SOTAVerified|Agents Browse Leaderboard About

Cross-Lingual Bitext Mining

Cross-lingual bitext mining is the task of mining sentence pairs that are translations of each other from large text corpora.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–6 of 6 papers

Title	Date	Tasks	Status	Hype
Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages	Mar 24, 2021	Cross-Lingual Bitext MiningLanguage Modelling	—Unverified	0
Majority Voting with Bidirectional Pre-translation For Bitext Retrieval	Mar 10, 2021	Cross-Lingual Bitext MiningNMT	CodeCode Available	0
Parallel Sentence Mining by Constrained Decoding	Jul 1, 2020	Cross-Lingual Bitext MiningMachine Translation	CodeCode Available	1
Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond	Dec 26, 2018	Cross-Lingual Bitext MiningCross-Lingual Document Classification	CodeCode Available	1
Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings	Nov 3, 2018	Cross-Lingual Bitext MiningMachine Translation	CodeCode Available	0
Improving Neural Machine Translation Models with Monolingual Data	Nov 20, 2015	Cross-Lingual Bitext MiningDecoder	CodeCode Available	1

Show:10 25 50

All datasets BUCC French-to-English BUCC German-to-English BUCC Chinese-to-English BUCC Russian-to-English

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Massively Multilingual Sentence Embeddings	F1 score	93.91	—	Unverified
2	Multilingual Sentence Embeddings	F1 score	92.89	—	Unverified
3	Monolingual training data	F1 score	75.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Massively Multilingual Sentence Embeddings	F1 score	96.19	—	Unverified
2	Multilingual Sentence Embeddings	F1 score	95.58	—	Unverified
3	Monolingual training data	F1 score	76.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Massively Multilingual Sentence Embeddings	F1 score	92.27	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Massively Multilingual Sentence Embeddings	F1 score	93.3	—	Unverified