Challenge: Neural sequence-to-sequence models have proven effective for machine translation, but at the expense of interpretability.
Approach: They analyze how morphological features are captured at different levels of the NMT encoder while varying the target language.
Outcome: The proposed model is not interpretable, but only captures morphological features in context and only to the extent they are directly transferable to the target words.

Similar Papers

A Morphology-Based Investigation of Positional Encodings (2024.emnlp-main)

Copied to clipboard

Challenge: Contemporary deep learning models handle languages with diverse morphology . morphological complexity of languages is closely linked with positional encodings .
Approach: They propose to use positional encodings to integrate morphological complexity into deep learning models.
Outcome: The proposed model improves on 22 languages and 5 downstream tasks.
Low-resource neural machine translation with morphological modeling (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods for character-based and sub-word tokenization are limited to the surface forms of the words.
Approach: They propose a framework-solution for modeling complex morphology in low-resource settings using a transformer architecture and beam search-based decoder.
Outcome: The proposed model improves translation performance on Kinyarwanda English translation using public-domain parallel text.
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.
One Size Does Not Fit All: Comparing NMT Representations of Different Granularities (N19-1)

Copied to clipboard

Challenge: Recent work has shown that contextualized word representations are a viable alternative to simple word prediction tasks.
Approach: They propose to use subword units and characters to model morphology, syntax, and semantics instead of word embeddings.
Outcome: The proposed representations are better for modeling syntax and more robust to noisy input.
Improving Character-Based Decoding Using Target-Side Morphological Information for Neural Machine Translation (N18-1)

Copied to clipboard

Challenge: Morphologically complex words (MCWs) are multi-layer structures consisting of different subunits, each of which carries semantic information and has a specific syntactic role.
Approach: They propose an extension to the state-of-the-art model which works at the character level and boosts the decoder with target-side morphological information.
Outcome: The proposed model improves on the state-of-the-art model and can be extended to include morphologically complex words (MCWs) in three languages.
Proceedings of the 3rd Workshop on Neural Generation and Translation (D19-56)

Copied to clipboard

Challenge: The third workshop on neural generation and translation is held in london . the workshop received 68 submissions from leading minds in the field .
Approach: the third workshop on neural generation and translation is held in london . the workshop will feature four invited talks from leading minds in the field .
Outcome: the third workshop on neural generation and translation is held in london . the conference received 68 submissions from which 36 accepted .
Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: In encoder-decoder neural models, multiple encoders are used to represent contextual information in addition to the individual sentence.
Approach: They propose to use multiple context encoders to encode the individual sentences in document-level neural machine translation (NMT) They propose a noisy dropout setup and a single-encoder approach to encode context sentences.
Outcome: The proposed approach encodes the context and the current sentence without contexts.
On the differences between BERT and MT encoder spaces and how to address them in translation tasks (2021.acl-srw)

Copied to clipboard

Challenge: Various studies show that pretrained language models cannot replace encoders in neural machine translation despite their success in other tasks.
Approach: They propose a supervised transformation from one into the other to improve the applicability of BERT in neural machine translation.
Outcome: The proposed transformations show that they cannot replace encoders in MT despite their success in other tasks.
Towards Modeling the Style of Translators in Neural Machine Translation (2021.naacl-main)

Copied to clipboard

Challenge: a key ingredient of neural machine translation is the use of large datasets with different but consistent translation styles . however, the models do not capture the variety of translators' styles from the data . a recent study shows that style-augmented models can capture the style variations of translator .
Approach: They propose to augment a neural machine translation model with translator information . they use TED talk datasets to model and control translator-related stylistic variations .
Outcome: The proposed models capture the style variations of translators and generate translations with different styles on new data.
Training and Adapting Multilingual NMT for Less-resourced and Morphologically Rich Languages (L18-1)

Copied to clipboard

Challenge: Using multilingual and multi-way neural machine translation approaches is a major advantage . training NMT systems for individual language pairs takes significantly more time than training of SMT systems .
Approach: They propose to employ multilingual and multi-way neural machine translation approaches for morphologically rich languages such as Estonian and Russian.
Outcome: The proposed approach improves translation quality by +3.27 BLEU points over baseline models.

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