Two important recent trends in natural language generation are (i) probabilistic techniques and (ii) comprehensive approaches that move away from traditional strictly modular and sequential models. This paper reports experiments in which pcru – a generation framework that combines probabilistic generation methodology with a comprehensive model of the generation space – was used to semi-automatically create five different versions of a weather forecast generator. The generators were evaluated in terms of output quality, development time and computational efficiency against (i) human forecasters, (ii) a traditional handcrafted pipelined nlg system and (iii) a halogen-style statistical generator. The most striking result is that despite acquiring all decision-making abilities automatically, the best pcru generators produce outputs of high enough quality to be scored more highly by human judges than forecasts written by experts.

Finite-state technology is considered the preferred model for representing the phonology and morphology of natural languages. The attractiveness of this technology for natural language processing stems from four sources: modularity of the design, due to the closure properties of regular languages and relations; the compact representation that is achieved through minimization; efficiency, which is a result of linear recognition time with finite-state devices; and reversibility, resulting from the declarative nature of such devices. However, when wide-coverage morphological grammars are considered, finite-state technology does not scale up well, and the benefits of this technology can be overshadowed by the limitations it imposes as a programming environment for language processing. This paper investigates the strengths and weaknesses of existing technology, focusing on various aspects of large-scale grammar development. Using a real-world case study, we compare a finite-state implementation with an equivalent Java program with respect to ease of development, modularity, maintainability of the code, and space and time efficiency. We identify two main problems, abstraction and incremental development, which are currently not addressed sufficiently well by finite-state technology, and which we believe should be the focus of future research and development.

The limits on predictability and refinement of English structural annotation are examined by comparing independent annotations, by experienced analysts using the same detailed published guidelines, of a common sample of written texts. Three conclusions emerge. First, while it is not easy to define watertight boundaries between the categories of a comprehensive structural annotation scheme, limits on inter-annotator agreement are in practice set more by the difficulty of conforming to a well-defined scheme than by the difficulty of making a scheme well defined. Secondly, although usage is often structurally ambiguous, commonly the alternative analyses are logical distinctions without a practical difference – which raises questions about the role of grammar in human linguistic behaviour. Finally, one specific area of annotation is strikingly more problematic than any other area examined, though this area (classifying the functions of clause-constituents) seems a particularly significant one for human language use. These findings should be of interest both to computational linguists and to students of language as an aspect of human cognition.

We describe SkillSum, a Natural Language Generation (NLG) system that generates a personalised feedback report for someone who has just completed a screening assessment of their basic literacy and numeracy skills. Because many SkillSum users have limited literacy, the generated reports must be easily comprehended by people with limited reading skills; this is the most novel aspect of SkillSum, and the focus of this paper. We used two approaches to maximise readability. First, for determining content and structure (document planning), we did not explicitly model readability, but rather followed a pragmatic approach of repeatedly revising content and structure following pilot experiments and interviews with domain experts. Second, for choosing linguistic expressions (microplanning), we attempted to formulate explicitly the choices that enhanced readability, using a constraints approach and preference rules; our constraints were based on corpus analysis and our preference rules were based on psycholinguistic findings. Evaluation of the SkillSum system was twofold: it compared the usefulness of NLG technology to that of canned text output, and it assessed the effectiveness of the readability model. Results showed that NLG was more effective than canned text at enhancing users' knowledge of their skills, and also suggested that the empirical ‘revise based on experiments and interviews’ approach made a substantial contribution to readability as well as our explicit psycholinguistically inspired models of readability choices.

Automatic pronunciation of unknown words (i.e., those not in the system dictionary) is a difficult problem in text-to-speech (TTS) synthesis. Currently, many data-driven approaches have been applied to the problem, as a backup strategy for those cases where dictionary matching fails. The difficulty of the problem depends on the complexity of spelling-to-sound mappings according to the particular writing system of the language. Hence, the degree of success achieved varies widely across languages but also across dictionaries, even for the same language with the same method. Further, the sizes of the training and test sets are an important consideration in data-driven approaches. In this paper, we study the variation of letter-to-phoneme transcription accuracy across seven European languages with twelve different lexicons. We also study the relationship between the size of dictionary and the accuracy obtained. The largest dictionaries of each language have been partitioned into ten approximately equal-sized subsets and combined to give ten different-sized test sets. In view of its superior performance in previous work, the transcription method used is pronunciation by analogy (PbA). Best results are obtained for Spanish, generally believed to have a very regular (‘shallow’) orthography, and poorest results for English, a language whose irregular spelling system is legendary. For those languages for which multiple dictionaries were available (i.e., French and English), results were found to vary across dictionaries. For the relationship between dictionary size and transcription accuracy, we find that as dictionary size grows, so performance grows monotonically. However, the performance gain decelerates (tends to saturate) as the dictionary increases in size; the relation can simply be described by a logarithmic regression, one parameter of which (α) can be taken as quantifying the depth of orthography of a language. We find that α for a language is significantly correlated with transcription performance on a small dictionary (approximately 10,000 words) for that language, but less so for asymptotic performance. This may be because our measure of asymptotic performance is unreliable, being extrapolated from the fitted logarithmic regression.

The semantic annotation of texts with senses from a computational lexicon is a complex and often subjective task. As a matter of fact, the fine granularity of the WordNet sense inventory [Fellbaum, Christiane (ed.). 1998. WordNet: An Electronic Lexical Database MIT Press], a de facto standard within the research community, is one of the main causes of a low inter-tagger agreement ranging between 70% and 80% and the disappointing performance of automated fine-grained disambiguation systems (around 65% state of the art in the Senseval-3 English all-words task). In order to improve the performance of both manual and automated sense taggers, either we change the sense inventory (e.g. adopting a new dictionary or clustering WordNet senses) or we aim at resolving the disagreements between annotators by dealing with the fineness of sense distinctions. The former approach is not viable in the short term, as wide-coverage resources are not publicly available and no large-scale reliable clustering of WordNet senses has been released to date. The latter approach requires the ability to distinguish between subtle or misleading sense distinctions. In this paper, we propose the use of structural semantic interconnections – a specific kind of lexical chains – for the adjudication of disagreed sense assignments to words in context. The approach relies on the exploitation of the lexicon structure as a support to smooth possible divergencies between sense annotators and foster coherent choices. We perform a twofold experimental evaluation of the approach applied to manual annotations from the SemCor corpus, and automatic annotations from the Senseval-3 English all-words competition. Both sets of experiments and results are entirely novel: structural adjudication allows to improve the state-of-the-art performance in all-words disambiguation by 3.3 points (achieving a 68.5% F1-score) and attains figures around 80% precision and 60% recall in the adjudication of disagreements from human annotators.