Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

End-to-end Training and Decoding for Pivot-based Cascaded Translation Model (2305.02261v1)

Published 3 May 2023 in cs.CL and cs.AI

Abstract: Utilizing pivot language effectively can significantly improve low-resource machine translation. Usually, the two translation models, source-pivot and pivot-target, are trained individually and do not utilize the limited (source, target) parallel data. This work proposes an end-to-end training method for the cascaded translation model and configures an improved decoding algorithm. The input of the pivot-target model is modified to weighted pivot embedding based on the probability distribution output by the source-pivot model. This allows the model to be trained end-to-end. In addition, we mitigate the inconsistency between tokens and probability distributions while using beam search in pivot decoding. Experiments demonstrate that our method enhances the quality of translation.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Hao Cheng (190 papers)
  2. Meng Zhang (184 papers)
  3. Liangyou Li (36 papers)
  4. Qun Liu (230 papers)
  5. Zhihua Zhang (118 papers)

Summary

We haven't generated a summary for this paper yet.