Qile Zhu
YOU?
Author Swipe
View article: Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding
Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding Open
Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve thi…
View article: Asking Complex Questions with Multi-hop Answer-focused Reasoning
Asking Complex Questions with Multi-hop Answer-focused Reasoning Open
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 questio…
View article: A Batch Normalized Inference Network Keeps the KL Vanishing Away
A Batch Normalized Inference Network Keeps the KL Vanishing Away Open
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. However, when paired with strong autoregre…
View article: Improving Question Generation with Sentence-Level Semantic Matching and Answer Position Inferring
Improving Question Generation with Sentence-Level Semantic Matching and Answer Position Inferring Open
Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrele…
View article: Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition
Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition Open
Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical mod…
View article: Don’t Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding
Don’t Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding Open
Semantic parsing is one of the key components of natural language understanding systems. A successful parse transforms an input utterance to an action that is easily understood by the system. Many algorithms have been proposed to solve thi…
View article: A Batch Normalized Inference Network Keeps the KL Vanishing Away
A Batch Normalized Inference Network Keeps the KL Vanishing Away Open
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. However, when paired with strong autoregre…
View article: Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring
Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring Open
Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrele…
View article: Statistical learning for semantic parsing: A survey
Statistical learning for semantic parsing: A survey Open
A long-term goal of Artificial Intelligence (AI) is to provide machines with the capability of understanding natural language. Understanding natural language may be referred as the system must produce a correct response to the received inp…
View article: GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model
GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model Open
Discovering the latent topics within texts has been a fundamental task for many applications. However, conventional topic models suffer different problems in different settings. The Latent Dirichlet Allocation (LDA) may not work well for s…
View article: Adversarial Examples: Attacks and Defenses for Deep Learning
Adversarial Examples: Attacks and Defenses for Deep Learning Open
With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input…
View article: GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text
GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text Open
Motivation Best performing named entity recognition (NER) methods for biomedical literature are based on hand-crafted features or task-specific rules, which are costly to produce and difficult to generalize to other corpora. End-to-end neu…
View article: Learning Fast and Slow: PROPEDEUTICA for Real-time Malware Detection
Learning Fast and Slow: PROPEDEUTICA for Real-time Malware Detection Open
Existing malware detectors on safety-critical devices have difficulties in runtime detection due to the performance overhead. In this paper, we introduce PROPEDEUTICA, a framework for efficient and effective real-time malware detection, le…
View article: Single Shot Text Detector with Regional Attention
Single Shot Text Detector with Regional Attention Open
We present a novel single-shot text detector that directly outputs word-level bounding boxes in a natural image. We propose an attention mechanism which roughly identifies text regions via an automatically learned attentional map. This sub…
View article: Character Sequence-to-Sequence Model with Global Attention for Universal Morphological Reinflection
Character Sequence-to-Sequence Model with Global Attention for Universal Morphological Reinflection Open
This paper presents a neural network based approach for the CoNLL-SIGMORPHON-2017 Shared Task 1 on morphological reinflection.We propose an encoder-decoder architecture to model this morphological reinflection problem.For an input word, ev…