Factored neural machine translation (FNMT) is founded on the idea of using the morphological and grammatical decomposition of the words (factors) at the output side of the neural network. This architecture addresses two well-known problems occurring in MT, namely the size of target language vocabulary and the number of unknown tokens produced in the translation. FNMT system is designed to manag...

The probability of skipping a word is influenced by its processing ease. For instance, a word that is predictable from the preceding context is skipped more often than an unpredictable word. A meta-analysis of studies examining this predictability effect reported effect sizes ranging from 0 to 13%, with an average of 8%. One study does not fit within this picture and reported 23% more skipping ...

In two studies we tested the hypothesis that the appropriate linguistic formulation of a deontic rule – i.e. the formulation which clarifies the monadic nature of deontic operators should produce more correct responses than the conditional formulation in Wason selection task. We tested this assumption by presenting a prescription rule and a prohibition rule in conditional vs. proper deontic for...

This paper describes the system developed by the UBham team for the SemEval2014 Aspect-Based Sentiment Analysis task (Task 4). We present an approach based on deep linguistic processing techniques and resources, and explore the parameter space of these techniques applied to the different stages in this task and examine possibilities to exploit interdependencies between them.

This study investigates the Voice Onset Time (VOT) of stop consonant production in six bilingual English-Arabic children in order to examine whether bilingual children possess one unitary or two separate linguistic systems. A total of six English-Arabic bilingual children participated ages 5 to 10. English and Arabic stop consonants followed by a vowel /a/ made by bilingual children were measur...

In this study we elaborate a road map for the conversion of a traditional lexical syntactico-semantic resource for French into a linguistic linked open data (LLOD) model. Our approach uses current best-practices and the analyses of earlier similar undertakings (lemonUBY and PDEV-lemon) to tease out the most appropriate representation for our resource.

This paper investigates the potential use of dialog-based ALICEbots in disseminating terrorism information to the general public. In particular, we study the acceptance and response satisfaction of ALICEbot responses in both the general conversation and terrorism domains. From our analysis of three different knowledge sets: general conversation, terrorism, and combined, we found that users were...

This paper describes a process of building a bilingual syntactically annotated corpus, the PCEDT (Prague Czech-English Dependency Treebank). The corpus is being created at Charles University, Prague, and the release of this corpus as Linguistic Data Consortium data collection is scheduled for the spring of 2004. The paper discusses important decisions made prior to the start of the project and ...

To relax the Term Independence Assumption, Term Dependency is introduced and it has improved retrieval precision dramatically. There are two kinds of term dependencies, one is defined by term proximity, and the other is defined by linguistic dependencies. In this paper, we take a comparative study to re-examine these two kinds of term dependencies in dependence language model framework. Syntact...

Absolute linguistic universals are often justified by cross-linguistic analysis: If all observed languages exhibit a property, the property is taken to be a likely universal, perhaps specified in the cognitive or linguistic systems of language learners and users. In many cases, these patterns are then taken to motivate linguistic theory. Here, we show that cross-linguistic analysis will very ra...