Jun Zhao

Study on the Application of Cognitive Apprenticeship in English Audio-visual Teaching in Colleges and Universities

2016

English audio-visual teaching uses multimedia to assist teaching, and creates English learning space in classroom teaching. With sufficient communication between teachers and students, English teachers guide students to change traditional learning modes, take an active …

Exploring supersymmetry with machine learning

2017 · arXiv (Cornell University)

Investigation of well-motivated parameter space in the theories of Beyond the Standard Model (BSM) plays an important role in new physics discoveries. However, a large-scale exploration of models with multi-parameter or equivalent solutions with a …

High Throughput Implementation of SMS4 on FPGA

2019 · IEEE Access

The SMS4 algorithm is a block cipher algorithm, which has the characteristics of high security and easy implementation. However, the optimization and implementation schemes proposed for FPGA platform currently use multi-channel parallel and pipelined architectures …

End-to-End Neural Ranking for eCommerce Product Search: an Application of Task Models and Textual Embeddings.

2018

We consider the problem of retrieving and ranking items in an eCommerce catalog, often called SKUs, in order of relevance to a user-issued query. The input data for the ranking are the texts of the …

Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network

2019

Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, Shengping Liu. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

An Analysis of Blockchain Consistency in Asynchronous Networks: Deriving a Neat Bound

2019 · arXiv (Cornell University)

Formal analyses of blockchain protocols have received much attention recently. Consistency results of Nakamoto's blockchain protocol are often expressed in a quantity $c$, which denotes the expected number of network delays before some block is …

Adaptive Differentially Private Data Stream Publishing in Spatio-temporal Monitoring of IoT

2019

Spatio-temporal monitoring of the Internet of Things (IoT) has enabled the development and proliferation of third-party computing services by extensively exploiting the massive amount of sensing data. In particular, continuously generated data stream are monitored …

Incremental Event Detection via Knowledge Consolidation Networks

2020

Conventional approaches to event detection usually require a fixed set of pre-defined event types. Such a requirement is often challenged in real-world applications, as new events continually occur. Due to huge computation cost and storage …

Effectiveness evaluation of smart equipment support information system based on Entropy-Revised G1 method

2021 · Journal of Physics Conference Series

Focusing on the complexity of the structure and the diversification of indicators in the equipment support information system, a combination weighting method was proposed to evaluate the system effectiveness. Firstly, based on the working principle …

LLaMA Beyond English: An Empirical Study on Language Capability Transfer

2024 · arXiv (Cornell University)

In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are pretrained on English-dominant …

Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning

2024

Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Daojian Zeng, Kang Liu, Jun Zhao. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

PGDiffSeg: Prior-Guided Denoising Diffusion Model with Parameter-Shared Attention for Breast Cancer Segmentation

2024 · arXiv (Cornell University)

Early detection through imaging and accurate diagnosis is crucial in mitigating the high mortality rate associated with breast cancer. However, locating tumors from low-resolution and high-noise medical images is extremely challenging. Therefore, this paper proposes …

Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

In this paper, we propose Neural-Symbolic Collaborative Distillation (NesyCD), a novel knowledge distillation method for learning the complex reasoning abilities of Large Language Models (LLMs, e.g., \textgreater 13B). We argue that complex reasoning tasks are …

Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks

2015

Two problems arise when using distant supervision for relation extraction. First, in this method, an already existing knowledge base is heuristically aligned to texts, and the alignment results are treated as labeled data. However, the …

Learning Continuous Word Embedding with Metadata for Question Retrieval in Community Question Answering

2015

Community question answering (cQA) has become an important issue due to the popularity of cQA archives on the web. This paper is concerned with the problem of question retrieval. Question retrieval in cQA archives aims …

Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions

2017 · Proceedings of the AAAI Conference on Artificial Intelligence

Distant supervision for relation extraction is an efficient method to scale relation extraction to very large corpora which contains thousands of relations. However, the existing approaches have flaws on selecting valid instances and lack of …

An End-to-End Model for Question Answering over Knowledge Base with Cross-Attention Combining Global Knowledge

2017

With the rapid growth of knowledge bases (KBs) on the web, how to take full advantage of them becomes increasingly important. Question answering over knowledge base (KB-QA) is one of the promising approaches to access …

Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms

2017

This paper tackles the task of event detection (ED), which involves identifying and categorizing events. We argue that arguments provide significant clues to this task, but they are either completely ignored or exploited in an …

Generating Natural Answers by Incorporating Copying and Retrieving Mechanisms in Sequence-to-Sequence Learning

2017

Generating answer with natural language sentence is very important in real-world question answering systems, which needs to obtain a right answer as well as a coherent natural response.

Large Scaled Relation Extraction With Reinforcement Learning

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Sentence relation extraction aims to extract relational facts from sentences, which is an important task in natural language processing field. Previous models rely on the manually labeled supervised dataset. However, the human annotation is costly …

Extracting Relational Facts by an End-to-End Neural Model with Copy Mechanism

2018

The relational facts in sentences are often complicated. Different relational triplets may have overlaps in a sentence. We divided the sentences into three types according to triplet overlap degree, including Normal, EntityPairOverlap and SingleEn-tiyOverlap. Existing …

Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-level Attention Mechanisms

2018

Traditional approaches to the task of ACE event detection primarily regard multiple events in one sentence as independent ones and recognize them separately by using sentence-level information. However, events in one sentence are usually interdependent …

Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism

2018

Named entity recognition (NER) is an important task in natural language processing area, which needs to determine entities boundaries and classify them into pre-defined categories. For Chinese NER task, there is only a very small …

IntentGC

2019

The remarkable progress of network embedding has led to state-of-the-art algorithms in recommendation. However, the sparsity of user-item interactions (i.e., explicit preferences) on websites remains a big challenge for predicting users' behaviors. Although research efforts …

Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning

2019

Xiangrong Zeng, Shizhu He, Daojian Zeng, Kang Liu, Shengping Liu, Jun Zhao. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). …

Knowledge Enhanced Event Causality Identification with Mention Masking Generalizations

2020

Identifying causal relations of events is a crucial language understanding task. Despite many efforts for this task, existing methods lack the ability to adopt background knowledge, and they typically generalize poorly to new, previously unseen …