no code implementations • EMNLP 2020 • Jinyue Feng, Chantal Shaib, Frank Rudzicz
Clinical prediction models often use structured variables and provide outcomes that are not readily interpretable by clinicians.
1 code implementation • LREC 2022 • Xindi Wang, Robert E. Mercer, Frank Rudzicz
Medical Subject Heading (MeSH) indexing refers to the problem of assigning a given biomedical document with the most relevant labels from an extremely large set of MeSH terms.
no code implementations • 16 May 2024 • Raeid Saqur, Ken Kato, Nicholas Vinden, Frank Rudzicz
We introduce and make publicly available the NIFTY Financial News Headlines dataset, designed to facilitate and advance research in financial market forecasting using large language models (LLMs).
no code implementations • 10 May 2024 • Rohan Ajwani, Shashidhar Reddy Javaji, Frank Rudzicz, Zining Zhu
Some LLMs are not able to find alternative paths along simple graphs, indicating that their misleading explanations aren't produced by only logical deductions using complex knowledge.
no code implementations • 8 Apr 2024 • Rohan Deepak Ajwani, Zining Zhu, Jonathan Rose, Frank Rudzicz
Transformer-based Large Language Models (LLMs) have shown exceptional language generation capabilities in response to text-based prompts.
no code implementations • 26 Feb 2024 • Domenic Rosati, Jan Wehner, Kai Williams, Łukasz Bartoszcze, Jan Batzner, Hassan Sajjad, Frank Rudzicz
Approaches to aligning large language models (LLMs) with human values has focused on correcting misalignment that emerges from pretraining.
1 code implementation • 14 Feb 2024 • Domenic Rosati, Robie Gonzales, Jinkun Chen, Xuemin Yu, Melis Erkan, Yahya Kayani, Satya Deepika Chavatapalli, Frank Rudzicz, Hassan Sajjad
Evaluations of model editing currently only use the `next few token' completions after a prompt.
1 code implementation • 17 Oct 2023 • Esmat Sahak, Zining Zhu, Frank Rudzicz
The impressive success of recent deep neural network (DNN)-based systems is significantly influenced by the high-quality datasets used in training.
no code implementations • 6 Oct 2023 • Zining Zhu, Frank Rudzicz
Text-based explanation is a particularly promising approach in explainable AI, but the evaluation of text explanations is method-dependent.
no code implementations • 27 Aug 2023 • Zining Zhu, Haoming Jiang, Jingfeng Yang, Sreyashi Nag, Chao Zhang, Jie Huang, Yifan Gao, Frank Rudzicz, Bing Yin
Situated NLE provides a perspective and facilitates further research on the generation and evaluation of explanations.
no code implementations • 24 Aug 2023 • Shuja Khalid, Frank Rudzicz
By using GNNs to analyze the complex visual data of surgical procedures represented as graph structures, relevant features can be extracted and surgical skill can be predicted.
1 code implementation • 28 Jul 2023 • Xindi Wang, YuFei Wang, Can Xu, Xiubo Geng, BoWen Zhang, Chongyang Tao, Frank Rudzicz, Robert E. Mercer, Daxin Jiang
Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL), where learning a new task from just a few training examples is done without being explicitly pre-trained.
no code implementations • 7 Jul 2023 • Krishnapriya Vishnubhotla, Frank Rudzicz, Graeme Hirst, Adam Hammond
Current models for quotation attribution in literary novels assume varying levels of available information in their training and test data, which poses a challenge for in-the-wild inference.
no code implementations • 4 May 2023 • Faiza Khan Khattak, Vallijah Subasri, Amrit Krishnan, Elham Dolatabadi, Deval Pandya, Laleh Seyyed-Kalantari, Frank Rudzicz
We cover the foundational concepts of general machine learning operations, describe the initial setup of MLHOps pipelines (including data sources, preparation, engineering, and tools).
no code implementations • 15 Mar 2023 • Shuja Khalid, Frank Rudzicz
We demonstrate the effectiveness of our method on a variety of static and dynamic scenes and show that it outperforms traditional SfM and MVS approaches.
