The next generation of text-to-speech systems will have to be more sensitive to sociolinguistic 'style' variables. In order to assist in the adaptation of synthesis to a wider range of contexts, this article examines several sociolinguistic parameters which have been shown to influence the realization of negatives in actual discourse, analyzing their effects on the realization of negatives in E...

Philologist: I need to parse Old French texts of different types (verse, prose, dialects etc.). Do I have to train separate parser models? Computational Linguist: You won’t lose much if you train the parser on all the data you have. P: I can’t do the training myself. What can I expect from existing parser models? C: If the training corpus contained 12th century verse texts, you are best prepare...

Traditional music recommendation systems rely on collaborative filtering to recommend songs or artists. This is computationally efficient and performs well method but is not effective when there is limited or no user input. For these cases, it may be useful to consider content-based recommendation. This paper considers a content-based recommendation system based on lyrical data. We compare a co...

This paper describes two natural language processing systems designed to assist songwriters in obtaining and developing ideas for their craft. Titular is a text synthesis algorithm for automatically generating novel song titles, which lyricists can use to back-form concepts and narrative story arcs. LyriCloud is a word-level language “browser” or “explorer,” which allows users to interactively ...

There are at least two stages of text generation. One is generating the content of the text. The other is generating the language that represents and communicates the content (Thompson 1977). These two stages, though interrelated, have their owta sets of interesting problems and principles. The first stage, generating the semantic content of the text, involves motivating, planning and creating ...

In this paper we report on initial research we have conducted on a computational theory of prose style. Our theory speaks to the following major points: 1. Where in the generation process style is taken into account. 2. How a particular prose style is represented; what "stylistic rules" look like; 3. What modifications to a generation algor i thm are needed; what the deci~'on is that evaluates ...

We investigate the maximal length of repeat as a function of the text length in ten English texts. The maximal length of repeat in the experimental data is greater than a power of the logarithm of the text length where the exponent is close to 2. This result indicates that English prose cannot be modeled by a finite-energy stochastic process, differently than we have previously assumed.

Memory for details of text generally declines relatively rapidly, whereas memory for propositional and context-based meanings is generally more resilient over time. In the present study, we investigated short-term memory for two kinds of verbal material: prose and poetry. Participants heard or read prose stories or poems in which aphrase near the start of the passage served as a target. The tex...