Past year
All results
- All results
- Verbatim
Including results for Generating Diverse Back-Translations via Constrained Random Decoding.
Oct 9, 2023 · Be- low, we present two distinct strategies to try harder to promote the terminology constraints, via auto- matic post-editing through constrained beam search.
Missing: Diverse | Show results with:Diverse
Jan 10, 2024 · MBR decoding is shown to generate higher quality sentences than random sampling and beam search in directed text generation tasks including machine translation, ...
Apr 17, 2024 · Efficient Sign Language Translation with a Curriculum-based Non-autoregressive Decoder. ... Generating Diverse Back-Translations via Constraint Random Decoding.
Jul 9, 2023 · The model needs to cope with challenging lexical constraints that are “homographs” or “unseen” during training. To this end, we first design a homograph dis-.
Missing: Diverse | Show results with:Diverse
Apr 7, 2024 · A document-level neural machine translation model with dynamic caching guided by theme-rheme information ... Generating diverse back-translations via constraint ...
Jul 12, 2023 · We show the limitations of only using aspect planning in existing explanation generation, and propose to introduce lexical constraints for explanation ...
Missing: Back- | Show results with:Back-
Mar 29, 2024 · Back-translation using google translate (GT). Employing Google Translate, we ... This suggests that leveraging diverse translation sources can lead to more ...
Mar 20, 2024 · Back translation (BT), which generates pseudo-parallel data by translating in-domain spoken language texts into sign glosses, has been applied to alleviate ...
Missing: Diverse | Show results with:Diverse
Nov 22, 2023 · TL;DR: We introduce a novel decoding framework that treats language model decoding as an optimization problem, aiming to strictly match the expected performance ...
Oct 6, 2023 · COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics. ... Controlling politeness in neural machine translation via side constraints.