1 code implementation • 7 Feb 2023 • Stephen Obadinma, Faiza Khan Khattak, Shirley Wang, Tania Sidhom, Elaine Lau, Sean Robertson, Jingcheng Niu, Winnie Au, Alif Munim, Karthik Raja K. Bhaskar, Bencheng Wei, Iris Ren, Waqar Muhammad, Erin Li, Bukola Ishola, Michael Wang, Griffin Tanner, Yu-Jia Shiah, Sean X. Zhang, Kwesi P. Apponsah, Kanishk Patel, Jaswinder Narain, Deval Pandya, Xiaodan Zhu, Frank Rudzicz, Elham Dolatabadi
Building Agent Assistants that can help improve customer service support requires inputs from industry users and their customers, as well as knowledge about state-of-the-art Natural Language Processing (NLP) technology.
1 code implementation • 13 Oct 2022 • Zining Zhu, Soroosh Shahtalebi, Frank Rudzicz
Large NLP models have recently shown impressive performance in language understanding tasks, typically evaluated by their fine-tuned performance.
no code implementations • COLING (WNUT) 2022 • Malikeh Ehghaghi, Frank Rudzicz, Jekaterina Novikova
In this work, we investigate the ability of clustering approaches in distinguishing between depression and dementia from human speech.
no code implementations • 20 Sep 2022 • Shuja Khalid, Frank Rudzicz
We present a novel neural radiance model that is trainable in a self-supervised manner for novel-view synthesis of dynamic unstructured scenes.
no code implementations • 25 Aug 2022 • Zining Zhu, Soroosh Shahtalebi, Frank Rudzicz
We find that representations always encode some information about the domain.
1 code implementation • NLP4ConvAI (ACL) 2022 • Ian Berlot-Attwell, Frank Rudzicz
Our proposed metric achieves state-of-the-art performance on the HUMOD dataset while reducing measured sensitivity to dataset by 37%-66%.
no code implementations • 6 May 2022 • Aparna Balagopalan, Haoran Zhang, Kimia Hamidieh, Thomas Hartvigsen, Frank Rudzicz, Marzyeh Ghassemi
Across two different blackbox model architectures and four popular explainability methods, we find that the approximation quality of explanation models, also known as the fidelity, differs significantly between subgroups.
no code implementations • LTEDI (ACL) 2022 • Yoon A Park, Frank Rudzicz
Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity.
no code implementations • 28 Apr 2022 • Xindi Wang, Robert E. Mercer, Frank Rudzicz
Medical Subject Heading (MeSH) indexing refers to the problem of assigning a given biomedical document with the most relevant labels from an extremely large set of MeSH terms.
1 code implementation • BioNLP (ACL) 2022 • Hillary Ngai, Frank Rudzicz
We introduce Doctor XAvIer, a BERT-based diagnostic system that extracts relevant clinical data from transcribed patient-doctor dialogues and explains predictions using feature attribution methods.
1 code implementation • ACL 2022 • Xindi Wang, Robert E. Mercer, Frank Rudzicz
Currently, Medical Subject Headings (MeSH) are manually assigned to every biomedical article published and subsequently recorded in the PubMed database to facilitate retrieving relevant information.
1 code implementation • Findings (ACL) 2022 • Zining Zhu, Jixuan Wang, Bai Li, Frank Rudzicz
As large and powerful neural language models are developed, researchers have been increasingly interested in developing diagnostic tools to probe them.
1 code implementation • ACL 2022 • Bai Li, Zining Zhu, Guillaume Thomas, Frank Rudzicz, Yang Xu
Second, in a "Jabberwocky" priming-based experiment, we find that LMs associate ASCs with meaning, even in semantically nonsensical sentences.
no code implementations • 9 Feb 2022 • Yuchen Li, Frank Rudzicz
We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficiency across CIFAR10/100 and SVHN image classification, especially in larger acquisition sizes.
