State Spaces Aren't Enough: Machine Translation Needs Attention
Vardasbi, Ali, Pires, Telmo Pessoa, Schmidt, Robin M., Peitz, Stephan
–arXiv.org Artificial Intelligence
Structured State Spaces for Sequences (S4) is a recently proposed sequence model with successful applications in various tasks, e.g. vision, language modeling, and audio. Thanks to its mathematical formulation, it compresses its input to a single hidden state, and is able to capture long range dependencies while avoiding the need for an attention mechanism. In this work, we apply S4 to Machine Translation (MT), and evaluate several encoder-decoder variants on WMT'14 and WMT'16. In contrast with the success in language modeling, we find that S4 lags behind the Transformer by approximately 4 BLEU points, and that it counter-intuitively struggles with long sentences. Finally, we show that this gap is caused by S4's inability to summarize the full source sentence in a single hidden state, and show that we can close the gap by introducing an attention mechanism.
arXiv.org Artificial Intelligence
Apr-25-2023
- Country:
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States
- Maryland (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California
- San Diego County > San Diego (0.04)
- Los Angeles County > Long Beach (0.04)
- Canada > Quebec
- Montreal (0.04)
- United States
- Europe
- Germany (0.04)
- Czechia > Prague (0.04)
- Austria (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Netherlands > North Holland
- Amsterdam (0.04)
- Italy > Tuscany
- Florence (0.04)
- Belgium > Brussels-Capital Region
- Brussels (0.04)
- Asia > China
- Hong Kong (0.04)
- Oceania > Australia
- Genre:
- Research Report > Experimental Study (0.46)
- Technology: