Challenge: Existing methods for neural machine translation (NMT) use encoder-only enhancement or rely on specific multilingual PLMs.
Approach: They propose a monolingual PLM-sponsored NMT model that lets both encoder and decoder enjoy PLM enhancement.
Outcome: The proposed model improves on IWSLT14 En-De, De-En, WMT14 En -De and En-Fr tasks and achieves new state-of-the-art.

Similar Papers

SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Challenge: Using pre-training methods for NMT models is difficult because of the cross-attention module . cross-linguistic embeddings are not used to pretrain a decoder .
Approach: They propose a semantic interface between pre-trained encoder and pre-train decoder to improve NMT performance.
Outcome: The proposed method improves on translation and unsupervised translation tasks.
Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in machine translation have focused on a single pre-trained decoder . encoder-decoder architectures have received relatively little attention in NMT .
Approach: They propose a method that leverages LLMs as MT encoders and pairs them with lightweight decoders to develop universal translation models.
Outcome: The proposed method matches or surpasses baselines in terms of translation quality but achieves 75% reduction in memory footprint of the KV cache.
On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons (2024.naacl-long)

Copied to clipboard

Challenge: Existing decoder-based pre-trained language models demonstrate excellent multilingual capabilities, but it is unclear how they handle multilingualism.
Approach: They propose to examine the neuron-level internal behavior of decoder-based PLMs by finding neurons that fire “uniquely for each language” within decoded PLM models.
Outcome: The proposed models fire “uniquely for each language” and show that language-specific neurons are unique, with a slight overlap (5%) between languages.
Neural Machine Translation Incorporating Named Entity (C18-1)

Copied to clipboard

Challenge: Conventional NMT models have difficulty translating words with multiple meanings because of the high ambiguity.
Approach: They propose a neural machine translation model that incorporates named entity (NE) tags of source-language sentences to reduce the difficulty in translating multiple meanings.
Outcome: The proposed model achieves 3.11 point improvement in bilingual evaluation understudy (BLEU) on English-to-Japanese translation task with the ASPEC, and English- to-Bulgarian and English to-Romanian translation tasks with the Europarl corpus.
Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation (2020.findings-emnlp)

Copied to clipboard

Challenge: Multilingual data is more beneficial for NMT models that translate from the LRL to a target language than those that translate into the LLLs.
Approach: They propose a decoder that embeds character n-grams into NMT models that translate from an LRL to a target language.
Outcome: The proposed decoder improves the performance of NMT models that translate from an LRL to a target language.
Pre-trained language model representations for language generation (N19-1)

Copied to clipboard

Challenge: Pre-trained language model representations have been successful in a wide range of language understanding tasks.
Approach: They propose to use pre-trained language model representations to integrate them into sequence to sequence models and apply it to machine translation and abstractive summarization.
Outcome: The proposed model is able to perform 5.3 BLEU in machine translation and 5.3 on the full text version of CNN/DailyMail.
Enhancing Large Language Models for Document-Level Translation Post-Editing Using Monolingual Data (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have excellent performance in many tasks, but they still face challenges in document translation.
Approach: They propose a method that leverages the capabilities of Large Language Models to optimize document translation using only monolingual data.
Outcome: The proposed method improves translation quality and improves contextual consistency in document translation using only monolingual data.
Language-aware Interlingua for Multilingual Neural Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: Existing multilingual neural machine translation models fail to capture diversity and specificity of different languages, resulting in inferior performance against individual models that are sufficiently trained.
Approach: They propose to integrate a language-aware interlingua into an Encoder-Decoder architecture to learn a semantic representation from the semantic spaces of different languages while allowing for language-specific specialization of a particular language pair.
Outcome: The proposed model achieves remarkable improvements over state-of-the-art multilingual NMT models and produces comparable performance with strong individual models.
A Tree-based Decoder for Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Existing work on adding syntactic information to NMT systems is limited to linguistically-inspired tree structures.
Approach: They propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side.
Outcome: The proposed model outperforms standard seq2seq models by 2.1 BLEU points and other methods for incorporating target-side syntax by 0.7 BLUE points.
Effectively pretraining a speech translation decoder with Machine Translation data (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to improve the performance of AST systems are based on pretraining the encoder parameters using an ASR model, but using a pretrained MT decoder is not beneficial or improves the results.
Approach: They propose to use an adversarial regularizer to bring the encoder representations of the ASR and NMT tasks closer even though they are in different modalities.
Outcome: The proposed model can be pre-trained using the Automatic Speech Recognition (ASR) task even in different languages and improves in low resource settings.

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