1 code implementation • NeurIPS 2021 • Jixuan Wang, Kuan-Chieh Wang, Frank Rudzicz, Michael Brudno
Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks.
no code implementations • 17 Oct 2021 • Zining Zhu, Aparna Balagopalan, Marzyeh Ghassemi, Frank Rudzicz
This framework allows us to compare across datasets, saying that, apart from a set of ``shortcut features'', classifying each sample in the Multi-NLI task involves around 0. 4 nats more TSI than in the Quora Question Pair.
no code implementations • 13 Oct 2021 • Arvid Frydenlund, Gagandeep Singh, Frank Rudzicz
We also develop a method using $N$-grams to create a non-probabilistic teacher which generates the ranks without the need of a pre-trained LM.
1 code implementation • Findings (EMNLP) 2021 • Aida Ramezani, Zining Zhu, Frank Rudzicz, Yang Xu
Morality plays an important role in social well-being, but people's moral perception is not stable and changes over time.
1 code implementation • 13 Jul 2021 • Zining Zhu, Bai Li, Yang Xu, Frank Rudzicz
As the numbers of submissions to conferences grow quickly, the task of assessing the quality of academic papers automatically, convincingly, and with high accuracy attracts increasing attention.
1 code implementation • ACL 2021 • Bai Li, Zining Zhu, Guillaume Thomas, Yang Xu, Frank Rudzicz
Transformer language models have shown remarkable ability in detecting when a word is anomalous in context, but likelihood scores offer no information about the cause of the anomaly.
1 code implementation • NAACL (CMCL) 2021 • Bai Li, Frank Rudzicz
In this paper, we describe our submission to the CMCL 2021 shared task on predicting human reading patterns.
no code implementations • 13 Apr 2021 • Ian Berlot-Attwell, Frank Rudzicz
Automatically evaluating text-based, non-task-oriented dialogue systems (i. e., `chatbots') remains an open problem.
no code implementations • 9 Mar 2021 • Elsa Riachi, Muhammad Mamdani, Michael Fralick, Frank Rudzicz
Many healthcare decisions involve navigating through a multitude of treatment options in a sequential and iterative manner to find an optimal treatment pathway with the goal of an optimal patient outcome.
no code implementations • 6 Feb 2021 • Jixuan Wang, Xiong Xiao, Jian Wu, Ranjani Ramamurthy, Frank Rudzicz, Michael Brudno
Speaker attribution is required in many real-world applications, such as meeting transcription, where speaker identity is assigned to each utterance according to speaker voice profiles.
1 code implementation • 28 Jan 2021 • Demetres Kostas, Stephane Aroca-Ouellette, Frank Rudzicz
Deep neural networks (DNNs) used for brain-computer-interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such that these features could be fine-tuned to specific contexts.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +6
no code implementations • 1 Jan 2021 • Elsa Riachi, Frank Rudzicz
We show that training an autoencoder on adversarial input-target pairs leads to low reconstruction error on the standard test set, suggesting that adversarial attacks on autoencoders are predictive.
1 code implementation • EMNLP (ClinicalNLP) 2020 • John Chen, Ian Berlot-Attwell, Safwan Hossain, Xindi Wang, Frank Rudzicz
Clinical machine learning is increasingly multimodal, collected in both structured tabular formats and unstructured forms such as freetext.
no code implementations • 1 Nov 2020 • Zining Zhu, Yang Xu, Frank Rudzicz
Semantic shifts can reflect changes in beliefs across hundreds of years, but it is less clear whether trends in fast-changing communities across a short time can be detected.
1 code implementation • EMNLP 2020 • Stephane Aroca-Ouellette, Frank Rudzicz
BERT set many state-of-the-art results over varied NLU benchmarks by pre-training over two tasks: masked language modelling (MLM) and next sentence prediction (NSP), the latter of which has been highly criticized.
no code implementations • EMNLP (BlackboxNLP) 2020 • Zining Zhu, Chuer Pan, Mohamed Abdalla, Frank Rudzicz
In this paper, we propose a method that quantitatively evaluates the rhetorical capacities of neural LMs.
