While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set (sentence IDs) accounts for a significant performance gap among these algorithms. This feature set is also used by traditional alignment algorithms, such as IBM Model-1, which demonstrate similar performance to stateof- The-art embedding algorithms on a variety of benchmarks. Overall, we observe that different algorithmic approaches for utilizing the sentence ID feature space result in similar performance. This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account.
|Title of host publication||Long Papers - Continued|
|Publisher||Association for Computational Linguistics (ACL)|
|Number of pages||10|
|State||Published - 2017|
|Event||15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Valencia, Spain|
Duration: 3 Apr 2017 → 7 Apr 2017
|Name||15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference|
|Conference||15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017|
|Period||3/04/17 → 7/04/17|
Bibliographical notePublisher Copyright:
© 2017 Association for Computational Linguistics.