Richard Sproat

Emotions from Text: Machine Learning for Text-based Emotion Prediction

In addition to information, text contains attitudinal, and more specifically, emotional content. This paper explores the text-based emotion prediction problem empirically, using supervised machine learning with the SNoW learning architecture. The goal is to classify the emotional affinity of sentences in the narrative domain of childrens fairy tales, for subsequent usage in appropriate expressive rendering of text-to-speech synthesis. Initial experiments on a preliminary data set of 22 fairy tales show encouraging results over a naive baseline and BOW approach for classification of emotional versus non-emotional contents, with some dependency on parameter tuning. We also discuss results for a tripartite model which covers emotional valence, as well as feature set alternations. In addition, we present plans for a more cognitively sound sequential model, taking into consideration a larger set of basic emotions.

WordsEye: an automatic text-to-scene conversion system

Natural language is an easy and effective medium for describing visual ideas and mental images. Thus, we foresee the emergence of language-based 3D scene generation systems to let ordinary users quickly create 3D scenes without having to learn special software, acquire artistic skills, or even touch a desktop window-oriented interface. WordsEye is such a system for automatically converting text into representative 3D scenes. WordsEye relies on a large database of 3D models and poses to depict entities and actions. Every 3D model can have associated shape displacements, spatial tags, and functional properties to be used in the depiction process. We describe the linguistic analysis and depiction techniques used by WordsEye along with some general strategies by which more abstract concepts are made depictable.

Progress in speech synthesis

1. Section Introduction: Signal Processing and Source Modelling 2.Synthesizing Allophonic Glottaliztion 3. Text-to-Speech SynthesisWith Dynamic Control of Speech 4. Modifiction of the the AperiodicComponent of Speech Signals for Synthesis 5. On the Use of aSinusoidal Model for Speech Synthesis in Text-to-Speech 6. SectionIntroduction: The Analysis of Text in Text-to-Speech Synthesis 7.Language-Independent Data-Oriented Grapheme-to Phoneme Conversion 8.All-Prosodic Speech Synthesis 9. A Model of Timing for Non-SegmentalPhonological Structure 10. a Complete Linguistic analysis for anItalian Text-to-Speech System 11. Discourse Structural Constraints onAccent in Narrative 12. Homograph Disambiguation in Text-to-SpeechSynthesis 13. Section Introduction: Talking Heads in Speech 1= Synthesis 14. Section Introduction: Articulatory Synthesis and VisualSpeech: Bridging the Gap Between Speech Science and SpeechApplications 15. Speech Models and Speech Synthesis 16. A 3D Modelof the Lips and of the Jaw for Visual Speech Synthesis 17. AFramework for Synthesis of Segments based on Pseudo-articulatoryparameters 18. Biomechanical and Physiologically based Speech

Mining correlated bursty topic patterns from coordinated text streams

Previous work on text mining has almost exclusively focused on a single stream. However, we often have available multiple text streams indexed by the same set of time points (called coordinated text streams), which offer new opportunities for text mining. For example, when a major event happens, all the news articles published by different agencies in different languages tend to cover the same event for a certain period, exhibiting a correlated bursty topic pattern in all the news article streams. In general, mining correlated bursty topic patterns from coordinated text streams can reveal interesting latent associations or events behind these streams. In this paper, we define and study this novel text mining problem. We propose a general probabilistic algorithm which can effectively discover correlated bursty patterns and their bursty periods across text streams even if the streams have completely different vocabularies (e.g., English vs Chinese). Evaluation of the proposed method on a news data set and a literature data set shows that it can effectively discover quite meaningful topic patterns from both data sets: the patterns discovered from the news data set accurately reveal the major common events covered in the two streams of news articles (in English and Chinese, respectively), while the patterns discovered from two database publication streams match well with the major research paradigm shifts in database research. Since the proposed method is general and does not require the streams to share vocabulary, it can be applied to any coordinated text streams to discover correlated topic patterns that burst in multiple streams in the same period.

