68 citations · 218 across the 63 of their papers we have counts for
66 papers
Measuring Information in Text Explanations
Zining Zhu, Frank Rudzicz
Text-based explanation is a particularly promising approach in explainable AI, but the evaluation of text explanations is method-dependent. We argue that placing the explanations o…
SurGNN: Explainable visual scene understanding and assessment of surgical skill using graph neural networks
Shuja Khalid, Frank Rudzicz
This paper explores how graph neural networks (GNNs) can be used to enhance visual scene understanding and surgical skill assessment. By using GNNs to analyze the complex visual da…
Situated Natural Language Explanations
Zining Zhu, Haoming Jiang, Jingfeng Yang +6
Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to genera…
Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning
Xindi Wang, Yufei Wang, Can Xu +6
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 explici…
Improving Automatic Quotation Attribution in Literary Novels
Krishnapriya Vishnubhotla, Frank Rudzicz, Graeme Hirst +1
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…
MLHOps: Machine Learning for Healthcare Operations
Faiza Khan Khattak, Vallijah Subasri, Amrit Krishnan +4
Machine Learning Health Operations (MLHOps) is the combination of processes for reliable, efficient, usable, and ethical deployment and maintenance of machine learning models in he…
RefiNeRF: Modelling dynamic neural radiance fields with inconsistent or missing camera parameters
Shuja Khalid, Frank Rudzicz
Novel view synthesis (NVS) is a challenging task in computer vision that involves synthesizing new views of a scene from a limited set of input images. Neural Radiance Fields (NeRF…
Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support
Stephen Obadinma, Faiza Khan Khattak, Shirley Wang +23
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 Natura…
Predicting Fine-Tuning Performance with Probing
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. Alternatively, probing has receive…
Data-driven Approach to Differentiating between Depression and Dementia from Noisy Speech and Language Data
Malikeh Ehghaghi, Frank Rudzicz, Jekaterina Novikova
A significant number of studies apply acoustic and linguistic characteristics of human speech as prominent markers of dementia and depression. However, studies on discriminating de…
wildNeRF: Complete view synthesis of in-the-wild dynamic scenes captured using sparse monocular data
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. Our end-to-end trainable algorithm l…
Conformal Mirror Descent with Logarithmic Divergences
Amanjit Singh Kainth, Ting-Kam Leonard Wong, Frank Rudzicz
The logarithmic divergence is an extension of the Bregman divergence motivated by optimal transport and a generalized convex duality, and satisfies many remarkable properties. Usin…
OOD-Probe: A Neural Interpretation of Out-of-Domain Generalization
Zining Zhu, Soroosh Shahtalebi, Frank Rudzicz
The ability to generalize out-of-domain (OOD) is an important goal for deep neural network development, and researchers have proposed many high-performing OOD generalization method…
Relevance in Dialogue: Is Less More? An Empirical Comparison of Existing Metrics, and a Novel Simple Metric
Ian Berlot-Attwell, Frank Rudzicz
In this work, we evaluate various existing dialogue relevance metrics, find strong dependency on the dataset, often with poor correlation with human scores of relevance, and propos…
The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
Aparna Balagopalan, Haoran Zhang, Kimia Hamidieh +3
Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc exp…
Detoxifying Language Models with a Toxic Corpus
Yoon A Park, Frank Rudzicz
Existing studies have investigated the tendency of autoregressive language models to generate contexts that exhibit undesired biases and toxicity. Various debiasing approaches have…
MeSHup: A Corpus for Full Text Biomedical Document Indexing
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. Curr…
Doctor XAvIer: Explainable Diagnosis on Physician-Patient Dialogues and XAI Evaluation
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 att…
KenMeSH: Knowledge-enhanced End-to-end Biomedical Text Labelling
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 rel…
On the data requirements of probing
Zining Zhu, Jixuan Wang, Bai Li +1
As large and powerful neural language models are developed, researchers have been increasingly interested in developing diagnostic tools to probe them. There are many papers with c…
Neural reality of argument structure constructions
Bai Li, Zining Zhu, Guillaume Thomas +2
In lexicalist linguistic theories, argument structure is assumed to be predictable from the meaning of verbs. As a result, the verb is the primary determinant of the meaning of a c…
Improving greedy core-set configurations for active learning with uncertainty-scaled distances
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 efficienc…
Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
Jixuan Wang, Kuan-Chieh Wang, Frank Rudzicz +1
Large pretrained language models (LMs) like BERT have improved performance in many disparate natural language processing (NLP) tasks. However, fine tuning such models requires a la…
Quantifying the Task-Specific Information in Text-Based Classifications
Zining Zhu, Aparna Balagopalan, Marzyeh Ghassemi +1
Recently, neural natural language models have attained state-of-the-art performance on a wide variety of tasks, but the high performance can result from superficial, surface-level…