In previous lectures we’ve seen IBM translation models 1 and 2. In this note we will describe phrasebased translation models. Phrase-based translation models give much improved translations over the IBM models, and give state-of-the-art translations for many pairs of languages. Crucially, phrase-based translation models allow lexical entries with more than one word on either the source-language...

Data sparsity is one of the main factors that make word sense disambiguation (WSD) difficult. To overcome this problem we need to find effective ways to use resources other than sense labeled data. In this paper I describe a WSD system that uses a statistical language model based on a large unannotated corpus. The model is used to evaluate the likelihood of various substitutes for a word in a g...

The current study addresses a discrepancy in the psycholinguistic literature about the chronology of information processing during the visual recognition of morphologically complex words. Form-then-meaning accounts of complex word recognition claim that morphemes are processed as units of form prior to any influence of their meanings, whereas form-and-meaning models posit that recognition of co...

We report on a series of experiments addressing the fact that German is less suited than English for word-based n-gram language models. Several systems were trained at different vocabulary sizes using various sets of lexical units. They were evaluated against a newly created corpus of German and Austrian broadcast news.

We describe a method for automatically generating Lexical Transfer Rules (LTRs) from word equivalences using transfer rule templates. Templates are skeletal LTRs, unspecified for words. New LTRs are created by instantiating a template with words, provided that the words belong to the appropriate lexical categories required by the template. We define two methods for creating an inventory of temp...

This paper identifies some linguistic properties of technical terminology, and uses them to formulate an algorithm for identifying technical terms in running text. The grammatical properties discussed are preferred phrase structures: technical terms consist mostly of noun phrases containing adjectives, nouns, and occasionally prepositions; rarely do terms contain verbs, adverbs, or conjunctions...

This paper applies Chinese subword representations, namely character and syllable n-grams, into the TextTiling-based automatic story segmentation of Chinese broadcast news. We show the robustness of Chinese subwords against speech recognition errors, out-of-vocabulary (OOV) words and versatility in word segmentation in lexical matching on errorful Chinese speech recognition transcripts. We prop...

Abstract: Lexical bundles, as building blocks of coherent discourse, have been the subject of much research in the last two decades. While many of such studies have been mainly concerned with  exploring  variations  in  the  use  of  these  word  sequences  across  different  registers  and disciplines, very few have addressed the use of some particular groups of lexical bundles within some gen...

This Master's Thesis concerns research in the automatic analysis of the sub-lexical structure of English words. Sub-lexical structure includes linguistic categories such as syllabification, stress, phonemic representation, phonetics, and spelling. This information could be very useful in all sorts of speech applications, including duration modeling and speech recognition. ANGIE is a system that...

This paper describes the development of a web-service tool for the automatic extraction of Multi-word expressions lexicons, which has been integrated in a distributed platform for the automatic creation of linguistic resources. The main purpose of the work described is thus to provide a (computationally “light”) tool that produces a full lexical resource: multi-word terms/items with relevant an...