Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding

no code implementations • CONLL 2020 • Qile Zhu, Haidar Khan, Saleh Soltan, Stephen Rawls, Wael Hamza

For complex parsing tasks, the state-of-the-art method is based on autoregressive sequence to sequence models to generate the parse directly.

Natural Language Understanding Semantic Parsing +4

Asking Complex Questions with Multi-hop Answer-focused Reasoning

1 code implementation • 16 Sep 2020 • Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Wu

Asking questions from natural language text has attracted increasing attention recently, and several schemes have been proposed with promising results by asking the right question words and copy relevant words from the input to the question.

Question Generation Question-Generation

A Batch Normalized Inference Network Keeps the KL Vanishing Away

1 code implementation • ACL 2020 • Qile Zhu, Jianlin Su, Wei Bi, Xiaojiang Liu, Xiyao Ma, Xiaolin Li, Dapeng Wu

Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks.

Dialogue Generation Language Modelling +3

Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition

no code implementations • 12 Mar 2020 • Zhigang Dai, Jinhua Fu, Qile Zhu, Hengbin Cui, Xiaolong Li, Yuan Qi

We revise the attention distribution to focus on the local and contextual semantic information by incorporating the relative position information between utterances.

Sentence

Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring

no code implementations • 2 Dec 2019 • Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Wu

Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation.

Position Question Generation +2

GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model

1 code implementation • EMNLP 2018 • Qile Zhu, Zheng Feng, Xiaolin Li

In this paper, we propose a novel way called GraphBTM to represent biterms as graphs and design a Graph Convolutional Networks (GCNs) with residual connections to extract transitive features from biterms.

Recommendation Systems Topic Models +1

Adversarial Examples: Attacks and Defenses for Deep Learning

1 code implementation • 19 Dec 2017 • Xiaoyong Yuan, Pan He, Qile Zhu, Xiaolin Li

In this paper, we review recent findings on adversarial examples for deep neural networks, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods.

Learning Fast and Slow: PROPEDEUTICA for Real-time Malware Detection

no code implementations • 4 Dec 2017 • Ruimin Sun, Xiaoyong Yuan, Pan He, Qile Zhu, Aokun Chen, Andre Gregio, Daniela Oliveira, Xiaolin Li

Existing malware detectors on safety-critical devices have difficulties in runtime detection due to the performance overhead.

General Classification Malware Detection

Single Shot Text Detector with Regional Attention

1 code implementation • ICCV 2017 • Pan He, Weilin Huang, Tong He, Qile Zhu, Yu Qiao, Xiaolin Li

Our text detector achieves an F-measure of 77% on the ICDAR 2015 bench- mark, advancing the state-of-the-art results in [18, 28].

Scene Text Detection

Character Sequence-to-Sequence Model with Global Attention for Universal Morphological Reinflection

no code implementations • CONLL 2017 • Qile Zhu, Yanjun Li, Xiaolin Li

Machine Translation Question Answering