Cross-lingual Wikification Using Multilingual Embeddings

Abstract

Cross-lingual Wikification is the task of grounding mentions written in non-English documents to entries in the English Wikipedia. This task involves the problem of comparing textual clues across languages, which requires developing a notion of similarity between text snippets across languages. In this paper, we address this problem by jointly training multilingual embeddings for words and Wikipedia titles. The proposed method can be applied to all languages represented in Wikipedia, including those for which no machine translation technology is available. We create a challenging dataset in 12 languages and show that our proposed approach outperforms various baselines. Moreover, our model compares favorably with the best systems on the TAC KBP2015 Entity Linking task including those that relied on the availability of translation from the target language to English.

Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation

“…Such embedding models enable us to design NED models that capture the contextual information required to address NED. These models are typically based on conventional word embedding models (e.g., skip-gram (Mikolov et al, 2013)) that assign a fixed embedding to each word and entity (Yamada et al, 2016;Fang et al, 2016;Tsai and Roth, 2016;Cao et al, 2017;Ganea and Hofmann, 2017). In this study, we aim to test the effectiveness of the pretrained contextualized embeddings for NED.…”

On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

“…2). SBWES may be used to support many tasks, e.g., computing cross-lingual/multilingual semantic word similarity (Faruqui and Dyer, 2014), learning bilingual word lexicons (Mikolov et al, 2013a;Gouws et al, 2015;, cross-lingual entity linking (Tsai and Roth, 2016), parsing (Guo et al, 2015;Johannsen et al, 2015), machine translation (Zou et al, 2013), or crosslingual information retrieval (Vulić and Moens, 2015;Mitra et al, 2016).…”

Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning

“…We use the system proposed in Tsai and Roth (2016), which grounds input strings to the intersection of (the title spaces of) the English and the target language Wikipedias. The only requirement is a multilingual Wikipedia dump and it can be applied to all languages in Wikipedia.…”

“…The key contribution of this paper is the development of a method that makes use of crosslingual wikification and entity linking (Tsai and Roth, 2016;Moro et al, 2014) to generate language-independent features for NER, and showing how useful this can be for training NER models with no annotation in the target language. Given a mention (sub-string) from a document written in a foreign language, the goal of cross-lingual wikification is to find the cor- Figure 1: An example of a German sentence.…”