Challenge: a single source idiom can have multiple target-language equivalents depending on cultural references and contextual variations.
Approach: They propose an adaptive graph neural network-based method that learns intricate mappings between idiomatic expressions and generalizes to both seen and unseen nodes during training.
Outcome: The proposed method improves translation quality even in resource-constrained settings, facilitating improved idiomatic translation in smaller models.

Similar Papers

Examining the Tip of the Iceberg: A Data Set for Idiom Translation (L18-1)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) has been widely used in recent years with significant improvements for many language pairs.
Approach: They propose to use a large-scale data set to evaluate idiom translation in GermanEnglish.
Outcome: The proposed dataset is used to perform preliminary NMT experiments on idiom translation in GermanEnglish.
Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting (2023.emnlp-main)

Copied to clipboard

Challenge: idioms are common in everyday language, but often pose a challenge to translators because their meanings do not follow from the meanings of their parts.
Approach: They propose to use retrieval-augmented models to increase the accuracy of a strong pretrained machine translation model on idiomatic sentences by up to 13%.
Outcome: The proposed techniques improve the accuracy of a strong pretrained model on idiomatic sentences by up to 13% in absolute accuracy, and holds potential benefits for non-idiomatic phrases.
Multi-level Community-awareness Graph Neural Networks for Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Recent studies have used Graph Neural Networks (GNNs) to encode language knowledge into token embeddings.
Approach: They propose a multi-level community-awareness Graph Neural Network layer to jointly model local and global relationships between words and their linguistic roles in multiple communities.
Outcome: The proposed method reduces time complexity in very long sentences while preserving the original meaning.
No more beating about the bush : A Step towards Idiom Handling for Indian Language NLP (L18-1)

Copied to clipboard

Challenge: idioms are a part of natural language and are difficult to learn with a parallel corpora database.
Approach: They propose to use a parallel idiom dataset to train two NLP subtasks . they show significant improvement in the two subtask training without the idiomatic dataset .
Outcome: The proposed model improves on baseline models with the idiom dataset for two NLP applications.
IEKG: A Commonsense Knowledge Graph for Idiomatic Expressions (2023.emnlp-main)

Copied to clipboard

Challenge: Prior work on IE comprehension has focused on detecting idiomaticity, but this fails to account for IEs' non-compositionality.
Approach: They construct a commonsense knowledge graph for figurative interpretations of IEs that can be used to convert PTLMs into knowledge models that encode and infer commonsensical knowledge related to IE use.
Outcome: The proposed model can generalize to IEs unseen during training.
Idiomatic Expression Identification using Semantic Compatibility (2021.tacl-1)

Copied to clipboard

Challenge: Existing approaches to localize idiomatic expressions have limited views of their generalizability to new idioms.
Approach: They propose a multi-stage neural architecture to detect whether a sentence has an idiomatic expression and localize it when it occurs in a figurative sense.
Outcome: The proposed model achieves state-of-the-art on three of the largest datasets with idiomatic expressions of varied syntactic patterns and degrees of non-compositionality.
Neural-based Chinese Idiom Recommendation for Enhancing Elegance in Essay Writing (P19-1)

Copied to clipboard

Challenge: idiom recommendation is difficult because remembering idiomatic expressions is difficult, authors say . idiomas are often written in ancient classical Chinese for conciseness, meaning is difficult to remember .
Approach: They propose to use a neural machine translation framework to recommend idioms . they assume that idiomatic expressions are written with one pseudo target language .
Outcome: The proposed approach achieves promising performance compared with baseline methods.
Informative Language Representation Learning for Massively Multilingual Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Existing studies show that prepending language tokens fail to guide translation into right directions, especially on zero-shot translation.
Approach: They propose to use language embedding embodiment and language-aware multi-head attention to learn informative language representations to channel translation into right directions.
Outcome: The proposed methods improve translation direction guidance and significantly alleviate off-target translation issues on two datasets.
Automatic Evaluation and Analysis of Idioms in Neural Machine Translation (2023.eacl-main)

Copied to clipboard

Challenge: Neural machine translation (NMT) struggles with the translation of rare multi-word expressions (MWEs).
Approach: They propose a metric for automatically measuring the frequency of literal translation errors without human involvement.
Outcome: The proposed metric measures the frequency of literal translation errors without human involvement with the models trained in different conditions and across a wide range of metrics and test sets.
Context-aware Neural Machine Translation with Coreference Information (D19-65)

Copied to clipboard

Challenge: Existing models for translating a sentence in a text do not consider coreference relations provided within the text.
Approach: They propose a graph-based encoder which can consider coreference relations provided within the text explicitly.
Outcome: The proposed model improves on the previous approach by 0.9 points on the BLEU score . the graph-based encoder can handle a longer text well, compared with the previous model .

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