Javier Ferrando, Marta Costa-Jussà, Carlos Escolano, Gerard Gállego, Belen Alastruey
We lifted 8 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| mt-upc/transformer-contributions-nmt | canonical | 8 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| contrib_tok2words | Ran | mt-upc/transformer-contributions-nmt/alignment/align.py code served (permissive licence) · get_code("b0fe901062fe44a7") |
| contrib_tok2words_partial | Ran | mt-upc/transformer-contributions-nmt/alignment/align.py code served (permissive licence) · get_code("ccfc9acc2f460939") |
| contribution_source | Ran | mt-upc/transformer-contributions-nmt/wrappers/helper.py code served (permissive licence) · get_code("ee46b90a0484d484") |
| get_greedy_decoding | Ran | mt-upc/transformer-contributions-nmt/wrappers/helper.py code served (permissive licence) · get_code("b6c6b6eaf480d4b6") |
| get_normalized_rank | Ran | mt-upc/transformer-contributions-nmt/wrappers/utils.py code served (permissive licence) · get_code("83bb8ecb1a22ea52") |
| get_translation | Ran | mt-upc/transformer-contributions-nmt/wrappers/helper.py code served (permissive licence) · get_code("fa9a832d249635ca") |
| get_word_word_attention | Ran | mt-upc/transformer-contributions-nmt/alignment/align.py code served (permissive licence) · get_code("4c5f47f52afaaae6") |
| spearmanr | Ran | mt-upc/transformer-contributions-nmt/wrappers/utils.py code served (permissive licence) · get_code("1b48822629bead35") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly focused solely on source sentence tokens' attributions. Therefore, we lack a full understanding of the influences of every input token (source sentence and target prefix) in the model predictions. In this work, we propose an interpretability method that tracks input tokens' attributions for both contexts. Our method, which can be extended to any encoder-decoder Transformer-based model, allows us to better comprehend the inner workings of current NMT models. We apply the proposed method to both bilingual and multilingual Transformers and present insights into their behaviour.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.11631")
get_code_for_paper("2205.11631")
have("2205.11631")
Connect an agent — have() is free.