no code implementations • NAACL (DaSH) 2021 • Natraj Raman, Sameena Shah, Tucker Balch, Manuela Veloso
Information visualization is critical to analytical reasoning and knowledge discovery.
no code implementations • SMM4H (COLING) 2022 • Alec Louis Candidato, Akshat Gupta, Xiaomo Liu, Sameena Shah
This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English).
no code implementations • SMM4H (COLING) 2022 • Leung Wai Liu, Akshat Gupta, Saheed Obitayo, Xiaomo Liu, Sameena Shah
This paper presents my submission for Tasks 1 and 2 for the Social Media Mining of Health (SMM4H) 2022 Shared Tasks competition.
no code implementations • SMM4H (COLING) 2022 • Adrian Garcia Hernandez, Leung Wai Liu, Akshat Gupta, Vineeth Ravi, Saheed O. Obitayo, Xiaomo Liu, Sameena Shah
We present our response to Task 5 of the Social Media Mining for Health Applications (SMM4H) 2022 competition.
no code implementations • 5 Apr 2024 • Ran Zmigrod, Dongsheng Wang, Mathieu Sibue, Yulong Pei, Petr Babkin, Ivan Brugere, Xiaomo Liu, Nacho Navarro, Antony Papadimitriou, William Watson, Zhiqiang Ma, Armineh Nourbakhsh, Sameena Shah
Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key entity extraction (KEE), entity linking, visual question answering (VQA), inter alia.
no code implementations • 26 Mar 2024 • Toyin Aguda, Suchetha Siddagangappa, Elena Kochkina, Simerjot Kaur, Dongsheng Wang, Charese Smiley, Sameena Shah
Collecting labeled datasets in finance is challenging due to scarcity of domain experts and higher cost of employing them.
no code implementations • 13 Mar 2024 • Rares Dolga, Ran Zmigrod, Rui Silva, Salwa Alamir, Sameena Shah
Log analysis and monitoring are essential aspects in software maintenance and identifying defects.
no code implementations • 7 Feb 2024 • Ran Zmigrod, Zhiqiang Ma, Armineh Nourbakhsh, Sameena Shah
Visually Rich Form Understanding (VRFU) poses a complex research problem due to the documents' highly structured nature and yet highly variable style and content.
no code implementations • 5 Jan 2024 • Dongsheng Wang, Zhiqiang Ma, Armineh Nourbakhsh, Kang Gu, Sameena Shah
Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts.
no code implementations • 12 Oct 2023 • Ethan Callanan, Amarachi Mbakwe, Antony Papadimitriou, Yulong Pei, Mathieu Sibue, Xiaodan Zhu, Zhiqiang Ma, Xiaomo Liu, Sameena Shah
Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models.
no code implementations • 6 Sep 2023 • Natraj Raman, Sameena Shah
Generating synthetic variants of a document is often posed as text-to-text transformation.
no code implementations • 14 Jul 2023 • Akshat Gupta, Xiaomo Liu, Sameena Shah
A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain.
1 code implementation • 29 May 2023 • Yi Wu, Nan Jiang, Hung Viet Pham, Thibaud Lutellier, Jordan Davis, Lin Tan, Petr Babkin, Sameena Shah
The results call for innovations to enhance automated Java vulnerability repair such as creating larger vulnerability repair training data, tuning LLMs with such data, and applying code simplification transformation to facilitate vulnerability repair.
1 code implementation • 22 May 2023 • Simerjot Kaur, Charese Smiley, Akshat Gupta, Joy Sain, Dongsheng Wang, Suchetha Siddagangappa, Toyin Aguda, Sameena Shah
A number of datasets for Relation Extraction (RE) have been created to aide downstream tasks such as information retrieval, semantic search, question answering and textual entailment.
no code implementations • 22 May 2023 • Simerjot Kaur, Andrea Stefanucci, Sameena Shah
However, unavailability of labeled datasets as well as the need for high precision results within the financial domain makes this a challenging problem.
no code implementations • 10 May 2023 • Xianzhi Li, Samuel Chan, Xiaodan Zhu, Yulong Pei, Zhiqiang Ma, Xiaomo Liu, Sameena Shah
The most recent large language models(LLMs) such as ChatGPT and GPT-4 have shown exceptional capabilities of generalist models, achieving state-of-the-art performance on a wide range of NLP tasks with little or no adaptation.
Ranked #1 on Question Answering on ConvFinQA
no code implementations • 21 Jan 2023 • Natraj Raman, Daniele Magazzeni, Sameena Shah
Counterfactual explanations utilize feature perturbations to analyze the outcome of an original decision and recommend an actionable recourse.
no code implementations • 23 Dec 2022 • Petr Babkin, Nacho Navarro, Salwa Alamir, Sameena Shah
This paper tackles the challenging problem of automating code updates to fix deprecated API usages of open source libraries by analyzing their release notes.
