no code implementations • NAACL (MIA) 2022 • Zhucheng Tu, Sarguna Janani Padmanabhan
The first stage consists of multilingual passage retrieval with a hybrid dense and sparse retrieval strategy.
no code implementations • 17 Feb 2021 • Svitlana Vakulenko, Nikos Voskarides, Zhucheng Tu, Shayne Longpre
This paper describes the participation of UvA. ILPS group at the TREC CAsT 2020 track.
1 code implementation • 19 Jan 2021 • Svitlana Vakulenko, Nikos Voskarides, Zhucheng Tu, Shayne Longpre
Conversational passage retrieval relies on question rewriting to modify the original question so that it no longer depends on the conversation history.
1 code implementation • EMNLP (scai) 2020 • Svitlana Vakulenko, Shayne Longpre, Zhucheng Tu, Raviteja Anantha
The dependency between an adequate question formulation and correct answer selection is a very intriguing but still underexplored area.
2 code implementations • NAACL 2021 • Raviteja Anantha, Svitlana Vakulenko, Zhucheng Tu, Shayne Longpre, Stephen Pulman, Srinivas Chappidi
We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs.
no code implementations • 30 Apr 2020 • Svitlana Vakulenko, Shayne Longpre, Zhucheng Tu, Raviteja Anantha
Conversational question answering (QA) requires the ability to correctly interpret a question in the context of previous conversation turns.
1 code implementation • 9 Jan 2020 • Hadi Pouransari, Zhucheng Tu, Oncel Tuzel
We conduct experiments on the ImageNet dataset and show a reduced accuracy gap when using the proposed least squares quantization algorithms.
no code implementations • WS 2019 • Shayne Longpre, Yi Lu, Zhucheng Tu, Chris DuBois
To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation.
no code implementations • NAACL 2018 • Zhucheng Tu, Mengping Li, Jimmy Lin
We demonstrate the serverless deployment of neural networks for model inferencing in NLP applications using Amazon{'}s Lambda service for feedforward evaluation and DynamoDB for storing word embeddings.
no code implementations • NAACL 2018 • Yiyun Liang, Zhucheng Tu, Laetitia Huang, Jimmy Lin
We demonstrate a JavaScript implementation of a convolutional neural network that performs feedforward inference completely in the browser.
no code implementations • 25 Jul 2017 • Royal Sequiera, Gaurav Baruah, Zhucheng Tu, Salman Mohammed, Jinfeng Rao, Haotian Zhang, Jimmy Lin
Most work on natural language question answering today focuses on answer selection: given a candidate list of sentences, determine which contains the answer.