We present a technique which complements Hidden Markov Models by incorporating some lexicalized states representing syntactically uncommon words. Our approach examines the distribution of transitions, selects the uncommon words, and makes lexicalized states for the words. We performed a part-of-speech tagging experiment on the Brown corpus to evaluate the resultant language model and discovered...

Sequential LSTMs have been extended to model tree structures, giving competitive results for a number of tasks. Existing methods model constituent trees by bottom-up combinations of constituent nodes, making direct use of input word information only for leaf nodes. This is different from sequential LSTMs, which contain references to input words for each node. In this paper, we propose a method ...

Previous work on German parsing has provided confusing and conflicting results concerning the difficulty of the task and whether techniques that are useful for English, such as lexicalization, are effective for German. This paper aims to provide some understanding and solid baseline numbers for the task. We examine the performance of three techniques on three treebanks (Negra, Tiger, and TüBa-D...

Linked Open Data (LOD) is growing rapidly as a source of structured knowledge used in a variety of text processing applications. However, the applications using the LOD need to be able to mediate between the front end user interfaces and LOD. This often requires a natural language interpretation of this structured, linked data. We demonstrate a middle-tier framework that can generate patterns w...

In this squib we explore a strictly derivational explanation for the differences in possible middle voice constructions in Norwegian and Swedish. Whereas Norwegian allows by its lexical s-passive construction as well as a complex adjectival construction to stand in for middle semantics, only the latter option is available in Swedish. We argue that this contrast lies in the lexicalization of for...

There has been a hot debate on the typological status of Mandarin Chinese in Talmyan framework of Verb-framed languages (V-languages) and Satellite-framed Languages(S-languages). However, most previous studies focus on motion events, while other macro-events (Talmy, 2000) receive little attention. The present study aims to investigate event of realization in Mandarin Chinese with experimental m...

This research aims to investigate the types and factors of code mixing which found in official twitter account BKN (Indonesia National Civil Service Agency) during registration civil servant’s candidate November 2019. Qualitative approach was conducted analyze social mixing. Observation method with writing technique used collect data. Data reduction, data display drawing conclusion are process ...

This paper describes ongoing research on NLG for dialogue systems. Sentence planning is performed by selecting the appropriate template, while previously developed transfer and generation components of a transfer–based MT architecture perform the lexicalization and linguistic realization processes in the generation process. This approach allows for multilingual generation since there is a clear...