Papers with token-to-token interaction
Recurrent Attention for Neural Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent research questions the importance of dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns. |
| Approach: | They propose a novel mechanism to replace dot-product self-attention with a recurrent atteNtion mechanism that directly learns attention weights without token-to-token interaction. |
| Outcome: | The proposed model outperforms the Transformer model on translation tasks with fewer parameters and inference time. |
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Transformer architecture is composed of multi-head attention, which has been extensively analyzed. |
| Approach: | They extended the scope of the analysis of Transformers from solely the attention patterns to the whole attention block, i.e., multi-head attention, residual connection, and layer normalization. |
| Outcome: | The proposed method incorporates the whole attention block, i.e., multi-head attention, residual connection, and layer normalization into the analysis. |
SpanAlign: Sentence Alignment Method based on Cross-Language Span Prediction and ILP (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for automatic sentence alignment assume monotonic alignments, but they can handle non-monotonic alignments. |
| Approach: | They propose a method to automatically extract parallel sentences from noisy parallel documents by embeddings and encoding each source and target sentence. |
| Outcome: | The proposed method improves translation accuracy by 4.1 BLEU scores on English-Japanese . it can predict spans in target document from sentences in source document . |