2 code implementations • EMNLP 2020 • Bai Li, Guillaume Thomas, Yang Xu, Frank Rudzicz
Word class flexibility refers to the phenomenon whereby a single word form is used across different grammatical categories.
no code implementations • EMNLP 2020 • Zining Zhu, Frank Rudzicz
Hewitt and Liang (2019) showed that a high performance on diagnostic classification itself is insufficient, because it can be attributed to either "the representation being rich in knowledge", or "the probe learning the task", which Pimentel et al. (2020) challenged.
no code implementations • 28 Jul 2020 • Frank Rudzicz, Raeid Saqur
Here we discuss the four key principles of bio-medical ethics from surgical context.
no code implementations • 26 Jul 2020 • Aparna Balagopalan, Benjamin Eyre, Frank Rudzicz, Jekaterina Novikova
Research related to automatically detecting Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional methods.
no code implementations • 17 Jul 2020 • Arnold YS Yeung, Shalmali Joshi, Joseph Jay Williams, Frank Rudzicz
The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information.
no code implementations • 22 May 2020 • Jixuan Wang, Xiong Xiao, Jian Wu, Ranjani Ramamurthy, Frank Rudzicz, Michael Brudno
Deep speaker embedding models have been commonly used as a building block for speaker diarization systems; however, the speaker embedding model is usually trained according to a global loss defined on the training data, which could be sub-optimal for distinguishing speakers locally in a specific meeting session.
no code implementations • LREC 2020 • Rachid Riad, Anne-Catherine Bachoud-Lévi, Frank Rudzicz, Emmanuel Dupoux
Here, we introduce a new evaluation framework for disfluency detection inspired by the clinical and NLP perspective together with the theory of performance from \cite{clark1996using} which distinguishes between primary and collateral tracks.
no code implementations • WS 2019 • Serena Jeblee, Faiza Khan Khattak, Noah Crampton, Muhammad Mamdani, Frank Rudzicz
We present a system for automatically extracting pertinent medical information from dialogues between clinicians and patients.
no code implementations • WS 2020 • Bai Li, Jing Yi Xie, Frank Rudzicz
Tone is a prosodic feature used to distinguish words in many languages, some of which are endangered and scarcely documented.
no code implementations • WS 2019 • Jekaterina Novikova, Aparna Balagopalan, Ksenia Shkaruta, Frank Rudzicz
Understanding the vulnerability of linguistic features extracted from noisy text is important for both developing better health text classification models and for interpreting vulnerabilities of natural language models.
2 code implementations • 24 Jun 2019 • Yuchen Li, Frank Rudzicz, Jekaterina Novikova
We seek to improve the data efficiency of neural networks and present novel implementations of parameterized piece-wise polynomial activation functions.
no code implementations • NAACL 2019 • Kathleen C. Fraser, Nicklas Linz, Bai Li, Kristina Lundholm Fors, Frank Rudzicz, Alex K{\"o}nig, ra, Alex, Jan ersson, Philippe Robert, Dimitrios Kokkinakis
There is growing evidence that changes in speech and language may be early markers of dementia, but much of the previous NLP work in this area has been limited by the size of the available datasets.
no code implementations • WS 2019 • Faiza Khan Khattak, Chlo{\'e} Pou-Prom, Robert Wu, Frank Rudzicz
We explore the use of real-time clinical information, i. e., text messages sent between nurses and doctors regarding patient conditions in order to predict transfer to the intensive care unit(ICU).
no code implementations • WS 2019 • Kathleen C. Fraser, Frauke Zeller, David Harris Smith, Saif Mohammad, Frank Rudzicz
In 2014, a chatty but immobile robot called hitchBOT set out to hitchhike across Canada.
1 code implementation • WS 2019 • Akshay Budhkar, Krishnapriya Vishnubhotla, Safwan Hossain, Frank Rudzicz
Generative adversarial networks (GANs) have shown considerable success, especially in the realistic generation of images.
no code implementations • NAACL 2019 • Bai Li, Yi-Te Hsu, Frank Rudzicz
Machine learning has shown promise for automatic detection of Alzheimer's disease (AD) through speech; however, efforts are hampered by a scarcity of data, especially in languages other than English.
no code implementations • 6 Feb 2019 • Jixuan Wang, Kuan-Chieh Wang, Marc Law, Frank Rudzicz, Michael Brudno
Speaker embedding models that utilize neural networks to map utterances to a space where distances reflect similarity between speakers have driven recent progress in the speaker recognition task.
