Graph Algorithms for Multiparallel Word Alignment
With the advent of end-to-end deep learning approaches in machine translation, interest in word alignments initially decreased; however, they have again become a focus of research more recently. Alignments are useful for typological research, transferring formatting like markup to translated texts, and can be used in the decoding of machine translation systems. At the same time, massively multilingual processing is becoming an important NLP scenario, and pretrained language and machine translation models that are truly multilingual are proposed. However, most alignment algorithms rely on bitexts only and do not leverage the fact that many parallel corpora are multiparallel. In this work, we exploit the multiparallelity of corpora by representing an initial set of bilingual alignments as a graph and then predicting additional edges in the graph. We present two graph algorithms for edge prediction: one inspired by recommender systems and one based on network link prediction. Our experimental results show absolute improvements in $F_1$ of up to 28% over the baseline bilingual word aligner in different datasets.
Code (1)
Tasks
Link PredictionMachine TranslationRecommendation SystemsTranslationWord AlignmentSimilar Papers 제목 키워드 기반
Graph Neural Networks for Multiparallel Word Alignment
After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection and machine translation. Generally, alignment …
Community DetectionMachine TranslationWord AlignmentGraph Neural Networks for Multiparallel Word Alignment
After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection, and machine translation. Generally, alignment…
Community DetectionMachine TranslationTranslationWord AlignmentAssessing the Political Fairness of Multilingual LLMs: A Case Study based on a 21-way Multiparallel EuroParl Dataset
The political biases of Large Language Models (LLMs) are usually assessed by simulating their answers to English surveys. In this work, we propose an alternative framing of political biases, relying on principles of fair…
MASSAlign: Alignment and Annotation of Comparable Documents
We introduce MASSAlign: a Python library for the alignment and annotation of monolingual comparable documents. MASSAlign offers easy-to-use access to state of the art algorithms for paragraph and sentence-level alignment…
SentenceA Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs
Neural embedding approaches have become a staple in the fields of computer vision, natural language processing, and more recently, graph analytics. Given the pervasive nature of these algorithms, the natural question bec…
Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsSentence+1