4 citations · 10 across the 7 of their papers we have counts for
7 papers
Where does In-context Translation Happen in Large Language Models
Suzanna Sia, David Mueller, Kevin Duh
Self-supervised large language models have demonstrated the ability to perform Machine Translation (MT) via in-context learning, but little is known about where the model performs…
Anti-LM Decoding for Zero-shot In-context Machine Translation
Suzanna Sia, Alexandra DeLucia, Kevin Duh
Zero-shot In-context learning is the phenomenon where models can perform the task simply given the instructions. However, pre-trained large language models are known to be poorly c…
In-context Learning as Maintaining Coherency: A Study of On-the-fly Machine Translation Using Large Language Models
Suzanna Sia, Kevin Duh
The phenomena of in-context learning has typically been thought of as "learning from examples". In this work which focuses on Machine Translation, we present a perspective of in-co…
Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI
Suzanna Sia, Anton Belyy, Amjad Almahairi +3
Evaluating an explanation's faithfulness is desired for many reasons such as trust, interpretability and diagnosing the sources of model's errors. In this work, which focuses on th…
Clustering with UMAP: Why and How Connectivity Matters
Ayush Dalmia, Suzanna Sia
Topology based dimensionality reduction methods such as t-SNE and UMAP have seen increasing success and popularity in high-dimensional data. These methods have strong mathematical…
Mixture of Speaker-type PLDAs for Children's Speech Diarization
Jiamin Xie, Suzanna Sia, Paola Garcia +2
In diarization, the PLDA is typically used to model an inference structure which assumes the variation in speech segments be induced by various speakers. The speaker variation is t…
Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!
Suzanna Sia, Ayush Dalmia, Sabrina J. Mielke
Topic models are a useful analysis tool to uncover the underlying themes within document collections. The dominant approach is to use probabilistic topic models that posit a genera…