From this , a <term> language learning model </term> was implemented in the program <term> RINA </term> , which enhances its own <term> lexical hierarchy </term> by processing examples in context .
We believe that these <term> evaluation techniques </term> will provide information about both the <term> human language learning process </term> , the <term> translation process </term> and the <term> development </term> of <term> machine translation systems </term> . This , the first experiment in a series of experiments , looks at the <term> intelligibility </term> of <term> MT output </term> .
This method of using <term> expectations </term> to aid the understanding of <term> scruffy texts </term> has been incorporated into a working <term> computer program </term> called <term> NOMAD </term> , which understands <term> scruffy texts </term> in the domain of Navy messages . This abstract describes a <term> natural language system </term> which deals usefully with <term> ungrammatical input </term> and describes some actual and potential applications of it in <term> computer aided second language learning </term> .
<term> Simulated annealing approach </term> is used to implement this <term> alignment algorithm </term> .
Like <term> semantic grammar </term> , this allows easy exploitation of <term> limited domain semantics </term> .
This paper proposes a method for resolving this <term> ambiguity </term> based on <term> statistical information </term> obtained from <term> dialogue corpora </term> .
We incorporate this analysis into a <term> diagnostic tool </term> intended for <term> developers </term> of <term> machine translation systems </term> , and demonstrate how our application can be used by <term> developers </term> to explore <term> patterns </term> in <term> machine translation output </term> .
In this approach , the definitions of the <term> structure </term> and <term> surface representation </term> of <term> domain entities </term> are grouped together .
Using this <term> approach </term> , we extract <term> parallel data </term> from large <term> Chinese , Arabic , and English non-parallel newspaper corpora </term> .
The <term> generalized LR parsing </term> is enhanced in this approach .
A <term> pilot system </term> has shown great effectiveness of this approach .
We have built and will demonstrate an application of this approach called <term> LCS-Marine </term> .
Like most existing approaches it utilizes <term> clustering of word co-occurrences </term> . This approach differs from other approaches to <term> WSI </term> in that it enhances the effect of the <term> one sense per collocation observation </term> by using triplets of <term> words </term> instead of pairs .
We describe our use of this approach in numerous fielded <term> user studies </term> conducted with the U.S. military .
From different reasons among which the speed of processing prevails they are usually based on <term> dictionaries of word forms </term> instead of <term> words </term> . This approach is sufficient for languages with little <term> inflection </term> such as <term> English </term> , but fails for <term> highly inflective languages </term> such as <term> Czech </term> , <term> Russian </term> , <term> Slovak </term> or other <term> Slavonic languages </term> .
Experiments show that this approach is superior to a single <term> decision-tree classifier </term> .
The value of this approach is that as the <term> operational semantics </term> of <term> natural language applications </term> improve , even larger improvements are possible .
The principle advantage of this approach is that knowledge concerning translation equivalence of expressions may be directly exploited , obviating the need for answers to <term> semantic questions </term> that we do not yet have .
A novel <term> bootstrapping approach </term> to <term> Named Entity ( NE ) tagging </term> using <term> concept-based seeds </term> and <term> successive learners </term> is presented . This approach only requires a few <term> common noun </term> or <term> pronoun </term><term> seeds </term> that correspond to the <term> concept </term> for the targeted <term> NE </term> , e.g. he/she/man / woman for <term> PERSON NE </term> .
After introducing this approach to <term> MT system </term> design , and the basics of <term> monolingual UCG </term> , we will show how the two can be integrated , and present an example from an implemented <term> bi-directional Engllsh-Spanish fragment </term> .
hide detail