paper-with-me

Papers

Improving Contextualized Topic Models with Negative Sampling

2023-03-27 · Suman Adhya, Avishek Lahiri, Debarshi Kumar Sanyal, Partha Pratim Das

Topic modeling has emerged as a dominant method for exploring large document collections. Recent approaches to topic modeling use large contextualized language models and variational autoencoders. In this paper, we propose a negative sampling mechanism for a contextualized topic model to improve the quality of the generated topics. In particular, during model training, we perturb the generated document-topic vector and use a triplet loss to encourage the document reconstructed from the correct document-topic vector to be similar to the input document and dissimilar to the document reconstructed from the perturbed vector. Experiments for different topic counts on three publicly available benchmark datasets show that in most cases, our approach leads to an increase in topic coherence over that of the baselines. Our model also achieves very high topic diversity.

📄 PDF Abstract BibTeX arXiv:2303.14951

Code (2)

adhyasuman/ctmneg 공식 구현 pytorch
adhyasuman/ntms_dropout_analysis pytorch

Tasks

DiversityTopic ModelsTriplet

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Evaluating Negative Sampling Approaches for Neural Topic Models

2025-03-23 · Suman Adhya, Avishek Lahiri, Debarshi Kumar Sanyal, Partha Pratim Das

Negative sampling has emerged as an effective technique that enables deep learning models to learn better representations by introducing the paradigm of learn-to-compare. The goal of this approach is to add robustness to…

Document ClassificationTopic Models

Refining Dimensions for Improving Clustering-based Cross-lingual Topic Models

2024-12-17 · Chia-Hsuan Chang, Tien-Yuan Huang, Yi-Hang Tsai, Chia-Ming Chang 외

Recent works in clustering-based topic models perform well in monolingual topic identification by introducing a pipeline to cluster the contextualized representations. However, the pipeline is suboptimal in identifying t…

ClusteringTopic Models

CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modeling

2023-05-16 · Zheng Fang, Yulan He, Rob Procter

Most existing topic models rely on bag-of-words (BOW) representation, which limits their ability to capture word order information and leads to challenges with out-of-vocabulary (OOV) words in new documents. Contextualiz…

Document ClassificationLanguage ModellingNatural Language UnderstandingNER+3

Short Text Topic Modeling with Topic Distribution Quantization and Negative Sampling Decoder

2020-11-01 · EMNLP 2020 11 · Xiaobao Wu, Chunping Li, Yan Zhu, Yishu Miao

Topic models have been prevailing for many years on discovering latent semantics while modeling long documents. However, for short texts they generally suffer from data sparsity because of extremely limited word co-occur…

DecoderQuantizationTopic Models

Topic Modeling with Contextualized Word Representation Clusters

2020-10-23 · Laure Thompson, David Mimno

Clustering token-level contextualized word representations produces output that shares many similarities with topic models for English text collections. Unlike clusterings of vocabulary-level word embeddings, the resulti…

ClusteringTopic ModelsWord Embeddings