paper-with-me

홈 › Papers

Sentence-level Privacy for Document Embeddings

2022-05-10 · ACL 2022 5 · Casey Meehan, Khalil Mrini, Kamalika Chaudhuri

User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their data. In this work, we propose SentDP: pure local differential privacy at the sentence level for a single user document. We propose a novel technique, DeepCandidate, that combines concepts from robust statistics and language modeling to produce high-dimensional, general-purpose $\epsilon$-SentDP document embeddings. This guarantees that any single sentence in a document can be substituted with any other sentence while keeping the embedding $\epsilon$-indistinguishable. Our experiments indicate that these private document embeddings are useful for downstream tasks like sentiment analysis and topic classification and even outperform baseline methods with weaker guarantees like word-level Metric DP.

📄 PDF Abstract BibTeX arXiv:2205.04605

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingSentenceSentiment AnalysisTopic Classification

Similar Papers 제목 키워드 기반

Sentence-level Privacy for Document Embeddings

2021-11-16 · ACL ARR November 2021 11 · Anonymous

User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their data. In this work we propose SentDP, pure …

Language ModelingLanguage ModellingSentenceSentiment Analysis+1

Hierarchical Document Encoder for Parallel Corpus Mining

2019-06-20 · WS 2019 8 · Mandy Guo, Yinfei Yang, Keith Stevens, Daniel Cer 외

We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual se…

Parallel Corpus MiningSentenceSentence EmbeddingSentence-Embedding+1

Neural Attention-Aware Hierarchical Topic Model

2021-10-14 · EMNLP 2021 11 · Yuan Jin, He Zhao, Ming Liu, Lan Du 외

Neural topic models (NTMs) apply deep neural networks to topic modelling. Despite their success, NTMs generally ignore two important aspects: (1) only document-level word count information is utilized for the training, w…

modelSentenceTopic Models

Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings?

2023-04-28 · Sonal Sannigrahi, Josef van Genabith, Cristina Espana-Bonet

Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results in various tasks requiring semantic …

SentenceSentence EmbeddingsWord Embeddings

Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation

2024-07-26 · Doan Nam Long Vu, Timour Igamberdiev, Ivan Habernal

Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual data points during training is becoming increasingly popular in NLP. However, the choice of granularity at which DP is applied is …

Machine TranslationNMTSentence