Ge Li

Lightweight semantic service modelling for IoT: an environment-based approach

2016 · International Journal of Embedded Systems

Combining service-oriented architecture (SOA) with internet of things (IoT) has been paid more and more attentions for encapsulating the functionalities of heterogeneous devices as IoT services and enabling things to interact and communicate with each …

Deep code comment generation

2018

During software maintenance, code comments help developers comprehend programs and reduce additional time spent on reading and navigating source code. Unfortunately, these comments are often mismatched, missing or outdated in the software projects. Developers have …

Theoretical Proof that Auto-regressive Language Models Collapse when Real-world Data is a Finite Set

2024 · arXiv (Cornell University)

Auto-regressive language models (LMs) have been widely used to generate data in data-scarce domains to train new LMs, compensating for the scarcity of real-world data. Previous work experimentally found that LMs collapse when trained on …

LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding

2025 · arXiv (Cornell University)

Current advanced long-context language models offer great potential for real-world software engineering applications. However, progress in this critical domain remains hampered by a fundamental limitation: the absence of a rigorous evaluation framework for long code …

Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path

2015 · arXiv (Cornell University)

Relation classification is an important research arena in the field of natural language processing (NLP). In this paper, we present SDP-LSTM, a novel neural network to classify the relation of two entities in a sentence. …

Natural Language Inference by Tree-Based Convolution and Heuristic Matching

2016

In this paper, we propose the TBCNNpair model to recognize entailment and contradiction between two sentences. In our model, a tree-based convolutional neural network (TBCNN) captures sentencelevel semantics; then heuristic matching layers like concatenation, element-wise …

Sequence to Backward and Forward Sequences: A Content-Introducing\n Approach to Generative Short-Text Conversation

2016 · arXiv (Cornell University)

Using neural networks to generate replies in human-computer dialogue systems\nis attracting increasing attention over the past few years. However, the\nperformance is not satisfactory: the neural network tends to generate safe,\nuniversally relevant replies which carry little …