Search Results for author: Mengze Hong

Found 8 papers, 0 papers with code

Dialogue Language Model with Large-Scale Persona Data Engineering

no code implementations12 Dec 2024 Mengze Hong, Chen Zhang, Chaotao Chen, Rongzhong Lian, Di Jiang

Maintaining persona consistency is paramount in the application of open-domain dialogue systems, as exemplified by models like ChatGPT.

Diversity Language Modeling +1

Deconfounding Time Series Forecasting

no code implementations27 Oct 2024 Wentao Gao, Feiyu Yang, Mengze Hong, Xiaojing Du, Zechen Hu, Xiongren Chen, Ziqi Xu

Time series forecasting is a critical task in various domains, where accurate predictions can drive informed decision-making.

Decision Making Time Series +1

Expanding Chatbot Knowledge in Customer Service: Context-Aware Similar Question Generation Using Large Language Models

no code implementations16 Oct 2024 Mengze Hong, Yuanfeng Song, Di Jiang, Lu Wang, Zichang Guo, Chen Jason Zhang

To accommodate potential variations in how a customer's query may be expressed, it emerges as the favored solution to augment these QA pairs with similar questions that are possibly diverse while remaining semantic consistency.

Chatbot Diversity +3

Neural-Bayesian Program Learning for Few-shot Dialogue Intent Parsing

no code implementations8 Oct 2024 Mengze Hong, Di Jiang, Yuanfeng Song, Chen Jason Zhang

With the growing importance of customer service in contemporary business, recognizing the intents behind service dialogues has become essential for the strategic success of enterprises.

Feature Engineering Few-Shot Learning

Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting

no code implementations2 Oct 2024 Longyu Feng, Mengze Hong, Chen Jason Zhang

Batch prompting is a common technique in large language models (LLMs) used to process multiple inputs simultaneously, aiming to improve computational efficiency.

Computational Efficiency Few-Shot Learning

InfantCryNet: A Data-driven Framework for Intelligent Analysis of Infant Cries

no code implementations29 Sep 2024 Mengze Hong, Chen Jason Zhang, Lingxiao Yang, Yuanfeng Song, Di Jiang

Additionally, knowledge distillation and model quantization are applied to enhance model efficiency and reduce the model size, better supporting industrial deployment in mobile devices.

Knowledge Distillation Model Compression +2

Pairwise Judgment Formulation for Semantic Embedding Model in Web Search

no code implementations8 Aug 2024 Mengze Hong, Di Jiang, Wailing Ng, Zichang Guo, Chen Jason Zhang

Semantic Embedding Model (SEM), a neural network-based Siamese architecture, is gaining momentum in information retrieval and natural language processing.

Information Retrieval Learning-To-Rank

Cannot find the paper you are looking for? You can Submit a new open access paper.