Natural Language Parsing

Proper parsing can resolve part-of-speech ambiguity problems that finite state (ie HMM parsers) fail on, such as Example 49 above. 

The syntax can help determine sentential prominence patterns (explained in Section 6.8). 

The syntax gives a basic grouping of words, and these groupings strongly influence the prosodic phrase structure of the utterance (explained in Section 6.7). 

---

As with previous problems, we settle this issue by deciding what we think is best for TTS. While it is common in natural language parsing to expand contractions and regard them as two... 

Brodie, C., Karat, C.M., Karat, J. An empirical study of natural language parsing of privacy policy rules using the SPARCLE policy workbench. In Proceedings of the 2006 Symposium on Usable Privacy and Security (SOUPS 2006), New York, NY, July 2006, pp. 8-19. ACM Press, New York (2006)... 

Additional rules are used to shift prominence in cases where the parses would produce two prominent syllables side by side. We also find that many types of non-natural language entities have characteristic patterns. For example, it is common place to find telephone numbers read with a particular stress pattern (and indeed phrasing). Producing the correct stress patterns for these is often fairly straight forward and the creation of these patterns can be integrated into the verbalisation process. 

---