paper-with-me

Papers

Learning and Evaluating Sparse Interpretable Sentence Embeddings

2018-09-23 · WS 2018 11 · Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, Thomas Hofmann

Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased interpretability properties: to some degree, each dimension can be understood by a human and associated with a recognizable feature in the data. In this paper, we transfer this idea to sentence embeddings and explore several approaches to obtain a sparse representation. We further introduce a novel, quantitative and automated evaluation metric for sentence embedding interpretability, based on topic coherence methods. We observe an increase in interpretability compared to dense models, on a dataset of movie dialogs and on the scene descriptions from the MS COCO dataset.

📄 PDF Abstract BibTeX arXiv:1809.08621

Code (0)

등록된 구현이 없습니다.

Tasks

SentenceSentence EmbeddingSentence-EmbeddingSentence EmbeddingsWord Embeddings

Similar Papers 제목 키워드 기반

Finding Meaning in Embeddings: Concept Separation Curves

2026-04-23 · Paul Keuren, Marc Ponsen, Robert Ayoub Bagheri arxiv

Sentence embedding techniques aim to encode key concepts of a sentence's meaning in a vector space. However, the majority of evaluation approaches for sentence embedding quality rely on the use of additional classifiers …

Word Equations: Inherently Interpretable Sparse Word Embeddingsthrough Sparse Coding

2020-04-08 · Adly Templeton

Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where each dimension is inherently interpretable.…

Word Embeddings

Word Equations: Inherently Interpretable Sparse Word Embeddings through Sparse Coding

2021-11-01 · EMNLP (BlackboxNLP) 2021 11 · Adly Templeton

Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where each dimension is inherently interpretable.…

Word Embeddings

Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders

2026-06-19 · Wonseok Shin, Songkuk Kim arxiv

Dense sentence embeddings are fundamental to modern Retrieval-Augmented Generation (RAG) systems but suffer from a lack of interpretability due to feature superposition. This opacity hinders the alignment of retrieval pr…

Information Retrieval

SparseGAN: Sparse Generative Adversarial Network for Text Generation

2021-03-22 · Liping Yuan, Jiehang Zeng, Xiaoqing Zheng

It is still a challenging task to learn a neural text generation model under the framework of generative adversarial networks (GANs) since the entire training process is not differentiable. The existing training strategi…

Generative Adversarial NetworkSentenceText GenerationWord Embeddings