on open-domain datasets built on top of Wikipedia tables.

CFO: A Framework for Building Production NLP Systems (D19-3)

Copied to clipboard

Rishav Chakravarti, Cezar Pendus, Andrzej Sakrajda, Anthony Ferritto, Lin Pan, Michael Glass, Vittorio Castelli, J. William Murdock, Radu Florian, Salim Roukos, Avi Sil

Multimodality

Challenge:	Using a new orchestration framework, we build, test, and deploy interactive NLP and IR systems to production environments.
Approach:	They introduce a new orchestration framework for building, experimenting with, and deploying interactive NLP and IR systems to production environments.
Outcome:	The proposed framework is well suited to a variety of use cases but is not suitable for academic benchmarking or industry specific use cases.

Learning Relational Representations by Analogy using Hierarchical Siamese Networks (N19-1)

Copied to clipboard

Gaetano Rossiello, Alfio Gliozzo, Robert Farrell, Nicolas Fauceglia, Michael Glass

Semantic Text Processing

Challenge:	Existing approaches to learn representations of relations by textual mentions require a large amount of examples for each relation to reach satisfactory performance.
Approach:	They propose a method to learn representations of relations expressed by their textual mentions by matching triples in knowledge bases with web-scale corpora through distant supervision.
Outcome:	The proposed approach outperforms the state-of-the-art methods on a relation extraction task.

Discovering Implicit Knowledge with Unary Relations (P18-1)

Copied to clipboard

Michael Glass, Alfio Gliozzo

Knowledge Representation

Challenge:	State-of-the-art relation extraction methods only recognize relationships between mentions of entity arguments stated explicitly in the text.
Approach:	They propose a method to identify relations between two entities using unary relations and a common deep learning based representation.
Outcome:	The proposed method outperforms state-of-the-art relation extraction technology on a web scale knowledge base population benchmark.

KGI: An Integrated Framework for Knowledge Intensive Language Tasks (2022.emnlp-demos)

Copied to clipboard

Md Faisal Mahbub Chowdhury, Michael Glass, Gaetano Rossiello, Alfio Gliozzo, Nandana Mihindukulasooriya

Natural Language Interfaces

Challenge:	Existing state-of-the-art retrieval augmented generation models are not available for knowledge-intensive language tasks.
Approach:	They propose a retrieval augmented generation system that showcases the latest state-of-the-art retrieval models on knowledge-intensive language tasks.
Outcome:	The proposed system is based on the core of the KGI system.

Span Selection Pre-training for Question Answering (2020.acl-main)

Copied to clipboard

Michael Glass, Alfio Gliozzo, Rishav Chakravarti, Anthony Ferritto, Lin Pan, G P Shrivatsa Bhargav, Dinesh Garg, Avi Sil

Natural Language Interfaces

Challenge:	Pre-trained BERTs provide large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA).
Approach:	They propose a new pre-training task inspired by reading comprehension to better align the pre- training from memorization to understanding.
Outcome:	The proposed model outperforms BERT-BASE and BERT LARGE on a new dataset and improves answer prediction F1 by 4 points and supporting fact prediction F1.

CLTR: An End-to-End, Transformer-Based System for Cell-Level Table Retrieval and Table Question Answering (2021.acl-demo)

Copied to clipboard

Feifei Pan, Mustafa Canim, Michael Glass, Alfio Gliozzo, Peter Fox

Natural Language Interfaces

Challenge:	Existing systems that retrieve tables based on keyword queries and table contents often result in poor quality . a growing demand for natural language questions over tables to be used for QA .
Approach:	They propose an end-to-end transformer-based table question answering system that takes natural language questions and massive table corpora as inputs to retrieve the most relevant tables.
Outcome:	The proposed system can retrieve relevant tables and locate the correct cells to answer questions.

Re2G: Retrieve, Rerank, Generate (2022.naacl-main)

Copied to clipboard

Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, Alfio Gliozzo

Information Retrieval

Challenge:	Recent models such as RAG and REALM incorporate retrieval into conditional generation.
Approach:	They propose a method that combines retrieval and reranking into a BART-based sequence-to-sequence generation.
Outcome:	The proposed model combines retrieval and reranking into a BART-based sequence-to-sequence generation.

Retrieval-Based Transformer for Table Augmentation (2023.findings-acl)

Copied to clipboard

Michael Glass, Xueqing Wu, Ankita Rajaram Naik, Gaetano Rossiello, Alfio Gliozzo

Multimodality

Challenge:	Data preparation is one of the most expensive and time-consuming steps when performing analytics or building machine learning models.
Approach:	They propose a retrieval augmented transformer model that is self-trained for table augmentation tasks.
Outcome:	The proposed model outperforms current state-of-the-art models on EntiTables and WebTables.

Robust Retrieval Augmented Generation for Zero-shot Slot Filling (2021.emnlp-main)

Copied to clipboard

Michael Glass, Gaetano Rossiello, Md Faisal Mahbub Chowdhury, Alfio Gliozzo

Responsible & Trustworthy NLP

Challenge:	Automating high quality knowledge graphs from a given collection of documents remains a challenging problem in AI.
Approach:	They propose a novel approach to slot filling that extends dense passage retrieval with hard negatives and robust training procedures for retrieval augmented generation models.
Outcome:	The proposed model improves on both T-REx and zsRE slot filling datasets and ranks at the top-1 position in the KILT leaderboard.

Capturing Row and Column Semantics in Transformer Based Question Answering over Tables (2021.naacl-main)

Copied to clipboard

Michael Glass, Mustafa Canim, Alfio Gliozzo, Saneem Chemmengath, Vishwajeet Kumar, Rishav Chakravarti, Avi Sil, Feifei Pan, Samarth Bharadwaj, Nicolas Rodolfo Fauceglia

Multimodality

Challenge:	Existing transformer based approaches have been used to answer questions over tables.
Approach:	They propose a transformer based architecture that independently classifies rows and columns to identify relevant cells and a model that incorporates existing tables to improve efficiency.
Outcome:	The proposed model outperforms the state-of-the-art transformer based approaches on WikiSQL lookup questions and achieves 3.4% and 18.86% additional precision improvement on the standard WikisQL benchmark.