SemCSE-Multi: Multifaceted and Decodable Embeddings for Aspect-Specific and Interpretable Scientific Domain Mapping
We propose SemCSE-Multi, a novel unsupervised framework for generating multifaceted embeddings of scientific abstracts, evaluated in the domains of invasion biology and medicine. These embeddings capture distinct, individually specifiable aspects in isolation, thus enabling fine-grained and controllable similarity assessments as well as adaptive, user-driven visualizations of scientific domains. Our approach relies on an unsupervised procedure that produces aspect-specific summarizing sentences and trains embedding models to map semantically related summaries to nearby positions in the embedding space. We then distill these aspect-specific embedding capabilities into a unified embedding model that directly predicts multiple aspect embeddings from a scientific abstract in a single, efficient forward pass. In addition, we introduce an embedding decoding pipeline that decodes embeddings back into natural language descriptions of their associated aspects. Notably, we show that this decoding remains effective even for unoccupied regions in low-dimensional visualizations, thus offering vastly improved interpretability in user-centric settings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of…
Contrastive LearningSemantic SimilaritySemantic Textual SimilaritySentence+1Rethinking ANN-based Retrieval: Multifaceted Learnable Index for Large-scale Recommendation System
Approximate nearest neighbor (ANN) search is widely used in the retrieval stage of large-scale recommendation systems. In this stage, candidate items are indexed using their learned embedding vectors, and ANN search is e…
Recommendation SystemsMultifaceted Domain-Specific Document Embeddings
Current document embeddings require large training corpora but fail to learn high-quality representations when confronted with a small number of domain-specific documents and rare terms. Further, they transform each docu…
Document EmbeddingKnowledge GraphsAnalyzing and Improving Speaker Similarity Assessment for Speech Synthesis
Modeling voice identity is challenging due to its multifaceted nature. In generative speech systems, identity is often assessed using automatic speaker verification (ASV) embeddings, designed for discrimination rather th…
Speaker VerificationSpeech SynthesisCommonality and Individuality! Integrating Humor Commonality with Speaker Individuality for Humor Recognition
Humor recognition aims to identify whether a specific speaker's text is humorous. Current methods for humor recognition mainly suffer from two limitations: (1) they solely focus on one aspect of humor commonalities, igno…