Justin Chiu — accepted AI-conference papers

2024

A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames

Pinelopi Papalampidi, Skanda Koppula, Shreya Pathak, Justin Chiu, Joe Heyward, Viorica Patraucean +4

CVPR 2024poster

Understanding long real-world videos requires modeling of long-range visual dependencies. To this end we explore video-first architectures building on the common paradigm of transferring large-scale image--text models to video via shallow temporal fusion. However we expose two limitations to the app…

Cited by 26 Source ↗PDF ↗Scholar ↗

2024

Asking More Informative Questions for Grounded Retrieval

Sedrick Keh, Justin Chiu, Daniel Fried

NAACL 2024findings

When a model is trying to gather information in an interactive setting, it benefits from asking informative questions. However, in the case of a grounded multi-turn image identification task, previous studies have been constrained to polar yes/no questions (White et al., 2021), limiting how much inf…

Cited by 2 Source ↗PDF ↗Scholar ↗

2024

Predicting Text Preference Via Structured Comparative Reasoning

Jing Nathan Yan, Tianqi Liu, Justin Chiu, Jiaming Shen, Zhen Qin, Yue Yu +5

ACL 2024long

Comparative reasoning plays a crucial role in predicting text preferences; however, large language models (LLMs) often demonstrate inconsistencies in their reasoning, leading to incorrect preference predictions. While approaches like Chain-of-Thought improve accuracy in many settings, they struggle…

Cited by 6 Source ↗PDF ↗Scholar ↗

2024

UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations

Wenting Zhao, Justin Chiu, Jena Hwang, Faeze Brahman, Jack Hessel, Sanjiban Choudhury +3

NAACL 2024long

Language technologies that accurately model the dynamics of events must perform commonsense reasoning. Existing work evaluating commonsense reasoning focuses on making inferences about common, everyday situations. To instead investigate the ability to model unusual, unexpected, and unlikely situatio…

Cited by 3 Source ↗PDF ↗Scholar ↗

2023

Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations

Wenting Zhao, Justin Chiu, Claire Cardie, Alexander Rush

ACL 2023long

Abductive reasoning aims to find plausible explanations for an event. This style of reasoning is critical for commonsense tasks where there are often multiple plausible explanations. Existing approaches for abductive reasoning in natural language processing (NLP) often rely on manually generated ann…

Cited by 17 Source ↗PDF ↗Scholar ↗

2022

Cross-Encoder Data Annotation for Bi-Encoder Based Product Matching

Justin Chiu, Keiji Shinzato

EMNLP 2022industry

Matching a seller listed item to an appropriate product is an important step for an e-commerce platform. With the recent advancement in deep learning, there are different encoder based approaches being proposed as solution. When textual data for two products are available, cross-encoder approaches e…

Cited by 5 Source ↗PDF ↗Scholar ↗

2022

Unsupervised Text Deidentification

John Morris, Justin Chiu, Ramin Zabih, Alexander Rush

EMNLP 2022finding

Deidentification seeks to anonymize textual data prior to distribution. Automatic deidentification primarily uses supervised named entity recognition from human-labeled data points. We propose an unsupervised deidentification method that masks words that leak personally-identifying information. The…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2021

Reference-Centric Models for Grounded Collaborative Dialogue

Daniel Fried, Justin Chiu, Dan Klein

EMNLP 2021main

We present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game. We focus on a setting where two agents each observe an overlapping part of a world context and need to identify and agree on some object they share. Therefore, the agents…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗

2019

Tensor Variable Elimination for Plated Factor Graphs

Fritz Obermeyer, Eli Bingham, Martin Jankowiak, Neeraj Pradhan, Justin Chiu, Alexander Rush +1

ICML 2019oral

A wide class of machine learning algorithms can be reduced to variable elimination on factor graphs. While factor graphs provide a unifying notation for these algorithms, they do not provide a compact way to express repeated structure when compared to plate diagrams for directed graphical models. To…

Cited by 27 Source ↗PDF ↗code ↗Scholar ↗

2018

Latent Alignment and Variational Attention

Yuntian Deng, Yoon Kim, Justin Chiu, Demi Guo, Alexander Rush

NeurIPS 2018poster

Neural attention has become central to many state-of-the-art models in natural language processing and related domains. Attention networks are an easy-to-train and effective method for softly simulating alignment; however, the approach does not marginalize over latent alignments in a probabilistic s…

Cited by 161 Source ↗PDF ↗code ↗Scholar ↗