Symbolic Parsing and Probabilistic Decision Making. the Speech and Language Experience with Hybrid Information Processing
نویسنده
چکیده
In natural language technology up to now most projects were based on either logical and linguistic methods or they were strictly based on stochastic techniques alone borrowed from pattern recognition. This article discusses hybrid symbolic and stochastic techniques in natural language processing as they are currently explored in many projects and in particular in our work within the Verbmobil project. 1 First a short introduction is given on stochastic and on symbolic methods followed by a discussion of their accuracy for natural language processing. The rest of the article describes hybrid techniques which are typical in current research on speech and natural language parsing and \understanding".
منابع مشابه
بررسی مقایسهای تأثیر برچسبزنی مقولات دستوری بر تجزیه در پردازش خودکار زبان فارسی
In this paper, the role of Part-of-Speech (POS) tagging for parsing in automatic processing of the Persian language is studied. To this end, the impact of the quality of POS tagging as well as the impact of the quantity of information available in the POS tags on parsing are studied. To reach the goals, three parsing scenarios are proposed and compared. In the first scenario, the parser assigns...
متن کاملAn improved joint model: POS tagging and dependency parsing
Dependency parsing is a way of syntactic parsing and a natural language that automatically analyzes the dependency structure of sentences, and the input for each sentence creates a dependency graph. Part-Of-Speech (POS) tagging is a prerequisite for dependency parsing. Generally, dependency parsers do the POS tagging task along with dependency parsing in a pipeline mode. Unfortunately, in pipel...
متن کاملA Context-Sensitive Model for Probabilistic LR Parsing of Spoken Language with Transformation-Based Postprocessing
This paper describes a hybrid approach to spontaneous speech parsing. The implemented parser uses an extended probabilistic LR parsing model with rich context and its output is postprocessed by a symbolic tree transformation routine that tries to eliminate systematic errors of the parser. The parser has been trained for three different languages and was successfully integrated in the Verbmobil ...
متن کاملCommittee-based Decision Making in Probabiiistic Partial Parsing
This paper explores two directions ibr the next step beyond the state of the art of statistical parsing: probabilistic partial parsing and committee-based decision making. Probabilistic partial parsing is a probabilistic extension of the existing notion of partial parsing~ which enables fine-grained arbitrary choice on the tradeoff between accuracy and coverage. Committeebased decision making i...
متن کاملNew trends in natural language processing: statistical natural language processing.
The field of natural language processing (NLP) has seen a dramatic shift in both research direction and methodology in the past several years. In the past, most work in computational linguistics tended to focus on purely symbolic methods. Recently, more and more work is shifting toward hybrid methods that combine new empirical corpus-based methods, including the use of probabilistic and informa...
متن کامل