The First International Chinese Word Segmentation Bakeoff

This paper presents the results from the ACL-SIGHAN-sponsored First International Chinese Word Segmentation Bakeoff held in 2003 and reported in conjunction with the Second SIGHAN Workshop on Chinese Language Processing, Sapporo, Japan. We give the motivation for having an international segmentation contest (given that there have been two within-China contests to date) and we report on the results of this first international contest, analyze these results, and make some recommendations for the future.

An Efficient Compiler for Weighted Rewrite Rules

Context-dependent rewrite rules are used in many areas of natural language and speech processing. Work in computational phonology has demonstrated that, given certain conditions, such rewrite rules can be represented as finite-state transducers (FSTs). We describe a new algorithm for compiling rewrite rules into FSTs. We show the algorithm to be simpler and more efficient than existing algorithms. Further, many of our applications demand the ability to compile weighted rules into weighted FSTs, transducers generalized by providing transitions with weights. We have extended the algorithm to allow for this.

Compilation of Weighted Finite-State Transducers from Decision Trees

We report on a method for compiling decision trees into weighted finite-state transducers. The key assumptions are that the tree predictions specify how to rewrite symbols from an input string, and the decision at each tree node is stateable in terms of regular expressions on the input string. Each leaf node can then be treated as a separate rule where the left and right contexts are constructable from the decisions made traversing the tree from the root to the leaf. These rules are compiled into transducers using the weighted rewite-rule rule-compilation algorithm described in (Mohri and Sproat, 1996).

The Cross-Linguistic Distribution of Adjective Ordering Restrictions

English displays well-known restrictions on the ordering of multiple prenominal adjectival modifiers (see Bloomfield, 1933; Whorf, 1945; Lance, 1968; Vendler, 1968; Quirk et al, 1972 among numerous others). Most descriptions include a hierarchy such as the following: QUALITY > SIZE > SHAPE > COLOR > PROVENANCE.1

Named Entity Transliteration with Comparable Corpora

In this paper we investigate Chinese-English name transliteration using comparable corpora, corpora where texts in the two languages deal in some of the same topics --- and therefore share references to named entities --- but are not translations of each other. We present two distinct methods for transliteration, one approach using phonetic transliteration, and the second using the temporal distribution of candidate pairs. Each of these approaches works quite well, but by combining the approaches one can achieve even better results. We then propose a novel score propagation method that utilizes the co-occurrence of transliteration pairs within document pairs. This propagation method achieves further improvement over the best results from the previous step.

MAP adaptation of stochastic grammars

This paper investigates supervised and unsupervised adaptation of stochastic grammars, including n-gram language models and probabilistic context-free grammars (PCFGs), to a new domain. It is shown that the commonly used approaches of count merging and model interpolation are special cases of a more general maximum a posteriori (MAP) framework, which additionally allows for alternate adaptation approaches. This paper investigates the effectiveness of different adaptation strategies, and, in particular, focuses on the need for supervision in the adaptation process. We show that n-gram models as well as PCFGs benefit from either supervised or unsupervised MAP adaptation in various tasks. For n-gram models, we compare the benefit from supervised adaptation with that of unsupervised adaptation on a speech recognition task with an adaptation sample of limited size (about 17h), and show that unsupervised adaptation can obtain 51% of the 7.7% adaptation gain obtained by supervised adaptation. We also investigate the benefit of using multiple word hypotheses (in the form of a word lattice) for unsupervised adaptation on a speech recognition task for which there was a much larger adaptation sample available. The use of word lattices for adaptation required the derivation of a generalization of the well-known Good-Turing estimate. Using this generalization, we derive a method that uses Monte Carlo sampling for building Katz backoff models. The adaptation results show that, for adaptation samples of limited size (several tens of hours), unsupervised adaptation on lattices gives a performance gain over using transcripts. The experimental results also show that with a very large adaptation sample (1050h), the benefit from transcript-based adaptation matches that of lattice-based adaptation. Finally, we show that PCFG domain adaptation using the MAP framework provides similar gains in F-measure accuracy on a parsing task as was seen in ASR accuracy improvements with n-gram adaptation. Experimental results show that unsupervised adaptation provides 37% of the 10.35% gain obtained by supervised adaptation.