FLiP recovers more than 75% lexical content from pretrained sentence embeddings across languages and modalities, outperforming non-factorized baselines and exposing intrinsic biases.
Europarl: A parallel corpus for statistical machine translation,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
REINA-SAN and REINA-TAN add temporal context to information-based read/write policies, improving the quality-latency tradeoff in simultaneous speech translation by up to 7.1% on Normalized Streaming Efficiency.
citing papers explorer
-
FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings
FLiP recovers more than 75% lexical content from pretrained sentence embeddings across languages and modalities, outperforming non-factorized baselines and exposing intrinsic biases.
-
Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation
REINA-SAN and REINA-TAN add temporal context to information-based read/write policies, improving the quality-latency tradeoff in simultaneous speech translation by up to 7.1% on Normalized Streaming Efficiency.