SOTAVerified|Agents Browse Leaderboard About

Word Alignment

Word Alignment is the task of finding the correspondence between source and target words in a pair of sentences that are translations of each other.

Source: Neural Network-based Word Alignment through Score Aggregation

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 31–40 of 551 papers

Title	Date	Tasks	Status	Hype
Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents	May 22, 2023	Contrastive LearningLanguage Modeling	CodeCode Available	0
Contextualized Word Vector-based Methods for Discovering Semantic Differences with No Training nor Word Alignment	May 19, 2023	Word Alignment	—Unverified	0
AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation	May 19, 2023	Machine TranslationTranslation	CodeCode Available	0
Low-resource Bilingual Dialect Lexicon Induction with Large Language Models	Apr 19, 2023	Bilingual Lexicon InductionMachine Translation	CodeCode Available	0
Investigating the Role of Attribute Context in Vision-Language Models for Object Recognition and Detection	Mar 17, 2023	AttributeContrastive Learning	—Unverified	0
Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models	Feb 15, 2023	named-entity-recognitionNamed Entity Recognition	CodeCode Available	0
Multilingual Sentence Transformer as A Multilingual Word Aligner	Jan 28, 2023	SentenceWord Alignment	CodeCode Available	1
Noisy Parallel Data Alignment	Jan 23, 2023	Optical Character RecognitionOptical Character Recognition (OCR)	CodeCode Available	0
Learning Trajectory-Word Alignments for Video-Language Tasks	Jan 5, 2023	Question AnsweringRetrieval	—Unverified	0
Learning To Generate Language-Supervised and Open-Vocabulary Scene Graph Using Pre-Trained Visual-Semantic Space	Jan 1, 2023	Graph Generationobject-detection	CodeCode Available	1

Show:10 25 50

← PrevPage 4 of 56Next →

All datasets en-es en-fr es-en fr-en en-it MUSE en-de MUSE en-pt

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Barycenter Alignment	P@1	84.26	—	Unverified
2	Adv - Refine - CSLS	P@1	81.7	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Barycenter Alignment	P@1	82.94	—	Unverified
2	Adv - Refine - CSLS	P@1	82.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Barycenter Alignment	P@1	83.5	—	Unverified
2	Adv - Refine - CSLS	P@1	83.3	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Barycenter Alignment	P@1	83.23	—	Unverified
2	Adv - Refine - CSLS	P@1	82.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Barycenter Alignment	P@1	81.45	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Barycenter Alignment	P@1	74.08	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Barycenter Alignment	P@1	84.65	—	Unverified