paper-with-me

Papers

Cosine Similarity of Multimodal Content Vectors for TV Programmes

2020-09-23 · Saba Nazir. Taner Cagali, Chris Newell, Mehrnoosh Sadrzadeh

Multimodal information originates from a variety of sources: audiovisual files, textual descriptions, and metadata. We show how one can represent the content encoded by each individual source using vectors, how to combine the vectors via middle and late fusion techniques, and how to compute the semantic similarities between the contents. Our vectorial representations are built from spectral features and Bags of Audio Words, for audio, LSI topics and Doc2vec embeddings for subtitles, and the categorical features, for metadata. We implement our model on a dataset of BBC TV programmes and evaluate the fused representations to provide recommendations. The late fused similarity matrices significantly improve the precision and diversity of recommendations.

📄 PDF Abstract BibTeX arXiv:2009.11129

Code (0)

등록된 구현이 없습니다.

Tasks

Diversity

Similar Papers 제목 키워드 기반

Is Cosine-Similarity of Embeddings Really About Similarity?

2024-03-08 · Harald Steck, Chaitanya Ekanadham, Nathan Kallus

Cosine-similarity is the cosine of the angle between two vectors, or equivalently the dot product between their normalizations. A popular application is to quantify semantic similarity between high-dimensional objects by…

Semantic SimilaritySemantic Textual Similarity

Correlation Coefficients and Semantic Textual Similarity

2019-05-19 · NAACL 2019 6 · Vitalii Zhelezniak, Aleksandar Savkov, April Shen, Nils Y. Hammerla

A large body of research into semantic textual similarity has focused on constructing state-of-the-art embeddings using sophisticated modelling, careful choice of learning signals and many clever tricks. By contrast, lit…

Semantic Textual SimilaritySentence

A Comparison of Semantic Similarity Methods for Maximum Human Interpretability

2019-10-21 · Pinky Sitikhu, Kritish Pahi, Pujan Thapa, Subarna Shakya

The inclusion of semantic information in any similarity measures improves the efficiency of the similarity measure and provides human interpretable results for further analysis. The similarity calculation method that foc…

Information RetrievalRetrievalSemantic SimilaritySemantic Textual Similarity

COS-Mix: Cosine Similarity and Distance Fusion for Improved Information Retrieval

2024-06-02 · Kush Juvekar, Anupam Purwar

This study proposes a novel hybrid retrieval strategy for Retrieval-Augmented Generation (RAG) that integrates cosine similarity and cosine distance measures to improve retrieval performance, particularly for sparse data…

Information RetrievalRAGRetrievalRetrieval-augmented Generation

Variance-Adjusted Cosine Distance as Similarity Metric

2025-02-04 · Satyajeet Sahoo, Jhareswar Maiti

Cosine similarity is a popular distance measure that measures the similarity between two vectors in the inner product space. It is widely used in many data classification algorithms like K-Nearest Neighbors, Clustering e…

valid