We lifted 5 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| MicrosoftTranslator/ToShipOrNotToShip | canonical | 3 of 3 |
| unbabel/mt-telescope | pwc_unofficial | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| get_equal_pairs | Ran | MicrosoftTranslator/ToShipOrNotToShip/evaluation/tools.py pointer only (licence: CC-BY-SA-4.0) · get_code("a349341609dde330") |
| get_valid | Ran | MicrosoftTranslator/ToShipOrNotToShip/evaluation/tools.py pointer only (licence: CC-BY-SA-4.0) · get_code("06566b60002cdffc") |
| hash_string_md5 | Ran | MicrosoftTranslator/ToShipOrNotToShip/evaluation/tools.py pointer only (licence: CC-BY-SA-4.0) · get_code("142f04d7cedca9a0") |
| read_lines | Ran | unbabel/mt-telescope/telescope/utils.py code served (permissive licence) · get_code("b747bf1b0cf69e35") |
| update_buckets | Ran | unbabel/mt-telescope/telescope/plotting.py code served (permissive licence) · get_code("c1abbcd47b9fbaa0") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Automatic metrics are commonly used as the exclusive tool for declaring the superiority of one machine translation system's quality over another. The community choice of automatic metric guides research directions and industrial developments by deciding which models are deemed better. Evaluating metrics correlations with sets of human judgements has been limited by the size of these sets. In this paper, we corroborate how reliable metrics are in contrast to human judgements on -- to the best of our knowledge -- the largest collection of judgements reported in the literature. Arguably, pairwise rankings of two systems are the most common evaluation tasks in research or deployment scenarios. Taking human judgement as a gold standard, we investigate which metrics have the highest accuracy in predicting translation quality rankings for such system pairs. Furthermore, we evaluate the performance of various metrics across different language pairs and domains. Lastly, we show that the sole use of BLEU impeded the development of improved models leading to bad deployment decisions. We release the collection of 2.3M sentence-level human judgements for 4380 systems for further analysis and replication of our work.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2107.10821")
get_code_for_paper("2107.10821")
have("2107.10821")
Connect an agent — have() is free.