We present the RAGS (Reference Architecture for Generation Systems) framework: a specification of an abstract Natural Language Generation (NLG) system architecture to support sharing, re-use, comparison and evaluation of NLG technologies. We argue that the evidence from a survey of actual NLG systems calls for a different emphasis in a reference proposal from that seen in similar initiatives in information extraction and multimedia interfaces. We introduce the framework itself, in particular the two-level data model that allows us to support the complex data requirements of NLG systems in a flexible and coherent fashion, and describe our efforts to validate the framework through a range of implementations.

The recent scaling down of mobile device form factors has increased the importance of predictive text entry. It is now also becoming an important communication tool for the disabled. Techniques related to predictive text entry software are discussed in a generalized, language-independent manner. The essence of predictive text entry is twofold, consisting of (1) the design of codes for text entry, and (2) the use of adaptive language models for decoding. Code design is examined in terms of the information-theoretical efficiency. Four adaptive language models are introduced and compared, and experimental results on text entry with these models are shown for English, Thai and Japanese.

Natural Language Generation (NLG) can be used to generate textual summaries of numeric data sets. In this paper we develop an architecture for generating short (a few sentences) summaries of large (100KB or more) time-series data sets. The architecture integrates pattern recognition, pattern abstraction, selection of the most significant patterns, microplanning (especially aggregation), and realisation. We also describe and evaluate SumTime-Turbine, a prototype system which uses this architecture to generate textualsummaries of sensor data from gas turbines.

Folk wisdom holds that incorporating a part-of-speech tagger into a system that performs deep linguistic analysis will improve the speed and accuracy of the system. Previous studies of tagging have tested this belief by incorporating an existing tagger into a parsing system and observing the effect on the speed of the parser and accuracy of the results. However, not much work has been done to determine in a fine-grained manner exactly how much tagging can help to disambiguate or reduce ambiguity in parser output. We take a new approach to this issue by examining the full parse-forest output of a large-scale LFG-based English grammar (Riezler et al. (2002)) running on the XLE grammar development platform (Maxwell and Kaplan (1993); Maxwell and Kaplan (1996)); and partitioning the parse outputs into equivalence classes based on the tag sequences for each parse. If we find a large number of tag-sequence equivalence classes for each sentence, we can conclude that different parses tend to be distinguished by their tags; a small number means that tagging would not help much in reducing ambiguity. In this way, we can determine how much tagging would help us in the best case, if we had the “perfect tagger” to give us the correct tag sequence for each sentence. We show that if a perfect tagger were available, a reduction in ambiguity of about 50% would be available. Somewhat surprisingly, about 30% of the sentences in the corpus that was examined would not be disambiguated, even by the perfect tagger, since all of the parses for these sentences shared the same tag sequence. Our study also helps to inform research on tagging by providing a targeted determination of exactly which tags can help the most in disambiguation.

In spite of difficulty in defining the syllable unequivocally, and controversy over its role in theories of spoken and written language processing, the syllable is a potentially useful unit in several practical tasks which arise in computational linguistics and speech technology. For instance, syllable structure might embody valuable information for building word models in automatic speech recognition, and concatenative speech synthesis might use syllables or demisyllables as basic units. In this paper, we first present an algorithm for determining syllable boundaries in the orthographic form of unknown words that works by analogical reasoning from a database or corpus of known syllabifications. We call this syllabification by analogy (SbA). It is similarly motivated to our existing pronunciation by analogy (PbA) which predicts pronunciations for unknown words (specified by their spellings) by inference from a dictionary of known word spellings and corresponding pronunciations. We show that including perfect (according to the corpus) syllable boundary information in the orthographic input can dramatically improve the performance of pronunciation by analogy of English words, but such information would not be available to a practical system. So we next investigate combining automatically-inferred syllabification and pronunciation in two different ways: the series model in which syllabification is followed sequentially by pronunciation generation; and the parallel model in which syllabification and pronunciation are simultaneously inferred. Unfortunately, neither improves performance over PbA without syllabification. Possible reasons for this failure are explored via an analysis of syllabification and pronunciation errors.

This paper describes in detail an algorithm for the unsupervised learning of natural language morphology, with emphasis on challenges that are encountered in languages typologically similar to European languages. It utilizes the Minimum Description Length analysis described in Goldsmith (2001), and has been implemented in software that is available for downloading and testing.

