Papers with neural machine translation system
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
Julia Ive, Lucia Specia, Sara Szoc, Tom Vanallemeersch, Joachim Van den Bogaert, Eduardo Farah, Christine Maroti, Artur Ventura, Maxim Khalilov
| 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 . |