Yikang Shen

Multidimensional scaling based knowledge provision for new questions in community Question Answering systems

2016

Community-based Question Answering (CQA) sites have become popular since they allow users to get answers to complex, detailed and personal question from other users directly. However, since answering a question depends on the ability and …

An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training

2023 · arXiv (Cornell University)

We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Despite considerable progress in multi-task learning, most efforts focus on learning from multi-label data: a single …

Mixture of Attention Heads: Selecting Attention Heads Per Token

2022

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer architecture. This …

GraphText: Graph Reasoning in Text Space

2023 · arXiv (Cornell University)

Large Language Models (LLMs) have gained the ability to assimilate human knowledge and facilitate natural language interactions with both humans and other LLMs. However, despite their impressive achievements, LLMs have not made significant advancements in …

Question/Answer Matching for CQA System via Combining Lexical and Sequential Information

2015 · Proceedings of the AAAI Conference on Artificial Intelligence

Community-based Question Answering (CQA) has become popular in knowledge sharing sites since it allows users to get answers to complex, detailed, and personal questions directly from other users. Large archives of historical questions and associated …

BanditSum: Extractive Summarization as a Contextual Bandit

2018

In this work, we propose a novel method for training neural networks to perform singledocument extractive summarization without heuristically-generated extractive labels. We call our approach BANDITSUM as it treats extractive summarization as a contextual bandit …