132 citations · 161 across the 15 of their papers we have counts for
15 papers
Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination
Vijay Vankadaru, Asha Matthews, Tanya Roosta +1
Hallucination remains one of the central obstacles to deploying medical LLMs. Yet, even when hallucination can be detected, it is still unclear whether the internal representations…
The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs
Bryan Guan, Tanya Roosta, Peyman Passban +1
As large language models (LLMs) become integral to diverse applications, ensuring their reliability under varying input conditions is crucial. One key issue affecting this reliabil…
What is Lost in Knowledge Distillation?
Manas Mohanty, Tanya Roosta, Peyman Passban
Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge dist…
Training Mixed-Domain Translation Models via Federated Learning
Peyman Passban, Tanya Roosta, Rahul Gupta +2
Training mixed-domain translation models is a complex task that demands tailored architectures and costly data preparation techniques. In this work, we leverage federated learning…
Dynamic Position Encoding for Transformers
Joyce Zheng, Mehdi Rezagholizadeh, Peyman Passban
Recurrent models have been dominating the field of neural machine translation (NMT) for the past few years. Transformers \citep{vaswani2017attention}, have radically changed it by…
Communication-Efficient Federated Learning for Neural Machine Translation
Tanya Roosta, Peyman Passban, Ankit Chadha
Training neural machine translation (NMT) models in federated learning (FL) settings could be inefficient both computationally and communication-wise, due to the large size of tran…
Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax
Ehsan Kamalloo, Mehdi Rezagholizadeh, Peyman Passban +1
In Natural Language Processing (NLP), finding data augmentation techniques that can produce high-quality human-interpretable examples has always been challenging. Recently, leverag…
Robust Embeddings Via Distributions
Kira A. Selby, Yinong Wang, Ruizhe Wang +4
Despite recent monumental advances in the field, many Natural Language Processing (NLP) models still struggle to perform adequately on noisy domains. We propose a novel probabilist…
From Fully Trained to Fully Random Embeddings: Improving Neural Machine Translation with Compact Word Embedding Tables
Krtin Kumar, Peyman Passban, Mehdi Rezagholizadeh +2
Embedding matrices are key components in neural natural language processing (NLP) models that are responsible to provide numerical representations of input tokens.\footnote{In this…
ALP-KD: Attention-Based Layer Projection for Knowledge Distillation
Peyman Passban, Yimeng Wu, Mehdi Rezagholizadeh +1
Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The…
Revisiting Robust Neural Machine Translation: A Transformer Case Study
Peyman Passban, Puneeth S. M. Saladi, Qun Liu
Transformers (Vaswani et al., 2017) have brought a remarkable improvement in the performance of neural machine translation (NMT) systems but they could be surprisingly vulnerable t…
Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers
Yimeng Wu, Peyman Passban, Mehdi Rezagholizade +1
With the growth of computing power neural machine translation (NMT) models also grow accordingly and become better. However, they also become harder to deploy on edge devices due t…
Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation
Peyman Passban, Qun Liu, Andy Way
Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence…
Investigating Backtranslation in Neural Machine Translation
Alberto Poncelas, Dimitar Shterionov, Andy Way +2
A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. Th…
Sketching Word Vectors Through Hashing
Behrang QasemiZadeh, Laura Kallmeyer
We propose a new fast word embedding technique using hash functions. The method is a derandomization of a new type of random projections: By disregarding the classic constraint use…