This paper presents a universal morphological feature schema that represents the finest distinctions in meaning that are expressed by overt, affixal inflectional morphology across languages. This schema is used to universalize data extracted from Wiktionary via a robust multidimensional table parsing algorithm and feature mapping algorithms, yielding 883,965 instantiated paradigms in 352 langua...

In this paper we discuss experimental data from three different production studies conducted at the Cornell Language Acquisition Lab (CLAL). The three studies used the elicited imitation method; two of them tested English-speaking children and the third one tested German-speaking children (see Table 1 below). We also discuss data from natural speech studies conducted in different languages and ...

In this paper we investigate the use of rich morphology such as word segmentation, part-of-speech tagging and diacritic restoration to improve Arabic language modeling. We enrich the context by performing morphological analysis on the word history. We use neural network models to integrate this additional information, due to their ability to handle long and enriched dependencies. We experimente...

Translation is the activity producing a source language message with closest and natural equivalent to recipient's language, both in terms of meaning style. The translation process requires grammatical lexical adjustments evade unusual structures language. activities are not only done by humans. With advancement technology, electronic tools have emerged such as Google Translate translate parts ...

This proposal addresses the problem of translation into morphologically rich languages with two new models. In the first, we generate new word types that that are compositional translations of multiple source words (e.g., compounds in German) and augment existing translation models with these. In the second, we propose using automatically learned distributed representations of morphemes and the...

This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presentin...

Although it is well-established that children with Specific Language Impairment characteristically optionally inflect forms that require tense and agreement marking, their abilities with regards to derivational suffixation are less well understood. In this paper we provide evidence from children with Grammatical-Specific Language Impairment (G-SLI) that derivational suffixes, unlike tense and a...

This paper presents an exponential model for translation into highly inflected languages which can be scaled to very large datasets. As in other recent proposals, it predicts targetside phrases and can be conditioned on sourceside context. However, crucially for the task of modeling morphological generalizations, it estimates feature parameters from the entire training set rather than as a coll...

As more robots act in physical proximity to people, it is essential to ensure they make decisions and execute actions that align with human values. To do so, robots need to understand the true intentions behind human-issued commands. In this paper, we define a safe robot as one that receives a natural-language command from humans, considers an action in response to that command, and accurately ...