Papers by Zhucheng Tu

4 papers
Open-Domain Question Answering Goes Conversational via Question Rewriting (2021.naacl-main)

Copied to clipboard

Challenge: Existing large-scale benchmarks for conversational QA limit the topic of conversation to the content of a single document.
Approach: They propose a dataset for Question Rewriting in Conversational Context (QReCC) the dataset contains 14K conversations with 80K question-answer pairs.
Outcome: The proposed approach shows that the first baseline for the QReCC dataset is 19.10, compared to the human upper bound of 75.45, indicating the difficulty of the setup and a large room for improvement.
An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering (D19-58)

Copied to clipboard

Challenge: XLNet model is domain-agnostic for the MRQA 2019 Shared Task . a negative sampling technique is particularly effective for datasets that include unanswerable questions .
Approach: They develop a domain-agnostic question answering model for the MRQA 2019 Shared Task . they use large pre-trained language models, various data sampling strategies and query and context paraphrases generated by back-translation .
Outcome: The proposed model achieves second best Exact Match and F1 in the MRQA leaderboard competition.
CNNs for NLP in the Browser: Client-Side Deployment and Visualization Opportunities (N18-5)

Copied to clipboard

Challenge: a JavaScript implementation of a convolutional neural network performs feedforward inference completely in the browser.
Approach: They propose a JavaScript implementation that performs feedforward inference completely in the browser.
Outcome: The proposed model performs feedforward inference completely in the browser without server requests . the proposed model is useful for applications with stringent latency requirements or low connectivity .
Pay-Per-Request Deployment of Neural Network Models Using Serverless Architectures (N18-5)

Copied to clipboard

Challenge: Using Amazon’s Lambda service for feedforward evaluation and DynamoDB for word embeddings, we demonstrate a serverless deployment of neural networks for NLP applications.
Approach: They propose a pay-per-request pricing model for neural network deployment in NLP applications using Amazon’s Lambda service for feedforward evaluation and DynamoDB for storing word embeddings.
Outcome: The proposed architecture is scalable and inexpensive.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations