paper-with-me

Papers

Regularly varying representation for sentence embedding

2019-09-25 · Hamid Jalalzai, Pierre Colombo, Chloé Clavel, Eric Gaussier, Giovanna Varni, Emmanuel Vignon, Anne Sabourin

The dominant approaches to sentence representation in natural language rely on learning embeddings on massive corpuses. The obtained embeddings have desirable properties such as compositionality and distance preservation (sentences with similar meanings have similar representations). In this paper, we develop a novel method for learning an embedding enjoying a dilation invariance property. We propose two algorithms: Orthrus, a classification algorithm, constrains the distribution of the embedded variable to be regularly varying, i.e. multivariate heavy-tail. and uses Extreme Value Theory (EVT) to tackle the classification task on two separate regions: the tail and the bulk. Hydra, a text generation algorithm for dataset augmentation, leverages the invariance property of the embedding learnt by Orthrus to generate coherent sentences with controllable attribute, e.g. positive or negative sentiment. Numerical experiments on synthetic and real text data demonstrate the relevance of the proposed framework.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeSentenceSentence EmbeddingSentence-EmbeddingText Generation

Similar Papers 제목 키워드 기반

Grammatical information in BERT sentence embeddings as two-dimensional arrays

2023-12-15 · Vivi Nastase, Paola Merlo

Sentence embeddings induced with various transformer architectures encode much semantic and syntactic information in a distributed manner in a one-dimensional array. We investigate whether specific grammatical informatio…

Few-Shot LearningSentenceSentence Embeddings

Unsupervised Sentence-embeddings by Manifold Approximation and Projection

2021-02-07 · EACL 2021 2 · Subhradeep Kayal

The concept of unsupervised universal sentence encoders has gained traction recently, wherein pre-trained models generate effective task-agnostic fixed-dimensional representations for phrases, sentences and paragraphs. S…

SentenceSentence Embeddingstext-classificationText Classification+1

Comparative Study of Sentence Embeddings for Contextual Paraphrasing

2020-05-01 · LREC 2020 5 · Louisa Pragst, Wolfgang Minker, Stefan Ultes

Paraphrasing is an important aspect of natural-language generation that can produce more variety in the way specific content is presented. Traditionally, paraphrasing has been focused on finding different words that conv…

ClusteringSentenceSentence EmbeddingsText Generation

Representation of Ambiguity in Pre-Trained Sentence Embeddings

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

Pre-trained language models have been shown to be very effective for various NLP tasks. All of these models are trained on different datasets and often have different architectures. Simultaneously, various approaches for…

SentenceSentence Embeddings

CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising

2026-07-30 · Sina Heydari, Amirreza Abbasi, Mohsen Hooshmand, Majid Ramezani arxiv

Pre-trained language models have significantly improved sentence representation learning, yet their embedding remain sensitive to semantic preserving textual perturbations such as synonym substitution, masking and word d…

Representation Learning