paper-with-me

홈 › Papers

Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases

2022-07-26 · Sławomir Dadas

Sentence embeddings are commonly used in text clustering and semantic retrieval tasks. State-of-the-art sentence representation methods are based on artificial neural networks fine-tuned on large collections of manually labeled sentence pairs. Sufficient amount of annotated data is available for high-resource languages such as English or Chinese. In less popular languages, multilingual models have to be used, which offer lower performance. In this publication, we address this problem by proposing a method for training effective language-specific sentence encoders without manually labeled data. Our approach is to automatically construct a dataset of paraphrase pairs from sentence-aligned bilingual text corpora. We then use the collected data to fine-tune a Transformer language model with an additional recurrent pooling layer. Our sentence encoder can be trained in less than a day on a single graphics card, achieving high performance on a diverse set of sentence-level tasks. We evaluate our method on eight linguistic tasks in Polish, comparing it with the best available multilingual sentence encoders.

📄 PDF Abstract BibTeX arXiv:2207.12759

Code (1)

sdadas/polish-sentence-evaluation 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingRetrievalSemantic RetrievalSentenceSentence EmbeddingsText Clustering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Fake Sentence Detection as a Training Task for Sentence Encoding

2018-08-11 · ICLR 2019 5 · Viresh Ranjan, Heeyoung Kwon, Niranjan Balasubramanian, Minh Hoai

Sentence encoders are typically trained on language modeling tasks with large unlabeled datasets. While these encoders achieve state-of-the-art results on many sentence-level tasks, they are difficult to train with long …

Binary ClassificationLanguage ModelingLanguage ModellingSentence

Fake Sentence Detection as a Training Task for Sentence Encoding

2018-05-23 · Anonymous

Sentence encoders are typically trained on language modeling tasks which enable them to use large unlabeled datasets. While these models achieve state-of-the-art results on many sentence-level tasks, they are difficult …

Binary ClassificationLanguage ModelingLanguage ModellingSentence

Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment

2024-07-20 · Yongxin Huang, Kexin Wang, Goran Glavaš, Iryna Gurevych

Multilingual sentence encoders are commonly obtained by training multilingual language models to map sentences from different languages into a shared semantic space. As such, they are subject to curse of multilinguality,…

Contrastive LearningMultiple-choiceSentenceSentence Embeddings+1

Ranking-Enhanced Unsupervised Sentence Representation Learning

2022-09-09 · Yeon Seonwoo, Guoyin Wang, Changmin Seo, Sajal Choudhary 외

Unsupervised sentence representation learning has progressed through contrastive learning and data augmentation methods such as dropout masking. Despite this progress, sentence encoders are still limited to using only an…

Contrastive LearningData AugmentationRepresentation LearningSemantic Similarity+4

DisSent: Sentence Representation Learning from Explicit Discourse Relations

2017-10-12 · Allen Nie, Erin D. Bennett, Noah D. Goodman

Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation …

Dependency ParsingNatural Language UnderstandingRelationRelation Prediction+3