paper-with-me

Short Text Clustering

8개 벤치마크 · 논문 39편 · 이 태스크의 논문 보기 →

Benchmarks

Stackoverflow

결과 5개

Biomedical

결과 4개

Searchsnippets

결과 4개

AG News

결과 1개

GoogleNews-S

결과 1개

GoogleNews-T

결과 1개

GoogleNews-TS

결과 1개

Tweet

결과 1개

Most implemented

Papers

Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering

2026-07-12 · Zhihao Yao, Yuxuan Gu, Jixuan Yin, Bo Li arxiv

Pseudo-labeling based on Optimal Transport (OT) has become an effective mechanism for enhancing short text clustering. Existing OT methods are short in modeling semantic consistencies between samples, which may assign di…

Short Text Clustering

LUMI: Unsupervised Intent Clustering with Multiple Pseudo-Labels

2025-10-16 · I-Fan Lin, Faegheh Hasibi, Suzan Verberne arxiv

In this paper, we propose an intuitive, training-free and label-free method for intent clustering in conversational search. Current approaches to short text clustering use LLM-generated pseudo-labels to enrich text repre…

Short Text Clustering

LLMs Enable Bag-of-Texts Representations for Short-Text Clustering

2025-10-08 · I-Fan Lin, Faegheh Hasibi, Suzan Verberne arxiv

In this paper, we propose a training-free method for unsupervised short text clustering that relies less on careful selection of embedders than other methods. In customer-facing chatbots, companies are dealing with large…

Short Text Clustering

Normalisation of SWIFT Message Counterparties with Feature Extraction and Clustering

2025-08-24 · Thanasis Schoinas, Benjamin Guinard, Diba Esbati, Richard Chalk arxiv

Short text clustering is a known use case in the text analytics community. When the structure and content falls in the natural language domain e.g. Twitter posts or instant messages, then natural language techniques can …

Short Text Clustering

An Enhanced Model-based Approach for Short Text Clustering

2025-07-18 · Enhao Cheng, Shoujia Zhang, Jianhua Yin, Xuemeng Song 외 arxiv

Short text clustering has become increasingly important with the popularity of social media like Twitter, Google+, and Facebook. Existing methods can be broadly categorized into two paradigms: topic model-based approache…

Representation LearningShort Text Clustering

Moving Past Single Metrics: Exploring Short-Text Clustering Across Multiple Resolutions

2025-02-24 · Justin Miller, Tristram Alexander

Cluster number is typically a parameter selected at the outset in clustering problems, and while impactful, the choice can often be difficult to justify. Inspired by bioinformatics, this study examines how the nature of …

ClusteringInformativenessShort Text ClusteringText Clustering

전체 39편 보기 →