Hao Zhou

An Improved PageRank Algorithm Based on Web Content

2015

With the development of Web technology and more kinds of information, how to provide high quality, relevant search results become a huge challenge to the current Web search engines. We analyze the shortcomings of PageRank …

Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation

2018 · arXiv (Cornell University)

The variational autoencoder (VAE) imposes a probabilistic distribution (typically Gaussian) on the latent space and penalizes the Kullback--Leibler (KL) divergence between the posterior and prior. In NLP, VAEs are extremely difficult to train due to …

AutoCross

2019

Feature crossing captures interactions among categorical features and is useful to enhance learning from tabular data in real-world businesses. In this paper, we present AutoCross, an automatic feature crossing tool provided by 4Paradigm to its …

Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs

2020 · arXiv (Cornell University)

Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neural network training, is hard to analyze, theoretically. The huge gap …

On the Sentence Embeddings from Pre-trained Language Models

2020 · arXiv (Cornell University)

Pre-trained contextual representations like BERT have achieved great success in natural language processing. However, the sentence embeddings from the pre-trained language models without fine-tuning have been found to poorly capture semantic meaning of sentences. In …

"Listen, Understand and Translate": Triple Supervision Decouples End-to-end Speech-to-text Translation

2020 · arXiv (Cornell University)

An end-to-end speech-to-text translation (ST) takes audio in a source language and outputs the text in a target language. Existing methods are limited by the amount of parallel corpus. Can we build a system to …

On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Dialogue safety problems severely limit the real-world deployment of neural conversational models and have attracted great research interests recently. However, dialogue safety problems remain under-defined and the corresponding dataset is scarce. We propose a taxonomy …

E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning

2022 · Findings of the Association for Computational Linguistics: ACL 2022

The ability to recognize analogies is fundamental to human cognition. Existing benchmarks to test word analogy do not reveal the underneath process of analogical reasoning of neural models. Holding the belief that models capable of …

Backdoor Threats from Compromised Foundation Models to Federated Learning

2023 · arXiv (Cornell University)

Federated learning (FL) represents a novel paradigm to machine learning, addressing critical issues related to data privacy and security, yet suffering from data insufficiency and imbalance. The emergence of foundation models (FMs) provides a promising …

Anomaly Sound Detection of Industrial Equipment Based on Incremental Learning

2023

The objective of the anomaly sound detection task is to monitor for sounds coming from the target object and analyze whether they are coming from it normally or in an anomalous status. Existing anomaly sound …

XFMP: A Benchmark for Explainable Fine-Grained Abnormal Behavior Recognition on Medical Personal Protective Equipment

2024 · IEEE Transactions on Circuits and Systems for Video Technology

The proper use of medical personal protective equipment (MPPE) is critical for frontline healthcare workers (HCWs) to handle highly contagious diseases. Due to the complexity of PPE donning and doffing protocols, public health organizations typically …

Adaptive elite ant colony optimization for track planning in gravity-aided navigation with multi-feature fusion

2025 · Defence Technology

Autonomous Underwater Vehicle track planning is critical for maritime defense missions, particularly in signal-denied and stealth-sensitive environments. Gravity-aided inertial navigation systems (GAINS), as a passive and emission-free approach, offer strong potential for such missions. However, …

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

2017 · arXiv (Cornell University)

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose …

Word-Context Character Embeddings for Chinese Word Segmentation

2017

Neural parsers have benefited from automatically labeled data via dependencycontext word embeddings. We investigate training character embeddings on a word-based context in a similar way, showing that the simple method significantly improves state-of-the-art neural word …

Commonsense Knowledge Aware Conversation Generation with Graph Attention

2018

Commonsense knowledge is vital to many natural language processing tasks. In this paper, we present a novel open-domain conversation generation model to demonstrate how large-scale commonsense knowledge can facilitate language understanding and generation. Given a …

Generating Fluent Adversarial Examples for Natural Languages

2019

Efficiently building an adversarial attacker for natural language processing (NLP) tasks is a real challenge. Firstly, as the sentence space is discrete, it is difficult to make small perturbations along the direction of gradients. Secondly, …

Dynamically Fused Graph Network for Multi-hop Reasoning

2019

Text-based question answering (TBQA) has been studied extensively in recent years. Most existing approaches focus on finding the answer to a question within a single paragraph. However, many difficult questions require multiple supporting evidence from …

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose …

Generating Sentences from Disentangled Syntactic and Semantic Spaces

2019

Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model the syntactic information. In this …

Augmenting End-to-End Dialogue Systems With Commonsense Knowledge

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Building dialogue systems that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent is expected to respond to human utterances in an …

CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neural networks (RNNs). However, …

Unsupervised Paraphrasing by Simulated Annealing

2020

We propose UPSA, a novel approach that accomplishes Unsupervised Paraphrasing by Simulated Annealing. We model paraphrase generation as an optimization problem and propose a sophisticated objective function, involving semantic similarity, expression diversity, and language fluency …

Gemini: A Family of Highly Capable Multimodal Models

2023 · arXiv (Cornell University)

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging …