Formality Style Transfer with Shared Latent Space

2020-12-01 · COLING 2020 8 · Yunli Wang, Yu Wu, Lili Mou, Zhoujun Li, WenHan Chao

Conventional approaches for formality style transfer borrow models from neural machine translation, which typically requires massive parallel data for training. However, the dataset for formality style transfer is considerably smaller than translation corpora. Moreover, we observe that informal and formal sentences closely resemble each other, which is different from the translation task where two languages have different vocabularies and grammars. In this paper, we present a new approach, Sequence-to-Sequence with Shared Latent Space (S2S-SLS), for formality style transfer, where we propose two auxiliary losses and adopt joint training of bi-directional transfer and auto-encoding. Experimental results show that S2S-SLS (with either RNN or Transformer architectures) consistently outperforms baselines in various settings, especially when we have limited data.

📄 PDF Abstract BibTeX

Code (1)

jimth001/formality_style_transfer_with_shared_latent_space 공식 구현 tf

Tasks

Formality Style Transfer Machine Translation Style Transfer Translation

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Position-Wise Feed-Forward Layer 설명 없음

Residual Connection 설명 없음

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Multi-Head Attention 설명 없음

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 $x$…

Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer

2021-08-01 · ACL 2021 5 · Sharmila Reddy Nangi, Niyati Chhaya, Sopan Khosla, Nikhil Kaushik 외

Disentanglement of latent representations into content and style spaces has been a commonly employed method for unsupervised text style transfer. These techniques aim to learn the disentangled representations and tweak t…

Attribute counterfactual Disentanglement Sentence+3

Formality Style Transfer with Hybrid Textual Annotations

2019-03-15 · Ruochen Xu, Tao Ge, Furu Wei

Formality style transformation is the task of modifying the formality of a given sentence without changing its content. Its challenge is the lack of large-scale sentence-aligned parallel data. In this paper, we propose a…

Formality Style Transfer Sentence Style Transfer Text Style Transfer+1

Multi-Task Neural Models for Translating Between Styles Within and Across Languages

2018-06-12 · COLING 2018 8 · Xing Niu, Sudha Rao, Marine Carpuat

Generating natural language requires conveying content in an appropriate style. We explore two related tasks on generating text of varying formality: monolingual formality transfer and formality-sensitive machine transla…

Machine Translation Multi-Task Learning Translation

Parallel Data Augmentation for Formality Style Transfer

2020-05-14 · ACL 2020 6 · Yi Zhang, Tao Ge, Xu sun

The main barrier to progress in the task of Formality Style Transfer is the inadequacy of training data. In this paper, we study how to augment parallel data and propose novel and simple data augmentation methods for thi…

Data Augmentation Formality Style Transfer Sentence Style Transfer

Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer

2021-10-20 · EMNLP 2021 11 · Eleftheria Briakou, Sweta Agrawal, Joel Tetreault, Marine Carpuat

While the field of style transfer (ST) has been growing rapidly, it has been hampered by a lack of standardized practices for automatic evaluation. In this paper, we evaluate leading ST automatic metrics on the oft-resea…

Formality Style Transfer Style Transfer