1 code implementation • 7 Oct 2022 • Zhiyu Chen, Shiyang Li, Charese Smiley, Zhiqiang Ma, Sameena Shah, William Yang Wang
With the recent advance in large pre-trained language models, researchers have achieved record performances in NLP tasks that mostly focus on language pattern matching.
Ranked #2 on Question Answering on ConvFinQA
no code implementations • 22 Sep 2022 • Alec Candidato, Akshat Gupta, Xiaomo Liu, Sameena Shah
This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English).
no code implementations • 16 Aug 2022 • Mohsen Ghassemi, Niccolò Dalmasso, Simran Lamba, Vamsi K. Potluru, Sameena Shah, Tucker Balch, Manuela Veloso
Online learning of Hawkes processes has received increasing attention in the last couple of years especially for modeling a network of actors.
no code implementations • 8 Feb 2022 • Cenk Baykal, Vamsi K. Potluru, Sameena Shah, Manuela M. Veloso
Most of the existing work focuses primarily on the monoplex setting where we have access to a network with only a single type of connection between entities.
no code implementations • 11 Jan 2022 • Natraj Raman, Sameena Shah, Manuela Veloso
Retrieving relevant documents from a corpus is typically based on the semantic similarity between the document content and query text.
no code implementations • NeurIPS 2021 • Shangshu Qian, Hung Pham, Thibaud Lutellier, Zeou Hu, Jungwon Kim, Lin Tan, YaoLiang Yu, Jiahao Chen, Sameena Shah
Our study of 22 mitigation techniques and five baselines reveals up to 12. 6% fairness variance across identical training runs with identical seeds.
no code implementations • 11 Nov 2021 • Natraj Raman, Sameena Shah, Manuela Veloso
Analyzing the layout of a document to identify headers, sections, tables, figures etc.
no code implementations • 27 Oct 2021 • Simerjot Kaur, Ivan Brugere, Andrea Stefanucci, Armineh Nourbakhsh, Sameena Shah, Manuela Veloso
We compare the performance of our system with human generated recommendations and demonstrate the ability of our algorithm to perform extremely well on this task.
no code implementations • 19 Sep 2021 • Mahmoud Mahfouz, Armineh Nourbakhsh, Sameena Shah
Organizations around the world face an array of risks impacting their operations globally.
1 code implementation • EMNLP 2021 • Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan Routledge, William Yang Wang
In contrast to existing tasks on general domain, the finance domain includes complex numerical reasoning and understanding of heterogeneous representations.
Ranked #4 on Question Answering on FinQA
no code implementations • 4 Nov 2020 • Ashrya Agrawal, Florian Pfisterer, Bernd Bischl, Francois Buet-Golfouse, Srijan Sood, Jiahao Chen, Sameena Shah, Sebastian Vollmer
We present an empirical study of debiasing methods for classifiers, showing that debiasers often fail in practice to generalize out-of-sample, and can in fact make fairness worse rather than better.
no code implementations • 3 Nov 2020 • Daniel Borrajo, Manuela Veloso, Sameena Shah
One of the key characteristics of these applications is the wide range of strategies that an adversary may choose as they adapt their strategy dynamically to sustain benefits and evade authorities.
no code implementations • 23 Oct 2020 • Natraj Raman, Armineh Nourbakhsh, Sameena Shah, Manuela Veloso
Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems.
no code implementations • 9 Dec 2019 • Riyasat Ohib, Nicolas Gillis, Niccolò Dalmasso, Sameena Shah, Vamsi K. Potluru, Sergey Plis
Instead, in our approach we set the sparsity level for the whole set explicitly and simultaneously project a group of vectors with the sparsity level of each vector tuned automatically.
no code implementations • 11 Nov 2017 • Xiaomo Liu, Armineh Nourbakhsh, Quanzhi Li, Sameena Shah, Robert Martin, John Duprey
It has a bottom-up approach to news detection, and does not rely on a predefined set of sources or subjects.
Social and Information Networks
no code implementations • 14 Aug 2017 • Quanzhi Li, Sameena Shah, Xiaomo Liu, Armineh Nourbakhsh
In addition to the data sets learned from just tweet data, we also built embedding sets from the general data and the combination of tweets with the general data.
no code implementations • SEMEVAL 2017 • Quanzhi Li, Sameena Shah, Armineh Nourbakhsh, Rui Fang, Xiaomo Liu
This paper describes the approach we used for SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs.
no code implementations • CONLL 2017 • Quanzhi Li, Sameena Shah
Previous studies have shown that investor sentiment indicators can predict stock market change.
no code implementations • SEMEVAL 2017 • Quanzhi Li, Armineh Nourbakhsh, Xiaomo Liu, Rui Fang, Sameena Shah
This paper describes the approach we used for SemEval-2017 Task 4: Sentiment Analysis in Twitter.