This paper presents our segmentation system developed for the MLP 2017 shared tasks on cross-lingual word segmentation and morpheme segmentation. We model both word and morpheme segmentation as character-level sequence labelling tasks. The prevalent bidirectional recurrent neural network with conditional random fields as the output interface is adapted as the baseline system, which is further i...

This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build an English to Finnish translation system). Our methods use unsupervised morphology induction. Unlike previous work we focus on morphologically productive phrase pairs – our decoder can combine morphemes across phrase bo...

Both dictionary-based and rule-based methods on grapheme-to-phoneme conversion have their own advantages and limitations. For example, a large sized phonetic dictionary and complex morphophonemic rules are required for the dictionary-based method and the LTS(letter to sound) rule-based method itself cannot model the complete morphophonemic constraints. This paper describes a grapheme-to-phoneme...

Most of errors in Korean morphological analysis and POS (Part-of-Speech) tagging are caused by unknown morphemes. This paper presents a generalized unknown morpheme handling method with P OSTAG (POStech TAGger) which is a statistical/rule based hybrid POS tagging system. The generalized unknown morpheme guessing is based on a combination of a morpheme pattern dictionary which encodes general le...

Reading and understanding morphologically complex words can sometimes be a particular challenge to nonnative speakers. For example, compound words consist of multiple free morphemes, oftentimes without explicit marking of the morpheme boundaries. In a lexical decision task, we investigated compound reading in native and nonnative speakers of Dutch. The compounds differed in that the letter bigr...

The first goal of this paper is to determine whether superficially ‘tenseless’ sentences like (1b) contain a covert tense morpheme; I will argue that they do. The second goal is to determine what the semantics of that tense morpheme is. I will propose that (1b) contains a phonologically null tense morpheme which is lexically underspecified with respect to whether the reference time precedes or ...

The continuous emergence of new technical terms and the difficulty of keeping up with neologism in parallel corpora deteriorate the performance of statistical machine translation (SMT) systems. This paper explores the use of morphological information to improve English-to-Chinese translation for technical terms. To reduce the morphemelevel translation ambiguity, we group the morphemes into morp...

Cities grow through the addition of new housing structures, but existing tissue is also modernized. Krakow, like any city with a historical origin, has typologically varied tissue. A large area occupied by multi-family panel-block estates which are being revitalised and scope this revitalization should include sustainable design elements. This paper determines potential for implementing integra...

The goal of Morpho Challenge 2008 was to find and evaluate unsupervised algorithms that provide morpheme analyses for words in different languages. Especially in morphologically complex languages, such as Finnish, Turkish and Arabic, morpheme analysis is important for lexical modeling of words in speech recognition, information retrieval and machine translation. The evaluation in Morpho Challen...

The analysis of stem alternations (e.g. sang as past of sing) is controversial; there is a lasting tension between morphophonological theories (sang is derived from sing by rule) and stem storage theories (sang and sing are stored allomorphs). This paper argues that in many cases of stem alternation (e.g., Spanish diphthongization) the locality conditions on contextual allomorphy provide crucia...