Mona Forsman — accepted AI-conference papers

2024

PromptStream: Self-Supervised News Story Discovery Using Topic-Aware Article Representations

Arezoo Hatefi, Anton Eklund, Mona Forsman

COLING 2024main

Given the importance of identifying and monitoring news stories within the continuous flow of news articles, this paper presents PromptStream, a novel method for unsupervised news story discovery. In order to identify coherent and comprehensive stories across the stream, it is crucial to create arti…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2022

Topic Modeling by Clustering Language Model Embeddings: Human Validation on an Industry Dataset

Anton Eklund, Mona Forsman

EMNLP 2022industry

Topic models are powerful tools to get an overview of large collections of text data, a situation that is prevalent in industry applications. A rising trend within topic modeling is to directly cluster dimension-reduced embeddings created with pretrained language models. It is difficult to evaluate…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