Cross-lingual Joint Entity and Word Embedding to Improve Entity Linking and Parallel Sentence Mining
Xiaoman Pan, Thamme Gowda, Heng Ji, Jonathan May, Scott Miller · 2019
Entities, which refer to distinct objects in the real world, can be viewed as language universals and used as effective signals to generate less ambiguous semantic representations and align multiple languages.We propose a novel method, CLEW, to generate cross-lingual data that is a mix of entities and contextual words based on Wikipedia.We replace each anchor link in the source language with its corresponding entity title in the target language if it exists, or in the source language otherwise.A cross-lingual joint entity and word embedding learned from this kind of data not only can disambiguate linkable entities but can also effectively represent unlinkable entities.Because this multilingual common space directly relates the semantics of contextual words in the source language to that of entities in the target language, we leverage it for unsupervised cross-lingual entity linking.Experimental results show that CLEW significantly advances the state-of-the-art: up to 3.1% absolute Fscore gain for unsupervised cross-lingual entity linking.Moreover, it provides reliable alignment on both the word/entity level and the sentence level, and thus we use it to mine parallel sentences for all 302 2 language pairs in Wikipedia. 1 * ዓርብ የሳምንቱ ስድስተኛ ቀን ሲሆን ሐሙስ በኋላ ቅዳሜ በፊት ይገኛል ። * Friday is the day after Thursday and the day before Saturday .Amharic -English Yoruba -English * Glasgow ni ilu totobijulo ni orile-ede Skotlandi ati eyi totobijulo keta ni Britani .* Glasgow is the largest city in Scotland , and third largest in the United Kingdom .Uyghur -English * ﺪۇر ﻛﯜﻧ ﻨﭽﻰ ﺷ ﺑ ﯔ ﻨ ﭘﺘ ھ ، ﻜﻰ ﺪ ﺋﻮﺗﺘﯘرﺳ ﻧﺒ ﺷ ن ﻠ ﺑ ﻧﺒ ﯾﺸ ﭘ ، ﺟﯜﻣ .* Friday is the day after Thursday and the