Manually performed treebanking is an expensive effort compared with automatic annotation. In return, manual treebanking is generally believed to provide higherquality/value syntactic annotation than automatic methods. Unfortunately, there is little or no empirical evidence for or against this belief, though arguments have been voiced for the high degree of subjectivity in other levels of lingui...

Similarity between words is becoming a generic problem for many applications of computational linguistics, and computing word similarities is determined by word representations. Inspired by the analogies between words and lymphocytes, a lymphocyte-style word representation is proposed. The word representation is built on the basis of dependency syntax of sentences and represent word context as ...

We describe the methods and resources used to build FinnTreeBank-3, a 76.4 million token corpus of Finnish with automatically produced morphological and dependency syntax analyses. Starting from a definition of the target dependency scheme, we show how existing resources are transformed to conform to this definition and subsequently used to develop a parsing pipeline capable of processing a lar...

We argue that Discourse Representation Structures form a suitable level of languageneutral meaning representation for micro planning and surface realisation. DRSs can be viewed as the output of macro planning, and form the rough plan and structure for generating a text. We present the first ideas of building a large DRS corpus that enables the development of broad-coverage, robust text generato...

In dynamic environment, the path planning of mobile robot is a problem difficult to solve. A path planning method for mobile robot based on genetic algorithm is put forward. This method makes use of real number coding and adaptive function with definite physical meaning in the dynamic environment so as to accelerate real-time calculation and improve calculation precision. The simulation result ...