Papers with neural machine translation system

6 papers
Parallel Sentence Mining by Constrained Decoding (2020.acl-main)

Copied to clipboard

Challenge: Using a neural machine translation system to extract parallel sentences from two monolingual corpora is challenging.
Approach: They propose a method to extract parallel sentences from two monolingual corpora by constraining the decoding by a prefix tree built on the other corpus.
Outcome: The proposed method achieves comparable results to other submissions on the BUCC shared task.
Cheat Codes to Quantify Missing Source Information in Neural Machine Translation (2022.naacl-main)

Copied to clipboard

Challenge: a neural machine translation system generates a translation t in the target language, but for any sentence of non-trivial complexity, the translation s is not unique.
Approach: They propose a method to quantify the amount of information missing in a machine translation system.
Outcome: The proposed model captures extra information from a single float representation of the target sentence and reproduces it with two 32-bit floats per target token.
The LTRC Hindi-Telugu Parallel Corpus (2022.lrec-1)

Copied to clipboard

Challenge: a qualitative corpus of 700K parallel sentences was created using multiple methods such as extract, align and review of Hindi-Telugu corpora.
Approach: They propose to create a Hindi-Telugu parallel corpus of different technical domains using different methods including extract, align and review.
Outcome: The proposed corpus is the largest, publicly available domain parallel corpus for Hindi-Telugu.
Long to reign over us: A Case Study of Machine Translation and a New Monarch (2023.findings-acl)

Copied to clipboard

Challenge: We examine translations between French and English in contexts with ambiguity . with the passing of Queen Elizabeth II, MT systems can produce errors due to linguistic features of both languages and the paucity of references to kings in the training data.
Approach: They examine translations between French and English as they were produced by MT systems . they find that even when human translators would have adequate context, machine translation systems do not always produce the expected output.
Outcome: The proposed model shows that even when human translators have context, machine translation systems do not always produce the expected output.
A Post-Editing Dataset in the Legal Domain: Do we Underestimate Neural Machine Translation Quality? (2020.lrec-1)

Copied to clipboard

Challenge: Current state-of-the-art in Neural Machine Translation (NMT) has reached remarkable progress, but human evaluations are often judged as having lower quality than top NMT systems.
Approach: They propose to use a machine translation dataset with post-edited high-quality neural machine translation and independent human references to compare the results.
Outcome: The proposed dataset includes 31K tuples including a source sentence, the respective machine translation by a neural machine translation system, and a post-edited version of such translation by professional translator.
Dialectal and Low Resource Machine Translation for Aromanian (2025.coling-main)

Copied to clipboard

Challenge: Existing training methods for low-resource languages are focused on English or are massively multilingual, but do not consider the particularities of lowresource language.
Approach: They propose a neural machine translation system that can translate between Romanian, English, and Aromanian.
Outcome: The proposed system can translate between Romanian, English, and Aromanian . BLEU scores range from 17 to 32 depending on direction and genre of text .

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