We consider using online language models for translating multiple streams which naturally arise on the Web. After establishing that using just one stream can degrade translations on different domains, we present a series of simple approaches which tackle the problem of maintaining translation performance on all streams in small space. By exploiting the differing throughputs of each stream and h...

The digital text written in an Indian script is difficult to use as such. This is because, there are a number of font formats available for typing, and these font-formats are not mutually compatible. Gurmukhi alone has more than 225 popular ASCII-based fonts whereas this figure is 180 in case of Devanagari. To read the text written in a particular font, that font is required to be installed on ...

How can the quality of a mobile ad hoc network (MANET) be quantified? This work aims at an answer based on the lower network layers, i.e. on connectivity between the wireless nodes, using statistical methods. A number of different quality measures are introduced and classified according to their scaling behaviour. They are analysed in a statistical model of a 1-dimensional MANET system (corresp...

Wireless Sensor Networks closely resemble a human behaviour model, in which a number of nodes that have just met are able to communicate with each other based on mutual trust levels developed over a period of time. WSNs are characterised by their performance of an additional function to the traditional functions of an ad-hoc network, which is monitoring events and reporting data and, as such, t...

Researchers in the fields of psycholinguistics and neurolinguistics increasingly test their experimental hypotheses against probabilistic models of language. VALEX (Korhonen, Krymolowski & Briscoe, 2006) is a large-scale verb lexicon that specifies verb usage as probability distributions over a set of 163 verb SUBCATEGORIZATION FRAMES (SCFs). VALEX has proved to be a popular computational lingu...

Wireless Sensor Networks closely resemble a human behaviour model, in which a number of nodes that have just met are able to communicate with each other based on mutual trust levels developed over a period of time. WSNs are characterised by their performance of an additional function to the traditional functions of an ad-hoc network, which is monitoring events and reporting data and, as such, t...

Complex Language Models cannot be easily integrated in the first pass decoding of a Statistical Machine Translation system – the decoder queries the LM a very large number of times; the search process in the decoding builds the hypotheses incrementally and cannot make use of LMs that analyze the whole sentence. We present in this paper the Language Computer’s system for WMT06 that employs LMpow...

Identifying textual inferences, where the meaning of one text follows from another, is a general underlying task within many natural language applications. Commonly, it is approached either by generative syntactic-based methods or by “lightweight” heuristic lexical models. We suggest a model which is confined to simple lexical information, but is formulated as a principled generative probabilis...

Many successful approaches to semantic parsing build on top of the syntactic analysis of text, and make use of distributional representations or statistical models to match parses to ontology-specific queries. This paper presents a novel deep learning architecture which provides a semantic parsing system through the union of two neural models of language semantics. It allows for the generation ...

Conveying information in a false or indirect manner in consideration of listeners’ wants (i.e. being polite) seemingly contradicts an important goal of a cooperative speaker: information transfer. We propose that a cooperative speaker considers both epistemic utility, or utility of providing the listener new and accurate information, and social utility, or utility of maintaining or boosting the...