Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation
By Kellie Webster, Emily Pitler. 2020
5 citations recorded by the source corpus.
Machine translation systems with inadequate document understanding can make errors when translating dropped or neutral pronouns into languages with gendered pronouns (e.g., English). Predicting the underlying gender of these pronouns is difficult since it is not marked textually and must instead be inferred from coreferent mentions in the context. We propose a novel cross-lingual pivoting technique for automatically producing high-quality gender labels, and show that this data can be used to fine-tune a BERT classifier with 92% F1 for Spanish dropped feminine pronouns, compared with 30-51% for neural machine translation models and 54-71% for a non-fine-tuned BERT model. We augment a neural machine translation model with labels from our classifier to improve pronoun translation, while still having parallelizable translation models that translate a sentence at a time.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Graham Neubig
- Mohit Bansal
- Yejin Choi
- Quoc V. Le
- Luke S. Zettlemoyer
- Richard Socher
- Caiming Xiong
- Kyunghyun Cho
Citations in the corpus
- PaLM: Scaling Language Modeling with Pathways (2022, background): “Coreference resolution is an important linguistic capability for language systems such as question answering, summarization, and translation (Stanovsky et al., 2019; Webster & Pitler, 2020).”
- GLaM: Efficient Scaling of Language Models with Mixture-of-Experts (2021, background): “Coreference resolution is a capability that many applications require to perform well, including machine translation (Stanovsky et al., 2019; Webster & Pitler, 2020) and question answering (Lamm et al., 2020).”