No abstract

This paper presents several techniques for managing ambiguity in LFG parsing of Wolof, a less-resourced Niger-Congo language. Ambiguity is pervasive in Wolof and This raises a number of theoretical and practical issues for managing ambiguity associated with different objectives. From a theoretical perspective, the main aim is to design a large-scale grammar for Wolof that is able to make linguistically motivated disambiguation decisions, and to find appropriate ways of controlling ambiguity at important interface representations. The practical aim is to develop disambiguation strategies to improve the performance of the grammar in terms of efficiency, robustness and coverage.To achieve these goals, different avenues are explored to manage ambiguity in the Wolof grammar, including the formal encoding of noun class indeterminacy, lexical specifications, the use of Constraint Grammar models (Karlsson 1990) for morphological disambiguation, the application of the c-structure pruning mechanism (Cahill et al. 2007, 2008; Crouch et al. 2013), and the use of optimality marks for preferences (Frank et al. 1998, 2001). The parsing system is further controlled by packing ambiguities. In addition, discriminant-based techniques for parse disambiguation (Rosén et al. 2007) are applied for treebanking purposes.

No abstract

No abstract

This paper presents a finite-state transducer (FST) for tokenizing and normalizing natural texts that are input to a large-scale LFG grammar for Wolof. In the early stage of grammar development, a language-independent tokenizer was used to split the input stream into a unique sequence of tokens. is simple transducer took into account general character classes, without using any language-specific information. However, at a later stage of grammar development, uncovered and non-trivial tokenization issues arose, including issues related to multi-word expressions (MWEs), clitics and text normalization. As a consequence, the tokenizer was extended by integrating FST components. is extension was crucial for scaling the hand-written grammar to free text and for enhancing the performance of the parser.