A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments
This work provides insights for researchers in natural language processing by highlighting incremental improvements in baseline methods for cross-lingual embeddings.
The paper tackles the problem of understanding performance differences in cross-lingual word embedding algorithms by identifying that the use of sentence IDs is a key feature, showing that traditional alignment algorithms like IBM Model-1 achieve similar performance to state-of-the-art methods on benchmarks.
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 state-of-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.