Image captioning has emerged as an interesting research field in recent years due to its broad application scenarios. The traditional paradigm of image relies on paired image-caption datasets train the model a supervised manner. However, creating such for every target language is prohibitively expensive, which hinders extensibility technology and deprives large part world population benefit. In...

Multi-lingual generation starts from non-linguistic content representations for generating texts in different languages that are equivalent in meaning. In contrast, cross-lingual generation is based on a language-neutral content representation which is the result of a linguistic analysis process. Non-linguistic representations do not reflect the structure of the text. Quite differently, languag...

We present the idea of estimating semantic distance in one, possibly resource-poor, language using a knowledge source in another, possibly resource-rich, language. We do so by creating cross-lingual distributional profiles of concepts, using a bilingual lexicon and a bootstrapping algorithm, but without the use of any sense-annotated data or word-aligned corpora. The cross-lingual measures of s...

Word embeddings are well known to capture linguistic regularities of the language on which they are trained. Researchers also observe that these regularities can transfer across languages. However, previous endeavors to connect separate monolingual word embeddings typically require cross-lingual signals as supervision, either in the form of parallel corpus or seed lexicon. In this work, we show...

Täckström, O. 2013. Predicting Linguistic Structure with Incomplete and Cross-Lingual Supervision. Acta Universitatis Upsaliensis. Studia Linguistica Upsaliensia 14. xii+215 pp. Uppsala. ISBN 978-91-554-8631-0. Contemporary approaches to natural language processing are predominantly based on statistical machine learning from large amounts of text, which has been manually annotated with the ling...

Relation extraction has been widely used for finding unknown relational facts from the plain text. Most existing methods focus on exploiting mono-lingual data for relation extraction, ignoring massive information from the texts in various languages. To address this issue, we introduce a multi-lingual neural relation extraction framework, which employs monolingual attention to utilize the inform...

This paper demonstrates the effectiveness of cross-lingual patent wikification, which links technical terms in a patent application document to their corresponding Wikipedia articles in different languages. The number of links increases definitely because different language versions of Wikipedia cover different sets of technical terms. We present an experiment of Japanese-to-English cross-lingu...

This work is, to our knowledge, a first attempt at a machine learning approach to cross-lingual coreference resolution, i.e. coreference resolution (CR) performed on a bitext. Focusing on CR of English pronouns, we leverage language differences and enrich the feature set of a standard monolingual CR system for English with features extracted from the Czech side of the bitext. Our work also incl...

The amount of entities in large knowledge bases (KBs) has been increasing rapidly, making it possible to propose new ways of intelligent information access. In addition, there is an impending need for systems that can enable multilingual and cross-lingual information access. In this work, we firstly demonstrate X-LiSA, an infrastructure for multilingual and cross-lingual semantic annotation, wh...

We present a matrix factorization model for learning cross-lingual representations. Using sentence-aligned corpora, the proposed model learns distributed representations by factoring the given data into language-dependent factors and one shared factor. Moreover, the model can quickly learn shared representations for more than two languages without undermining the quality of the monolingual comp...