Papers with average BLEU score

5 papers
A Semantic Uncertainty Sampling Strategy for Back-Translation in Low-Resources Neural Machine Translation (2025.acl-srw)

Copied to clipboard

Challenge: Back-translation methods rely on large-scale parallel corpora to enhance performance, but ignore the semantic quality of monolingual data.
Approach: They propose a method which prioritizes sentences with higher semantic uncertainty as training samples by computationally evaluating the complexity of unannotated monolingual data.
Outcome: The proposed method improves translation accuracy and fluency by +1.7 on all three translation tasks.
STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions (2023.acl-short)

Copied to clipboard

Challenge: We present a corpus of Swiss German speech annotated with Standard German text at the sentence level.
Approach: They present a corpus of Swiss German speech annotated with Standard German sentences . they use a web app to show the speakers standard German sentences and record them .
Outcome: The corpus contains 343 hours of speech from all Swiss German dialect regions . it is the largest public speech corpus for Swiss German to date .
Modularized Multilingual NMT with Fine-grained Interlingua (2024.naacl-long)

Copied to clipboard

Challenge: Neural Machine Translation (MNMT) systems lack layer-sharing to generate interlingua features . however, layer-share structure does not guarantee explicit propagation of language-specific features to respective decoders.
Approach: They propose to share top of language-specific encoder layers to enable interlingua features . their method demonstrates an improved average BLEU score by "+2.90" in En-to-Any directions .
Outcome: The proposed approach improves the BLEU score by "+2.90" in En-to-Any directions and by "+1.06" in zero-shot translation.
Multi-lingual Mathematical Word Problem Generation using Long Short Term Memory Networks with Enhanced Input Features (2020.lrec-1)

Copied to clipboard

Challenge: Existing methods for multi-lingual MWP generation are incapable of identifying language specific constraints, especially in morphologically rich yet low resource languages such as Sinhala and Tamil.
Approach: They propose to use a long-term memory network to generate elementary level MWPs by adding character embeddings, word embedds and Part of Speech (POS) tag embeddements to the network.
Outcome: The proposed model generates elementary level MWPs while satisfying language specific constraints while providing attention for numerical values and units.
CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Copied to clipboard

Challenge: End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach: They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome: The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations