We present a novel PCFG-based architecture for robust probabilistic generation based on wide-coverage LFG approximations (Cahill et al., 2004) automatically extracted from treebanks, maximising the probability of a tree given an f-structure. We evaluate our approach using stringbased evaluation. We currently achieve coverage of 95.26%, a BLEU score of 0.7227 and string accuracy of 0.7476 on the Penn-II WSJ Section 23 sentences of length ≤20. 1

In this paper we describe and evaluate di#erent statistical models for the task of realization ranking, i.e. the problem of discriminating between competing surface realizations generated for a given input semantics. Three models are trained and tested; an n-gram language model, a discriminative maximum entropy model using structural features, and a combination of these two. Our realization component forms part of a larger, hybrid MT system.

This paper explores the use of statistical machine translation (SMT) methods for tactical natural language generation. We present results on using phrase-based SMT for learning to map meaning representations to natural language. Improved results are obtained by inverting a semantic parser that uses SMT methods to map sentences into meaning representations. Finally, we show that hybridizing these two approaches results in still more accurate generation systems. Automatic and human evaluation of generated sentences are presented across two domains and four languages. 1

This paper reports on progress towards developing the first broad coverage English surface realizer for Combinatory Categorial Grammar (CCG). The paper provides initial automatic evaluation results which are roughly comparable to those reported with other formalisms when using a (nonblind) grammar derived from the development section of the CCGbank; the results are worse, though still respectable, when using the standard dev/train/test splits, highlighting the need for better lexical smoothing and more focused search. The paper also shows that factored language models that interpolate word-level n-grams with n-grams over POS tags and supertags provide similar absolute performance improvements over word-level n-grams as have been observed with parsing-inspired log-linear models. 1

in human-robot interaction

In lexicalized grammatical formalisms, it is possible to separate lexical category assignment from the combinatory processes that make use of such categories, such as parsing and realization. We adapt techniques from supertagging — a relatively recent technique that performs complex lexical tagging before full parsing (Bangalore and Joshi, 1999; Clark, 2002) — for chart realization in OpenCCG, an open-source NLP toolkit for CCG. We call this approach hypertagging, as it operates at a level “above ” the syntax, tagging semantic representations with syntactic lexical categories. Our results demonstrate that a hypertagger-informed chart realizer can achieve substantial improvements in realization speed (being approximately twice as fast) with superior realization quality.

In this paper we describe and evaluate several statistical models for the task of realization ranking, i.e. the problem of discriminating between competing surface realizations generated for a given input semantics. Three models (and several variants) are trained and tested: an-gram language model, a discriminative maximum entropy model using structural information (and incorporating the language model as a separate feature), and finally an SVM ranker trained on the same feature set. The resulting hybrid tactical generator is part of a larger, semantic transfer MT system. 1

Surface realisers divide into those used in generation (NLG geared realisers) and those mirroring the parsing process (Reversible realisers). While the first rely on grammars not easily usable for parsing, it is unclear how the second type of realisers could be parameterised to yield from among the set of possible paraphrases, the paraphrase appropriate to a given generation context. In this paper, we present a surface realiser which combines a reversible grammar (used for parsing and doing semantic construction) with a symbolic means of selecting paraphrases. 1

We investigate two methods for enhancing variation in the output of a stochastic surface realiser: choosing from among the highest-scoring realisation candidates instead of taking the single highestscoring result (ε-best sampling), and penalising the words from earlier sentences in a discourse when generating later ones (anti-repetition scoring). In a human evaluation study, subjects were asked to compare texts generated with and without the variation enhancements. Strikingly, subjects judged the texts generated using these two methods to be better written and less repetitive than the texts generated with optimal n-gram scoring; at the same time, no significant difference in understandability was found between the two versions. In analysing the two methods, we show that the simpler ε-best sampling method is considerably more prone to introducing dispreferred variants into the output, indicating that best results can be obtained using antirepetition scoring with strict or no ε-best sampling. 1

We extend a recently proposed algorithm for n-best unpacking of parse forests to deal efficiently with (a) Maximum Entropy (ME) parse selection models containing important classes of non-local features, and (b) forests produced by unification grammars containing significant proportions of globally inconsistent analyses. The new algorithm empirically exhibits a linear relationship between processing time and the number of analyses unpacked at all degrees of ME feature nonlocality; in addition, compared with agendadriven best-first parsing and exhaustive parsing with post-hoc parse selection it leads to improved parsing speed, coverage, and accuracy.