Abstract | ||
---|---|---|
This paper investigates the problem of learning cross-lingual representations in a contextual space. We propose Cross-Lingual BERT Transformation (CLBT), a simple and efficient approach to generate cross-lingual contextualized word embeddings based on publicly available pre-trained BERT models (Devlin et al., 2018). In this approach, a linear transformation is learned from contextual word alignments to align the contextualized embeddings independently trained in different languages. We demonstrate the effectiveness of this approach on zero-shot cross-lingual transfer parsing. Experiments show that our embeddings substantially outperform the previous state-of-the-art that uses static embeddings. We further compare our approach with XLM (Lample and Conneau, 2019), a recently proposed cross-lingual language model trained with massive parallel data, and achieve highly competitive results. |
Year | DOI | Venue |
---|---|---|
2019 | 10.18653/v1/D19-1575 | EMNLP/IJCNLP (1) |
DocType | Volume | Citations |
Conference | D19-1 | 1 |
PageRank | References | Authors |
0.35 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuxuan Wang | 1 | 144 | 12.04 |
Wanxiang Che | 2 | 711 | 66.39 |
Jiang Guo | 3 | 33 | 5.74 |
Yijia Liu | 4 | 49 | 7.34 |
Ting Liu | 5 | 2735 | 232.31 |