mlsanityData to 14 Oct 2026

Learning a Formality-Aware Japanese Sentence Representation

arXiv 2301.07209 ↗First posted 17 Jan 2023cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

While the way intermediate representations are generated in encoder-decoder sequence-to-sequence models typically allow them to preserve the semantics of the input sentence, input features such as formality might be left out. On the other hand, downstream tasks such as translation would benefit from working with a sentence representation that preserves formality in addition to semantics, so as to generate sentences with the appropriate level of social formality -- the difference between speaking to a friend versus speaking with a supervisor. We propose a sequence-to-sequence method for learning a formality-aware representation for Japanese sentences, where sentence generation is conditioned on both the original representation of the input sentence, and a side constraint which guides the sentence representation towards preserving formality information. Additionally, we propose augmenting the sentence representation with a learned representation of formality which facilitates the extraction of formality in downstream tasks. We address the lack of formality-annotated parallel data by adapting previous works on procedural formality classification of Japanese sentences. Experimental results suggest that our techniques not only helps the decoder recover the formality of the input sentence, but also slightly improves the preservation of input sentence semantics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 17 Jan 2023.

Builds on

19 of 30 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  5. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 211
  6. 2020Deep Learning for Text Style Transfer: A Surveycited by 162
  7. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  8. 2018Towards Understanding Linear Word Analogiescited by 57
  9. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 52
  10. 2017A Deep Reinforcement Learning Chatbotcited by 36
  11. 2020Unsupervised Text Generation by Learning from Searchcited by 36
  12. 2021StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfercited by 34
7 more
  1. 2018Multi-Task Neural Models for Translating Between Styles Within and Across Languagescited by 28
  2. 2021Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfercited by 25
  3. 2020On Learning Text Style Transfer with Direct Rewardscited by 24
  4. 2021Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTcited by 21
  5. 2020Semi-supervised Formality Style Transfer using Language Model Discriminator and Mutual Information Maximizationcited by 19
  6. 2019Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translationcited by 7
  7. 2017English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructorcited by 1

Built on by

Not cited yet.