Challenge: Existing document-level machine translation test-sets cover general domain but fall short on specialised domains, such as legal and financial.
Approach: They propose to use a document-level machine translation test-set to replace perfectly aligned sentences by presenting data in units of sections rather than sentences.
Outcome: The proposed dataset is built from specialised financial documents and it shows that it can discriminate between context-sensitive and context-agnostic models and shows the weaknesses when models fail to accurately translate financial texts.

Similar Papers

DocFinQA: A Long-Context Financial Reasoning Dataset (2024.acl-short)

Copied to clipboard

Challenge: Existing work on automating financial numerical reasoning focuses on unrealistically specific document snippets, failing to reflect the broader and more realistic scenarios faced by analysts.
Approach: They propose a long-document financial QA task that augments 7,437 questions from existing FinQA dataset with full-document context, extending the average context length from under 700 words in FinQA to 123k words in DocFinQA.
Outcome: The proposed task extends the average context length from under 700 words in FinQA to 123k words in DocFinQA.
MultiFin: A Dataset for Multilingual Financial NLP (2023.findings-eacl)

Copied to clipboard

Challenge: Multilingual models are needed to process financial text, which is produced across the world and requires a large dataset.
Approach: They propose to annotate a publicly available financial dataset using a hierarchical label structure and an annotation schema based on a real-world application.
Outcome: The proposed model can be used in high-resource languages, but there is room for improvement in low-resourced languages.
AFRIDOC-MT: Document-level MT Corpus for African Languages (2025.emnlp-main)

Copied to clipboard

Challenge: AFRIDOC-MT is a document-level multi-parallel translation dataset covering five languages . AFRITIC-MT models perform better on sentences than general-purpose LLMs .
Approach: They propose a document-level multi-parallel translation dataset covering English and five African languages.
Outcome: The proposed dataset covers 334 health and 271 information technology news documents . it shows that NLLB-200 achieves the best average performance among standard models .
Rethinking Document-level Neural Machine Translation (2022.findings-acl)

Copied to clipboard

Challenge: Neural machine translation models are weak enough for document-level translation . current models only translate sentences individually, resulting in poor document coherence .
Approach: They propose to use the original Transformer model to test document-level neural machine translation . they find that the original transformer models can achieve strong results for document translation if trained properly .
Outcome: The proposed model outperforms sentence-level models on nine datasets and two sentence- level datasets across six languages.
Document Sub-structure in Neural Machine Translation (2020.lrec-1)

Copied to clipboard

Challenge: Current approaches to machine translation (MT) translate sentences in isolation, disregarding context they appear in, or model context at the level of the full document.
Approach: They propose to include information about the topic of the section within which each sentence is found in a document that is not homogeneous . they use a cache-based model to model the context of the document, instead of translating sentences in isolation .
Outcome: The proposed model incorporates information about the topic of the section within which each sentence is found into a neural model.
The Impact of Domain-Specific Terminology on Machine Translation for Finance in European Languages (2025.naacl-long)

Copied to clipboard

Challenge: Existing datasets for evaluating MT systems in this domain are limited.
Approach: They propose to use a multi-parallel corpus from the European Central Bank to analyze the impact of domain-specific terminology on multilingual machine translation for finance.
Outcome: The proposed method compares open-source multilingual MT systems with large language models (LLMs) that possess multilingual capabilities.
Discourse-Centric Evaluation of Document-level Machine Translation with a New Densely Annotated Parallel Corpus of Novels (2023.acl-long)

Copied to clipboard

Challenge: Several recent papers claim to have achieved human parity at sentence-level machine translation.
Approach: They propose to use a dataset with rich discourse annotations to evaluate MT performance . they find that MT outputs differ fundamentally from human translations in terms of latent discourse structures.
Outcome: The proposed dataset builds upon the large-scale parallel corpus BWB . it covers 15,095 entity mentions in both languages and compares them to human translations .
On Context Span Needed for Machine Translation Evaluation (2020.lrec-1)

Copied to clipboard

Challenge: a number of common patterns can be observed for context-aware MT evaluation, authors say . document-level evaluations have largely been performed at the sentence level . the definition of what constitutes a "document level" evaluation is still unclear .
Approach: They propose to use a series of surveys to identify the necessary context span . they find common patterns that can be used to draw general guidelines .
Outcome: The proposed evaluations of machine translation systems show that some issues and spans depend on domain and target language.
TANDO: A Corpus for Document-level Machine Translation (2022.lrec-1)

Copied to clipboard

Challenge: Document-level Neural Machine Translation aims to increase the quality of neural translation models by taking into account contextual information.
Approach: They propose to use document-level corpus for Basque-Spanish language pairs to take into account contextual information and perform fine-grained evaluations of gender and gender.
Outcome: The proposed corpus is suitable for fine-grained evaluation of document-level machine translation systems.

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