mlsanityData to 7 Oct 2026

Cross-lingual Contextualized Topic Models with Zero-shot Learning

arXiv 2004.07737 ↗First posted 16 Apr 2020cs.CLcited by 66

Not on the map. Why?

Abstract (arXiv)

Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to be either single-language or suffer from a huge, but extremely sparse vocabulary. Both issues can be addressed by transfer learning. In this paper, we introduce a zero-shot cross-lingual topic model. Our model learns topics on one language (here, English), and predicts them for unseen documents in different languages (here, Italian, French, German, and Portuguese). We evaluate the quality of the topic predictions for the same document in different languages. Our results show that the transferred topics are coherent and stable across languages, which suggests exciting future research directions.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 13; 2023: 16; 2024: 12; 2025: 19; 2026: 5.

66 papers.

Sort:

By area:

  1. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 779
  2. 2022Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topicscited by 35
  3. 2023InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modelingcited by 24
  4. 2023Prompting Large Language Models for Topic Modelingcited by 24
  5. 2024A Survey on Neural Topic Models: Methods, Applications, and Challengescited by 18
  6. 2023Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modelingcited by 16
  7. 2023DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLMcited by 16
  8. 2022Are Neural Topic Models Broken?cited by 11
  9. 2022Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Mediacited by 10
  10. 2024NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularizationcited by 9
  11. 2021Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic Modelingcited by 8
  12. 2024Semantic-Driven Topic Modeling Using Transformer-Based Embeddings and Clustering Algorithmscited by 8
38 more
  1. 2023CWTM: Leveraging Contextualized Word Embeddings from BERT for Neural Topic Modelingcited by 7
  2. 2025Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoderscited by 7
  3. 2022Multilingual and Multimodal Topic Modelling with Pretrained Embeddingscited by 6
  4. 2022Unsupervised Opinion Summarization Using Approximate Geodesicscited by 5
  5. 2023Diversity-Aware Coherence Loss for Improving Neural Topic Modelscited by 5
  6. 2023PromptMTopic: Unsupervised Multimodal Topic Modeling of Memes using Large Language Modelscited by 5
  7. 2024Neural Multimodal Topic Modeling: A Comprehensive Evaluationcited by 5
  8. 2025Labeling Free-text Data using Language Model Ensemblescited by 5
  9. 2024GINopic: Topic Modeling with Graph Isomorphism Networkcited by 4
  10. 2025Bridging the Evaluation Gap: Leveraging Large Language Models for Topic Model Evaluationcited by 4
  11. 2025CEMTM: Contextual Embedding-based Multimodal Topic Modelingcited by 4
  12. 2022Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per classcited by 3
  13. 2024Refining Dimensions for Improving Clustering-based Cross-lingual Topic Modelscited by 3
  14. 2025XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignmentscited by 3
  15. 2025Sparse Autoencoders are Topic Modelscited by 3
  16. 2023MMT: A Multilingual and Multi-Topic Indian Social Media Datasetcited by 2
  17. 2023Bridging Nations: Quantifying the Role of Multilinguals in Communication on Social Mediacited by 2
  18. 2024Context is Key(NMF): Modelling Topical Information Dynamics in Chinese Diaspora Mediacited by 2
  19. 2025Semantic-Driven Topic Modeling for Analyzing Creativity in Virtual Brainstormingcited by 2
  20. 2022Twitter-Demographer: A Flow-based Tool to Enrich Twitter Datacited by 1
  21. 2022TSM: Measuring the Enticement of Honeyfiles with Natural Language Processingcited by 1
  22. 2022ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholdscited by 1
  23. 2023Characterizing Financial Market Coverage using Artificial Intelligencecited by 1
  24. 2023Improving Neural Topic Models with Wasserstein Knowledge Distillationcited by 1
  25. 2023Topics in the Haystack: Extracting and Evaluating Topics beyond Coherencecited by 1
  26. 2023Reinforcement Learning for Topic Modelscited by 1
  27. 2023Towards Generalising Neural Topical Representationscited by 1
  28. 2024Probabilistic Topic Modelling with Transformer Representationscited by 1
  29. 2024GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarizationcited by 1
  30. 2024Multilingual Topic Classification in X: Dataset and Analysiscited by 1
  31. 2024Tethering Broken Themes: Aligning Neural Topic Models with Labels and Authorscited by 1
  32. 2025Recommending the right academic programs: An interest mining approach using BERTopiccited by 1
  33. 2025S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modelingcited by 1
  34. 2025Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Mediacited by 1
  35. 2025Toward Purpose-oriented Topic Model Evaluation enabled by Large Language Modelscited by 1
  36. 2026LLM-XTM: Enhancing Cross-Lingual Topic Models with Large Language Modelscited by 1
  37. 2022One Configuration to Rule Them All? Towards Hyperparameter Transfer in Topic Models using Multi-Objective Bayesian Optimizationcited by 0
  38. 2022Automatic Scene-based Topic Channel Construction System for E-Commercecited by 0

50 most cited of 66 All 66 (JSON)