D-Level Analyzer
Xiaofei Lu
About
D-Level Analyzer is an automatic syntactic complexity analyzer based on the revised Developmental Level scale (Rosenberg & Abbeduto 1987; Covington et al. 2006). This analyzer assigns each sentence in an input text to one of eight levels, depending on the structure of the sentence. This software is an implementation of the system described in:
- Lu, Xiaofei (2009). Automatic measurement of syntactic complexity in child language acquisition. International Journal of Corpus Linguistics, 14(1):3-28.
To use the analyzer, the user needs to first tag a raw text using a part-of-speech tagger that follows the Penn Treebank tagging scheme and then parse the text using model 2 of Collins' parser. The analyzer is implemented in python and runs on UNIX-like systems (Unix, LINUX, and Mac OS) with emacs and python 2.5 or higher installed. The analyzer takes as input the output of Collins' parser (using model 2) and generates a file that contains the developmental levels (represented as numbers between 0 and 7) of the sentences in the input text in a one-number-per-line format. The analyzer references the regularized version of NOMLEX (Macleod et al. 1998) for nominalization recognition, which should be installed in the same directory as the analyzer.
Download
References
- Covington, M. A., He, C., Brown, C., Naçi, L. & Brown, J. (2006). How complex is that sentence? A proposed revision of the Rosenberg and Abbeduto D-Level scale. CASPR Research Report 2006-01. Athens, GA: The University of Georgia, Artificial Intelligence Center.
- Macleod, C., Grishman, R., Meyers, A., Barrett, L. & Reeves, R. (1998). NOMLEX: A lexicon of nominalizations. In Proceedings of the 8th International Congress of the European Association for Lexicography. Liege, Belgium.
- Rosenberg, S. & Abbeduto, L. (1987). Indicators of linguistic competence in the peer group conversational behavior of mildly retarded adults. Applied Psycholinguistics, 8(1), 19-32.