Brendan King

I’m a third year PhD student in Natural Language Processing, working with Prof. Jeffrey Flanigan. My research is focused on dialogue understanding, interactive systems, few-shot NLP methods, and continual learning.

Previously, I was a software engineer at Apptio, and before that a computational research intern at the Institute for Systems Biology, where I helped develop methods for automatic metabolic reconstruction of microbes with Prof. Nathan Price. I also completed my BS in computer science at University of Washington. Outside of work and research I enjoy hiking, mountaineering, skiing and otherwise being outdoors!

news

Jul 8, 2023	Our work “Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking” will be presented at Findings of the ACL, 2023! [paper] [code]
Dec 22, 2022	Our work on Dependency Dialogue Acts (DDA) will be presented at IWSDS 2023!
Sep 22, 2021	Starting my PhD at UC Santa Cruz working with Prof. Jeffrey Flanigan!

selected publications

Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking

Brendan King, and Jeffrey Flanigan

Jul 2023

PDF Code
Dependency Dialogue Acts — Annotation Scheme and Case Study

Jon Cai, Brendan King, Margaret Perkoff, and 9 more authors

In The 13th International Workshop on Spoken Dialogue Systems Technology, IWSDS 2023, Los Angeles, United States, Feb 2023

PDF
ProbAnnoWeb and ProbAnnoPy: probabilistic annotation and gap-filling of metabolic reconstructions

Brendan King, Terry Farrah, Matthew A. Richards, and 3 more authors

Bioinformatics (Oxford, England), May 2018

Abs

SUMMARY: Gap-filling is a necessary step to produce quality genome-scale metabolic reconstructions capable of flux-balance simulation. Most available gap-filling tools use an organism-agnostic approach, where reactions are selected from a database to fill gaps without consideration of the target organism. Conversely, our likelihood based gap-filling with probabilistic annotations selects candidate reactions based on a likelihood score derived specifically from the target organism’s genome. Here, we present two new implementations of probabilistic annotation and likelihood based gap-filling: a web service called ProbAnnoWeb, and a standalone python package called ProbAnnoPy. AVAILABILITY AND IMPLEMENTATION: Our tools are available as a web service with no installation needed (ProbAnnoWeb) at probannoweb.systemsbiology.net, and as a local python package implementation (ProbAnnoPy) at github.com/PriceLab/probannopy. CONTACT: evangelos.simeonidis@systemsbiology.org or nathan.price@systemsbiology.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.