We present three approaches to word sense disambiguation that use Wikipedia as a source of sense annotations. Starting from a basic monolingual approach, we develop two multilingual systems: one that uses a machine translation system to create multilingual features, and one where multilingual features are extracted primarily through the interlingual links available in Wikipedia. Experiments on ...

This study investigates pitch range variation in the affective speech of bilingual and monolingual children. Cross-linguistic differences in affective speech may lead bilingual children to express emotions differently in their two different languages. A cross-linguistically comparable corpus of 6 bilingual ScottishFrench children and 12 monolingual peers was recorded according to the developed ...

Collocation translation is important for machine translation and many other NLP tasks. Unlike previous methods using bilingual parallel corpora, this paper presents a new method for acquiring collocation translations by making use of monolingual corpora and linguistic knowledge. First, dependency triples are extracted from Chinese and English corpora with dependency parsers. Then, a dependency ...

To alleviate data sparsity in spoken Uyghur machine translation, we proposed a log-linear based morphological segmentation approach. Instead of learning model only from monolingual annotated corpus, this approach optimizes Uyghur segmentation for spoken translation based on both bilingual and monolingual corpus. Our approach relies on several features such as traditional conditional random fiel...

A simple and flexible schema for storing and presenting monolingual language resources is proposed. In this format, data for 18 different languages is already available in various sizes. The data is provided free of charge for online use and download. The main target is to ease the application of algorithms for monolingual and interlingual studies.

We describe our official runs for the ad hoc monolingual task in Hungarian for CLEF 2005. We conducted experiments with four stemmers of varying impact. The experiments indicate that stemmers focusing on noun inflection are as effective as more broadly oriented stemmers, and that extensive stemming is especially beneficial for Hungarian monolingual retrieval.

Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Monolingual data plays an important role in boosting fluency for phrase-based statistical machine translation, and we investigate the use of monolingual data for neural machine translation (NMT). In contrast to previous work, which integrates a sepa...

This study compared how lexical quality (vocabulary and decoding) and executive control (working memory and inhibition) predict reading comprehension directly as well as indirectly, via syntactic integration, in monolingual and bilingual fourth grade children. The participants were 76 monolingual and 102 bilingual children (mean age 10 years, SD = 5 months) learning to read Dutch in the Netherl...

BACKGROUND There is strong evidence that bilinguals have a deficit in speech perception for their second language compared with monolingual speakers under unfavourable listening conditions (e.g., noise or reverberation), despite performing similarly to monolingual speakers under quiet conditions. This deficit persists for speakers highly proficient in their second language and is greater in tho...

This study investigates whether four-month-old Japanese infants are able to distinguish English from Japanese spoken by a bilingual woman (level 9.5) (Experiment 1), and then, spoken by a Japanese monolingual woman (level 1) who has learned English fifty years ago and never been to English speaking countries (Experiment 2). According to Mehler et al. (1993), rhythmic cues play a role for infant...