Embedded Topic Models Enhanced by Wikification

2024-10-03 · Takashi Shibuya, Takehito Utsuro

Topic modeling analyzes a collection of documents to learn meaningful patterns of words. However, previous topic models consider only the spelling of words and do not take into consideration the homography of words. In this study, we incorporate the Wikipedia knowledge into a neural topic model to make it aware of named entities. We evaluate our method on two datasets, 1) news articles of \textit{New York Times} and 2) the AIDA-CoNLL dataset. Our experiments show that our method improves the performance of neural topic models in generalizability. Moreover, we analyze frequent terms in each topic and the temporal dependencies between topics to demonstrate that our entity-aware topic models can capture the time-series development of topics well.

📄 PDF Abstract BibTeX arXiv:2410.02441

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesTime SeriesTopic Models

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Towards Improving Dialogue Topic Tracking Performances with Wikification of Concept Mentions

2015-09-01 · WS 2015 9 · Seokhwan Kim, Rafael E. Banchs, Haizhou Li

Text Categorization

Concept Wikification for COVID-19

2020-12-01 · EMNLP (NLP-COVID19) 2020 12 · Panagiotis Lymperopoulos, Haoling Qiu, Bonan Min

Understanding scientific articles related to COVID-19 requires broad knowledge about concepts such as symptoms, diseases and medicine. Given the very large and ever-growing scientific articles related to COVID-19, it is …

Articles

DiffETM: Diffusion Process Enhanced Embedded Topic Model

2025-01-01 · Wei Shao, Mingyang Liu, Linqi Song

The embedded topic model (ETM) is a widely used approach that assumes the sampled document-topic distribution conforms to the logistic normal distribution for easier optimization. However, this assumption oversimplifies …

model

Fast End-to-End Wikification

2019-08-19 · Ilya Shnayderman, Liat Ein-Dor, Yosi Mass, Alon Halfon 외

Wikification of large corpora is beneficial for various NLP applications. Existing methods focus on quality performance rather than run-time, and are therefore non-feasible for large data. Here, we introduce RedW, a run-…

Wikification for Scriptio Continua

2016-05-01 · LREC 2016 5 · Yugo Murawaki, Shinsuke Mori

The fact that Japanese employs scriptio continua, or a writing system without spaces, complicates the first step of an NLP pipeline. Word segmentation is widely used in Japanese language processing, and lexical knowledge…

Segmentation