一个用于运行上下文主题建模的 Python 包。CTM 将上下文嵌入(例如 BERT)与主题模型结合,以获得连贯的主题。发表于 EACL 和 ACL 2021(Bianchi 等)。
neural-topic-models 开源项目推荐(15 个)
neural-topic-models 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 15
GitHub 共 15 个仓库,已全部展示OCTIS:比较主题模型很简单!一个用于优化和评估主题模型的 Python 包(已被 EACL2021 demo track 接收)
[ACL 2024 Demo] A Topic Modeling System Toolkit
[NeurIPS 2024] A Fast, Adaptive, Stable, and Transferable Topic Model
Papers of Neural Topic Models (NTMs)
Code for Effective Neural Topic Modeling with Embedding Clustering Regularization (ICML2023)
ACL Python package engineered for seamless topic modeling, topic evaluation, and topic visualization. Ideal for text analysis, natural language processing (NLP), and research in the social sciences, STREAM simplifies the extraction, interpretation, and visualization of topics from large, complex datasets.
Code for Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder (EMNLP2020).
Aligned Neural Topic Model (ANTM) for Exploring Evolving Topics: a dynamic neural topic model that uses document embeddings (data2vec) to compute clusters of semantically similar documents at different periods, and aligns document clusters to represent topic evolution.
Modeling Dynamic Topics in Chain-Free Fashion by Evolution-Tracking Contrastive Learning and Unassociated Word Exclusion (ACL 2024 Findings)
"Modeling electronic health record data using an end-to-end knowledge-graph-informed topic model" paper on Sci Rep (2022)
Code for On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling (AAAI 2024)
neural_topic_models
This repository is associated with the paper "Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling", accepted at EACL 2023.
Streamline AI prompting with persistent context management, versioning, and reuse across workflows.
关于这个话题
- 清单按 Star 数挑选该话题下最热门的 15 个项目,对应的话题主页见 https://github.com/topics/neural-topic-models。
- 该话题在 GitHub 上共有 15 个仓库, 这里呈现的是其中最具代表性的 15 个,不是全量列表。
- 星标与复刻数以 GitHub 上的实时数字为准。
- 当前 15 个项目累计 2862 Star,覆盖 2 种主要语言。
- 中文简介由本站编译整理,可点「查看原文」对照项目方提供的原始说明。