We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to l...

A machine translation model has been proposed where an input is translated through both source-language and target-language paraphrasing processes. We have implemented our prototype model for the Japanese-Chinese language pair. This paper describes our core idea of translation, where a source language paraphraser and a language transfer cooperates in translation by exchanging information about ...

We develop a module-based framework for constraint modeling where it is possible to combine different constraint modeling languages and exploit their strengths in a flexible way. In the framework a constraint model consists of modules with clear input/output interfaces. When combining modules, apart from the interface, a module is a black box whose internals are invisible to the outside world. ...

What is a statistical method and how can it be used in natural language processing (NLP)? In this paper, we start from a definition of NLP as concerned with the design and implementation of effective natural language input and output components for computational systems. We distinguish three kinds of methods that are relevant to this enterprise: application methods, acquisition methods, and eva...

We address the problem of cross-language adaptation for question-question similarity reranking in community question answering, with the objective to port a system trained on one input language to another input language given labeled training data for the first language and only unlabeled data for the second language. In particular, we propose to use adversarial training of neural networks to l...

Currently, inputting mathematical formulas into a document using a PC requires more effort by users than inputting normal text. This fact inhibits the spreading of mathematical formulas as internet contents. We propose a method for predicting user’s inputs of mathematical formulas using an N-gram model: a popular probabilistic language model in natural language processing. Mathematical formulas...

The RAGS project aims to define a reference architecture for Natural Language Generation (NLG) systems. Currently the major part of this architecture consists of a set of datatype definitions for specifying the input and output formats for modules within NLG systems. In this paper we describe our efforts to reinterpret an existing NLG system in terms of these definitions. The system chosen was ...

A fully integrated approach to Speech-Input Language Translation in limited-domain applications is presented. The mapping from the input to the output language is modeled in terms of a nite state translation model which is learned from examples of input-output sentences of the task considered. This model is tightly integrated with standard acoustic-phonetic models of the input language and the ...

the meaning of an idiomatic expression cannot be transparently worked out from the meanings of its constituent words due to its figurative and unpredictable nature. consequently, the syntactic composition and the structural paradigm of an idiomatic expression are supposed to be the same in every context. however, this is not the case in the institutionalized second language varieties of english...