There has been a contemporary surge of interest in the application of stochastic models of parsing. The use of tree-adjoining grammar (TAG) in this domain has been relatively limited due in part to the unavailability, until recently, of large-scale corpora hand-annotated with TAG structures. Our goals are to develop inexpensive means of generating such corpora and to demonstrate their applicability to stochastic modeling. We present a method for automatically extracting a linguistically plausible TAG from the Penn Treebank. Furthermore, we also introduce labor-inexpensive methods for inducing higher-level organization of TAGs. Empirically, we perform an evaluation of various automatically extracted TAGs and also demonstrate how our induced higher-level organization of TAGs can be used for smoothing stochastic TAG models.

A part-of-speech tagger is a fundamental and indispensable tool in computational linguistics, typically employed at the critical early stages of processing. Although taggers are widely available that achieve high accuracy in very general domains, these do not perform nearly as well when applied to novel specialized domains, and this is especially true with biological text. We present a stochastic tagger that achieves over 97.44% accuracy on MEDLINE abstracts. A primary component of the tagger is its lexicon which enumerates the permitted parts-of-speech for the 10000 words most frequently occurring in MEDLINE. We present evidence for the conclusion that the lexicon is as vital to tagger accuracy as a training corpus, and more important than previously thought.

To respond correctly to a free form factual question given a large collection of text data, one needs to understand the question to a level that allows determining some of the constraints the question imposes on a possible answer. These constraints may include a semantic classification of the sought after answer and may even suggest using different strategies when looking for and verifying a candidate answer. This work presents a machine learning approach to question classification. Guided by a layered semantic hierarchy of answer types, we develop a hierarchical classifier that classifies questions into fine-grained classes. This work also performs a systematic study of the use of semantic information sources in natural language classification tasks. It is shown that, in the context of question classification, augmenting the input of the classifier with appropriate semantic category information results in significant improvements to classification accuracy. We show accurate results on a large collection of free-form questions used in TREC 10 and 11.

For one aspect of grammatical annotation, part-of-speech tagging, we investigate experimentally whether the ceiling on accuracy stems from limits to the precision of tag definition or limits to analysts' ability to apply precise definitions, and we examine how analysts' performance is affected by alternative types of semi-automatic support. We find that, even for analysts very well-versed in a part-of-speech tagging scheme, human ability to conform to the scheme is a more serious constraint than precision of scheme definition. We also find that although semi-automatic techniques can greatly increase speed relative to manual tagging, they have little effect on accuracy, either positively (by suggesting valid candidate tags) or negatively (by lending an appearance of authority to incorrect tag assignments). On the other hand, it emerges that there are large differences between individual analysts with respect to usability of particular types of semi-automatic support.

Reading comprehension (RC) tests involve reading a short passage of text and answering a series of questions pertaining to that text. We present a methodology for evaluation of the application of modern natural language technologies to the task of responding to RC tests. Our work is based on ABCs (Abduction Based Comprehension system), an automated system for taking tests requiring short answer phrases as responses. A central goal of ABCs is to serve as a testbed for understanding the role that various linguistic components play in responding to reading comprehension questions. The heart of ABCs is an abductive inference engine that provides three key capabilities: (1) first-order logical representation of relations between entities and events in the text and rules to perform inference over such relations, (2) graceful degradation due to the inclusion of abduction in the reasoning engine, which avoids the brittleness that can be problematic in knowledge representation and reasoning systems and (3) system transparency such that the types of abductive inferences made over an entire corpus provide cues as to where the system is performing poorly and indications as to where existing knowledge is inaccurate or new knowledge is required. ABCs, with certain sub-components not yet automated, finds the correct answer phrase nearly 35 percent of the time using a strict evaluation metric and 45 percent of the time using a looser inexact metric on held out evaluation data. Performance varied for the different question types, ranging from over 50 percent on who questions to over 10 percent on what questions. We present analysis of the roles of individual components and analysis of the impact of various characteristics of the abductive proof procedure on overall system performance.

We present a Weighted Finite State Transducer Translation Template Model for statistical machine translation. This is a source-channel model of translation inspired by the Alignment Template translation model. The model attempts to overcome the deficiencies of word-to-word translation models by considering phrases rather than words as units of translation. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard finite state machine operations involving these transducers. One of the benefits of using this framework is that it avoids the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We report and analyze bitext word alignment and translation performance on the Hansards French-English task and the FBIS Chinese-English task under the Alignment Error Rate, BLEU, NIST and Word Error-Rate metrics. These experiments identify the contribution of each of the model components to different aspects of alignment and translation performance. We finally discuss translation performance with large bitext training sets on the NIST 2004 Chinese-English and Arabic-English MT tasks.

In this paper, a novel phrase alignment strategy combining linguistic knowledge and cooccurrence measures extracted from bilingual corpora is presented. The algorithm is mainly divided into four steps, namely phrase selection and classification, phrase alignment, one-to-one word alignment and postprocessing. The first stage selects a linguistically-derived set of phrases that convey a unified meaning during translation and are therefore aligned together in parallel texts. These phrases include verb phrases, idiomatic expressions and date expressions. During the second stage, very high precision links between these selected phrases for both languages are produced. The third step performs a statistical word alignment using association measures and link probabilities with the remaining unaligned tokens, and finally the fourth stage takes final decisions on unaligned tokens based on linguistic knowledge. Experiments are reported for an English-Spanish parallel corpus, with a detailed description of the evaluation measure and manual reference used. Results show that phrase cooccurrence measures convey a complementary information to word cooccurrences and a stronger evidence of a correct alignment, successfully introducing linguistic knowledge in a statistical word alignment scheme. Precision, Recall and Alignment Error Rate (AER) results are presented, outperforming state-of-the-art alignment algorithms.

One of the key issues in spoken-language translation is how to deal with unrestricted expressions in spontaneous utterances. We have developed a paraphraser for use as part of a translation system, and in this paper we describe the implementation of a Chinese paraphraser for a Chinese-Japanese spoken-language translation system. When an input sentence cannot be translated by the transfer engine, the paraphraser automatically transforms the sentence into alternative expressions until one of these alternatives can be translated by the transfer engine. Two primary issues must be dealt with in paraphrasing: how to determine new expressions, and how to retain the meaning of the input sentence. We use a pattern-based approach in which the meaning is retained to the greatest possible extent without deep parsing. The paraphrase patterns are acquired from a paraphrase corpus and human experience. The paraphrase instances are automatically extracted and then generalized into paraphrase patterns. A total of 1719 paraphrase patterns obtained using this method and an implemented paraphraser were used in a paraphrasing experiment. The results showed that the implemented paraphraser generated 1.7 paraphrases on average for each test sentence and achieved an accuracy of 88%.

We examine the implementation of clarification dialogues, a mechanism for ensuring that question answering systems take into account user goals by allowing them to ask series of related questions either by refining or expanding on previous questions with follow-up questions, in the context of open domain Question Answering systems. We develop an algorithm for clarification dialogue recognition through the analysis of collected data on clarification dialogues and examine the importance of clarification dialogue recognition for question answering. The algorithm is evaluated and shown to successfully recognize the start and continuation of clarification dialogues in 94% of cases. We then show the usefulness of the algorithm by demonstrating how the recognition of clarification dialogues can simplify the task of answer retrieval.

Suppose you're a corporate vice president at a well-known international software company, and you want to check on the visibility of one of your leading researchers in the outside world. You're sitting at your desk, so the most obvious thing to do is to enter their name into a search engine. If the well-known international software company happened to be Microsoft, and if the leading researcher happened to be Microsoft's Susan Dumais, and if the search engine you decided to use happened to be Google, you might be surprised to find that the sponsored link that comes atop the search results is actually from Google itself, exhorting you to ‘Work on NLP at Google’, and alerting you to the fact that ‘Google is hiring experts in statistical language processing’.

As part of a larger project to develop an aid for writers that would help to eliminate stylistic inconsistencies within a document, we experimented with neural networks to find the points in a text at which its stylistic character changes. Our best results, well above baseline, were achieved with time-delay networks that used features related to the author's syntactic preferences, whereas low-level and vocabulary-based features were not found to be useful. An alternative approach with character bigrams was not successful.