1 code implementation • 29 Nov 2018 • Aparna Balagopalan, Jekaterina Novikova, Frank Rudzicz, Marzyeh Ghassemi
We analyze the impact of age of the added samples and if they affect fairness in classification.
no code implementations • 26 Nov 2018 • Yi-Te Hsu, Zining Zhu, Chi-Te Wang, Shih-Hau Fang, Frank Rudzicz, Yu Tsao
In this study, we propose a detection system for pathological voice, which is robust against the channel effect.
1 code implementation • ICLR 2019 • Safwan Hossain, Kiarash Jamali, Yuchen Li, Frank Rudzicz
Current approaches attempt to learn the transformation from a noise sample to a generated data sample in one shot.
2 code implementations • 18 Nov 2018 • Yuchen Li, Safwan Hossain, Kiarash Jamali, Frank Rudzicz
We consider a classifier whose test set is exposed to various perturbations that are not present in the training set.
no code implementations • EMNLP 2018 • Chlo{\'e} Pou-Prom, Frank Rudzicz
As the incidence of Alzheimer{'}s Disease (AD) increases, early detection becomes crucial.
no code implementations • NAACL 2019 • Zining Zhu, Jekaterina Novikova, Frank Rudzicz
In this paper, we also present two methods that improve the performance of CNs.
no code implementations • NAACL 2019 • Akshay Budhkar, Frank Rudzicz
This paper presents three hybrid models that directly combine latent Dirichlet allocation and word embedding for distinguishing between speakers with and without Alzheimer's disease from transcripts of picture descriptions.
no code implementations • 11 Aug 2018 • Bai Li, Ran Zhang, Frank Rudzicz
We replicate a variation of the image captioning architecture by Vinyals et al. (2015), then introduce dropout during inference mode to simulate the effects of neurodegenerative diseases like Alzheimer's disease (AD) and Wernicke's aphasia (WA).
no code implementations • 19 Jul 2018 • Zining Zhu, Jekaterina Novikova, Frank Rudzicz
One of the most prevalent symptoms among the elderly population, dementia, can be detected by classifiers trained on linguistic features extracted from narrative transcripts.
no code implementations • 23 May 2018 • Zining Zhu, Jekaterina Novikova, Frank Rudzicz
Deep learning has demonstrated abilities to learn complex structures, but they can be restricted by available data.
no code implementations • 30 Nov 2017 • Zeinab Noorian, Chloé Pou-Prom, Frank Rudzicz
Data sets for identifying Alzheimer's disease (AD) are often relatively sparse, which limits their ability to train generalizable models.
1 code implementation • WS 2017 • Judy Hanwen Shen, Frank Rudzicz
Previous investigations into detecting mental illnesses through social media have predominately focused on detecting depression through Twitter corpora.
no code implementations • CL 2017 • Hamidreza Chinaei, Leila Chan Currie, Andrew Danks, Hubert Lin, Tejas Mehta, Frank Rudzicz
Alzheimer{'}s disease (AD) is an increasingly prevalent cognitive disorder in which memory, language, and executive function deteriorate, usually in that order.
no code implementations • 14 Sep 2016 • Peng Dai, Xue Teng, Frank Rudzicz, Ing Yann Soon
Experiments are carried out on the AURORA2 database and show that the word recognition rate using our proposed feature extraction method is significantly increased over the baseline.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 11 Aug 2016 • Stefania Raimondo, Frank Rudzicz
Automatically detecting inappropriate content can be a difficult NLP task, requiring understanding context and innuendo, not just identifying specific keywords.
no code implementations • 17 Mar 2016 • Samantha Wong, Hamidreza Chinaei, Frank Rudzicz
Informatics around public health are increasingly shifting from the professional to the public spheres.
no code implementations • 9 Dec 2015 • Hamidreza Chinaei, Mohsen Rais-Ghasem, Frank Rudzicz
In business analytics, measure values, such as sales numbers or volumes of cargo transported, are often summed along values of one or more corresponding categories, such as time or shipping container.