Michael Zeng

Large-Scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification

2022 · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

The speech representations learned from large-scale unlabeled data have shown better generalizability than those from supervised learning and thus attract a lot of interest to be applied for various downstream tasks. In this paper, we …

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

2022 · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering

2018 · arXiv (Cornell University)

Conversational question answering (CQA) is a novel QA task that requires understanding of dialogue context. Different from traditional single-turn machine reading comprehension (MRC) tasks, CQA includes passage comprehension, coreference resolution, and contextual understanding. In this …

MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization

2021

This paper introduces MEDIASUM 1 , a largescale media interview dataset consisting of 463.6K transcripts with abstractive summaries. To create this dataset, we collect interview transcripts from NPR and CNN and employ the overview and …

MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

2023 · arXiv (Cornell University)

We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks …

Automatic Prompt Optimization with “Gradient Descent” and Beam Search

2023

Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort. We propose a simple and nonparametric solution …