Papers with cached representations
Sequence Shortening for Context-Aware Machine Translation (2024.findings-eacl)
Copied to clipboard
| Challenge: | Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context. |
| Approach: | They propose to use latent representation of source sentence as context in a multi-encoder architecture to achieve higher accuracy on contrastive datasets. |
| Outcome: | The proposed architectures achieve comparable BLEU and COMET scores on contrastive datasets and comparable accuracies on the single- and multi-encoder approaches. |
Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks (2025.coling-main)
Copied to clipboard
| Challenge: | Existing encoders that encode incremented inputs have to re-encode the whole text to obtain the encoding of the extended input. |
| Approach: | They propose an efficient encoder dedicated for faster encoding of incremented input . it takes only added input as input but attends to cached representations of original input a lower layer . |
| Outcome: | The proposed encoder achieves 6.2x speedup over current encoders . it takes only added input as input but attends to cached representations of original input . |