K

Keyphrase Mpnet V1

Developed by uclanlp
A sentence transformer model optimized for phrases, mapping phrases into a 768-dimensional dense vector space, suitable for tasks like clustering or semantic search.
Downloads 4,278
Release Time : 5/8/2023

Model Overview

This model is based on sentence-transformers/all-mpnet-base-v2 and fine-tuned using the SimCSE method on 1 million keyphrase data entries, primarily used for evaluating semantic-based keyphrase model metrics.

Model Features

Phrase Optimization
Specifically optimized for phrases, better capturing phrase-level semantics compared to general sentence embedding models.
SimCSE Fine-tuning
Fine-tuned using the SimCSE method on 1 million keyphrase data entries to enhance semantic representation quality.
Multi-domain Applicability
Training data covers multiple domains including science, news, online forums, and web pages, ensuring broad applicability.

Model Capabilities

Phrase Vectorization
Semantic Similarity Calculation
Keyphrase Clustering
Semantic Search

Use Cases

Academic Research
Keyphrase Evaluation
Used to compute semantic-based keyphrase model evaluation metrics.
Served as an evaluation benchmark in the KPEval paper.
Information Retrieval
Semantic Search
Maps query phrases and document phrases into the same vector space for similarity matching.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase