codertimo / paper-log

읽어야 하는 논문들을 관리하고, 읽은 논문들의 기록을 남기는 공간
31 stars 5 forks source link

Mask and Infill: Applying Masked Language Model to Sentiment Transfer #13

Open codertimo opened 4 years ago

codertimo commented 4 years ago

어떤 내용의 논문인가요? 👋

Abstract (요약) 🕵🏻‍♂️

This paper focuses on the task of sentiment transfer on non-parallel text, which modifies sentiment attributes (e.g., positive or negative) of sentences while preserving their attribute-independent content. Due to the limited capability of RNNbased encoder-decoder structure to capture deep and long-range dependencies among words, previous works can hardly generate satisfactory sentences from scratch. When humans convert the sentiment attribute of a sentence, a simple but effective approach is to only replace the original sentimental tokens in the sentence with target sentimental expressions, instead of building a new sentence from scratch. Such a process is very similar to the task of Text Infilling or Cloze, which could be handled by a deep bidirectional Masked Language Model (e.g. BERT). So we propose a two step approach "Mask and Infill". In the mask step, we separate style from content by masking the positions of sentimental tokens. In the infill step, we retrofit MLM to Attribute Conditional MLM, to infill the masked positions by predicting words or phrases conditioned on the context and target sentiment. We evaluate our model on two review datasets with quantitative, qualitative, and human evaluations. Experimental results demonstrate that our models improve state-of-the-art performance.

이 논문을 읽어서 무엇을 배울 수 있는지 알려주세요! 🤔

레퍼런스의 URL을 알려주세요! 🔗

https://arxiv.org/abs/1908.08039