Using Global Constraints and Reranking to Improve Cognates Detection
This work addresses a domain-specific problem in computational linguistics, offering incremental improvements for researchers and practitioners in language processing.
The paper tackled the problem of cognates detection by introducing global constraints and reranking to rescore matrices from existing systems, resulting in significant performance improvements over state-of-the-art methods on various datasets and conditions.
Global constraints and reranking have not been used in cognates detection research to date. We propose methods for using global constraints by performing rescoring of the score matrices produced by state of the art cognates detection systems. Using global constraints to perform rescoring is complementary to state of the art methods for performing cognates detection and results in significant performance improvements beyond current state of the art performance on publicly available datasets with different language pairs and various conditions such as different levels of baseline state of the art performance and different data size conditions, including with more realistic large data size conditions than have been evaluated with in the past.