We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Minimum Bayes Risk (MBR) decoding is a powerful decoding strategy widely used for text generation tasks, but its quadratic computational complexity limits its practical application. This paper presents a novel approach for approximating MBR decoding using matrix completion techniques, focusing on the task of machine translation. We formulate MBR decoding as a matrix completion problem, where the utility metric scores between candidate hypotheses and pseudo-reference translations form a low-rank matrix. First, we empirically show that the scores matrices indeed have a low-rank structure. Then, we exploit this by only computing a random subset of the scores and efficiently recover the missing entries in the matrix by applying the Alternating Least Squares (ALS) algorithm, thereby enabling a fast approximation of the MBR decoding process. Our experimental results on machine translation tasks demonstrate that the proposed method requires 1/16 utility metric computations compared to vanilla MBR decoding while achieving equal translation quality measured by COMET22 on the WMT22 dataset (en<>de and en<>ru). We also benchmark our method against other approximation methods and we show gains in quality when comparing to them.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.02832")
get_code_for_paper("2406.02832")
have("2406.02832")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.02832.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.02832)
Connect an agent — have() is free.