{"title":"分布词嵌入的无监督对齐","authors":"Aïssatou Diallo","doi":"10.48550/arXiv.2203.04863","DOIUrl":null,"url":null,"abstract":"Cross-domain alignment play a key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have successfully been used to infer a bilingual lexicon without relying on supervision. However, current state-of-the art methods only focus on point vectors although distributional embeddings have proven to embed richer semantic information when representing words. In this paper, we propose stochastic optimization approach for aligning probabilistic embeddings. Finally, we evaluate our method on the problem of unsupervised word translation, by aligning word embeddings trained on monolingual data. We show that the proposed approach achieves good performance on the bilingual lexicon induction task across several language pairs and performs better than the point-vector based approach.","PeriodicalId":303369,"journal":{"name":"Deutsche Jahrestagung für Künstliche Intelligenz","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Unsupervised Alignment of Distributional Word Embeddings\",\"authors\":\"Aïssatou Diallo\",\"doi\":\"10.48550/arXiv.2203.04863\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Cross-domain alignment play a key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have successfully been used to infer a bilingual lexicon without relying on supervision. However, current state-of-the art methods only focus on point vectors although distributional embeddings have proven to embed richer semantic information when representing words. In this paper, we propose stochastic optimization approach for aligning probabilistic embeddings. Finally, we evaluate our method on the problem of unsupervised word translation, by aligning word embeddings trained on monolingual data. We show that the proposed approach achieves good performance on the bilingual lexicon induction task across several language pairs and performs better than the point-vector based approach.\",\"PeriodicalId\":303369,\"journal\":{\"name\":\"Deutsche Jahrestagung für Künstliche Intelligenz\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-03-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Deutsche Jahrestagung für Künstliche Intelligenz\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2203.04863\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Deutsche Jahrestagung für Künstliche Intelligenz","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2203.04863","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Unsupervised Alignment of Distributional Word Embeddings
Cross-domain alignment play a key roles in tasks ranging from machine translation to transfer learning. Recently, purely unsupervised methods operating on monolingual embeddings have successfully been used to infer a bilingual lexicon without relying on supervision. However, current state-of-the art methods only focus on point vectors although distributional embeddings have proven to embed richer semantic information when representing words. In this paper, we propose stochastic optimization approach for aligning probabilistic embeddings. Finally, we evaluate our method on the problem of unsupervised word translation, by aligning word embeddings trained on monolingual data. We show that the proposed approach achieves good performance on the bilingual lexicon induction task across several language pairs and performs better than the point-vector based approach.