Tao Lei

is this you? claim profile

0 followers
MIT ∙ ASAPP INC

Autoregressive Knowledge Distillation through Imitation Learning

The performance of autoregressive models on natural language generation ...
09/15/2020 ∙ by Alexander Lin, et al. ∙ 0 ∙ share

read it
Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport

Selecting input features of top relevance has become a popular method fo...
05/27/2020 ∙ by Kyle Swanson, et al. ∙ 7 ∙ share

read it
ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition

In this paper we present state-of-the-art (SOTA) performance on the Libr...
05/21/2020 ∙ by Jing Pan, et al. ∙ 0 ∙ share

read it
Interactive Classification by Asking Informative Questions

Natural language systems often rely on a single, potentially ambiguous i...
11/09/2019 ∙ by Lili Yu, et al. ∙ 0 ∙ share

read it
Metric Learning for Dynamic Text Classification

Traditional text classifiers are limited to predicting over a fixed set ...
11/04/2019 ∙ by Jeremy Wohlwend, et al. ∙ 0 ∙ share

read it
Structured Pruning of Large Language Models

Large language models have recently achieved state of the art performanc...
10/10/2019 ∙ by Ziheng Wang, et al. ∙ 0 ∙ share

read it
Building a Production Model for Retrieval-Based Chatbots

Response suggestion is an important task for building human-computer con...
06/07/2019 ∙ by Kyle Swanson, et al. ∙ 0 ∙ share

read it
Adaptive Morphological Reconstruction for Seeded Image Segmentation

Morphological reconstruction (MR) is often employed by seeded image segm...
04/08/2019 ∙ by Tao Lei, et al. ∙ 0 ∙ share

read it
Service Capacity Enhanced Task Offloading and Resource Allocation in Multi-Server Edge Computing Environment

An edge computing environment features multiple edge servers and multipl...
03/12/2019 ∙ by Wei Du, et al. ∙ 0 ∙ share

read it
Adversarial Domain Adaptation for Duplicate Question Detection

We address the problem of detecting duplicate questions in forums, which...
09/07/2018 ∙ by Darsh J Shah, et al. ∙ 0 ∙ share

read it
Training RNNs as Fast as CNNs

Common recurrent neural network architectures scale poorly due to the in...
09/08/2017 ∙ by Tao Lei, et al. ∙ 0 ∙ share

read it
Style Transfer from Non-Parallel Text by Cross-Alignment

This paper focuses on style transfer on the basis of non-parallel text. ...
05/26/2017 ∙ by Tianxiao Shen, et al. ∙ 0 ∙ share

read it
Deriving Neural Architectures from Sequence and Graph Kernels

The design of neural architectures for structured objects is typically g...
05/25/2017 ∙ by Tao Lei, et al. ∙ 0 ∙ share

read it
Rationalizing Neural Predictions

Prediction without justification has limited applicability. As a remedy,...
06/13/2016 ∙ by Tao Lei, et al. ∙ 0 ∙ share

read it
Semi-supervised Question Retrieval with Gated Convolutions

Question answering forums are rapidly growing in size with no effective ...
12/17/2015 ∙ by Tao Lei, et al. ∙ 0 ∙ share

read it
Molding CNNs for text: non-linear, non-consecutive convolutions

The success of deep learning often derives from well-chosen operational ...
08/17/2015 ∙ by Tao Lei, et al. ∙ 0 ∙ share

read it

Tao Lei

Featured Co-authors

Wei Wang

Wei Liu

Yu Zhang

Preslav Nakov

Regina Barzilay

Tongliang Liu

Tommi Jaakkola

Lluis Marquez

Yoav Artzi

Alessandro Moschitti

Wengong Jin

Autoregressive Knowledge Distillation through Imitation Learning

Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport

ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognition

Interactive Classification by Asking Informative Questions

Metric Learning for Dynamic Text Classification

Structured Pruning of Large Language Models

Building a Production Model for Retrieval-Based Chatbots

Adaptive Morphological Reconstruction for Seeded Image Segmentation

Service Capacity Enhanced Task Offloading and Resource Allocation in Multi-Server Edge Computing Environment

Adversarial Domain Adaptation for Duplicate Question Detection

Training RNNs as Fast as CNNs

Style Transfer from Non-Parallel Text by Cross-Alignment

Deriving Neural Architectures from Sequence and Graph Kernels

Rationalizing Neural Predictions

Semi-supervised Question Retrieval with Gated Convolutions

Molding CNNs for text: non-linear, non-consecutive convolutions