This paper presents and compares WordNetbased and distributional similarity approaches. The strengths and weaknesses of each approach regarding similarity and relatedness tasks are discussed, and a combination is presented. Each of our methods independently provide the best results in their class on the RG and WordSim353 datasets, and a supervised combination of them yields the best published r...

In this paper, we introduce an approach to combining word embeddings and machine translation for multilingual semantic word similarity, the task2 of SemEval2017. Thanks to the unsupervised transliteration model, our cross-lingual word embeddings encounter decreased sums of OOVs. Our results are produced using only monolingual Wikipedia corpora and a limited amount of sentence-aligned data. Alth...

This work evaluates the applicability of currently available research tools to the problem of cross lingual QA. We establish a task baseline by combining a cross lingual IR system with a monolingual QA system in a very short amount of time. A higher precision strategy involves applying the monolingual QA system to an automatically translated question, assumed to be correct. A higher coverage st...

Semi-supervised and cross-lingual knowledge transfer learnings are two strategies for boosting performance of lowresource speech recognition systems. In this paper, we propose a unified knowledge transfer learning method to deal with these two learning tasks. Such a knowledge transfer learning is realized by fine-tuning of Deep Neural Network (DNN). We demonstrate its effectiveness in both mono...

This article describes the distributional strategy submitted by the Citius team to the SemEval 2017 Task 2. Even though the team participated in two subtasks, namely monolingual and crosslingual word similarity, the article is mainly focused on the cross-lingual subtask. Our method uses comparable corpora and syntactic dependencies to extract count-based and transparent bilingual distributional...

This paper presents two instance-level transfer learning based algorithms for cross lingual opinion analysis by transferring useful translated opinion examples from other languages as the supplementary training data for improving the opinion classifier in target language. Starting from the union of small training data in target language and large translated examples in other languages, the Tran...

For TREC-10, we participated in the adhoc and manual web tracks and in both the site-finding and cross-lingual tracks. For the adhoc track, we did extensive calibrations and learned that combining similarity measures yields little improvement. This year, we focused on a single highperformance similarity measure. For site finding, we implemented several algorithms that did well on the data provi...

Given lexical-semantic resources in different languages, it is useful to establish cross-lingual correspondences, preferably with semantic relation labels, between the concept nodes in these resources. This paper presents a framework for enabling a cross-lingual/nodewise alignment of lexical-semantic resources, where cross-lingual correspondence candidates are first discovered and ranked, and t...

MuchMore provides a framework for integrating and refining existing technologies and developing new approaches to cross-lingual information retrieval (CLIR) for the medical domain. Existence of very large ontologies of domain concepts and extensive corpora for the medical domain has grounded the work toward refinement, integration and comparison of concept-based retrieval methods and corpora-ba...

We introduce BilBOWA (Bilingual Bag-ofWords without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-alig...