Efficiency, memory, ambiguity, robustness and scalability are the central issues in natural language parsing. Because of the complexity of natural language, different parsers may be suited only to certain subgrammars. In addition, grammar maintenance and updating may have adverse effects on tuned parsers. Motivated by these concerns, [25] proposed a grammar partitioning and top-down parser composition mechanism for loosely restricted Context-Free Grammars (CFGs). In this paper, we report on significant progress, i.e., (1) developing guidelines for the grammar partition through a set of heuristics, (2) devising a new mix-strategy composition algorithms for any rule-based grammar partition in a lattice framework, and 3) initial but encouraging parsing results for Chinese and English queries from an Air Travel Information System (ATIS) corpus.

This paper reviews and summarizes six different types of extra-grammatical phenomena and their corresponding recovery principles at the syntactic level, and describes some techniques used to deal with four of them completely within an Extended GLR parser (EGLR). Partial solutions to the remaining two by the EGLR parser are also discussed. The EGLR has been implemented.