Papers with similarity

4 papers
StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion (2025.naacl-long)

Copied to clipboard

Challenge: Recent advances in text-to-speech (TTS) models have led to improvements in speaker prosody and voices modeling.
Approach: They propose an efficient zero-shot TTS model that leverages distilled time-varying style diffusion to capture diverse speaker identities and prosodies.
Outcome: The proposed model surpasses state-of-the-art models in both naturalness and similarity while reducing inference speed by 90%.
HG2Vec: Improved Word Embeddings from Dictionary and Thesaurus Based Heterogeneous Graph (2022.coling-1)

Copied to clipboard

Challenge: Existing models that learn word embeddings rely on a large corpus of data . however, these models require massive time and space for data pre-processing and training .
Approach: They propose a model that learns word embeddings utilizing only dictionaries and thesauri . they exploit a new context-focused loss model that models transitive relationships between word pairs .
Outcome: The proposed model reaches the state-of-art on multiple word similarity and relatedness benchmarks.
Rethinking Word Similarity: Semantic Similarity through Classification Confusion (2025.naacl-long)

Copied to clipboard

Challenge: Word similarity measures cannot capture context-dependent, asymmetrical, polysemous nature of semantic similarity.
Approach: They propose a new measure of similarity that reframes semantic similarity in terms of feature-based classification confusion.
Outcome: The proposed model is comparable to cosine similarity in matching human similarity judgments across several datasets and can measure similarity using predetermined features of interest.
AnlamVer: Semantic Model Evaluation Dataset for Turkish - Word Similarity and Relatedness (C18-1)

Copied to clipboard

Challenge: a dataset for semantic model evaluation for Turkish is not available for the language . a similarity and relatedness evaluation resource is needed for higher level tasks .
Approach: They propose a semantic model evaluation dataset for Turkish that evaluates word similarity and word relatedness tasks while discriminating those two relations from each other.
Outcome: The proposed dataset is designed to evaluate word similarity and word relatedness tasks in Turkish.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations