On the Effect of Word Order on Cross-lingual Sentiment Analysis
This addresses a specific bottleneck in cross-lingual NLP for sentiment analysis, but it is incremental as it builds on existing methods with limited language combinations.
The paper tackled the problem of word order differences hindering cross-lingual sentiment analysis by exploring reordering as a pre-processing step for English-Spanish and English-Catalan classification, finding that reordering helps models with CNNs more sensitive to local reorderings and RNNs benefiting from global reordering.
Current state-of-the-art models for sentiment analysis make use of word order either explicitly by pre-training on a language modeling objective or implicitly by using recurrent neural networks (RNNs) or convolutional networks (CNNs). This is a problem for cross-lingual models that use bilingual embeddings as features, as the difference in word order between source and target languages is not resolved. In this work, we explore reordering as a pre-processing step for sentence-level cross-lingual sentiment classification with two language combinations (English-Spanish, English-Catalan). We find that while reordering helps both models, CNNS are more sensitive to local reorderings, while global reordering benefits RNNs.