We study the adaptation of Link Grammar Parser to the biomedical sublanguage with a focus on domain terms not found in a general parser lexicon. Using two biomedical corpora, we implement and evaluate three approaches to addressing unknown words: automatic lexicon expansion, the use of morphological clues, and disambiguation using a part-of-speech tagger. We evaluate each approach separately for its effect on parsing performance and consider combinations of these approaches. In addition to a 45% increase in parsing efficiency, we find that the best approach, incorporating information from a domain part-of-speech tagger, offers a statistically significant 10% relative decrease in error. The adapted parser is available under an open-source license at http://www.it.utu.fi/biolg .

We study the complexity and expressive power of conjunctive queries over unranked labeled trees represented using a variety of structure relations such as ``child'', ``descendant'', and ``following'' as well as unary relations for node labels. We establish a framework for characterizing structures representing trees for which conjunctive queries can be evaluated efficiently. Then we completely chart the tractability frontier of the problem and establish a dichotomy theorem for our axis relations, i.e., we find all subset-maximal sets of axes for which query evaluation is in polynomial time and show that for all other cases, query evaluation is NP-complete. All polynomial-time results are obtained immediately using the proof techniques from our framework. Finally, we study the expressiveness of conjunctive queries over trees and show that for each conjunctive query, there is an equivalent acyclic positive query (i.e., a set of acyclic conjunctive queries), but that in general this query is not of polynomial size.

Designers of statistical machine translation (SMT) systems have begun to employ tree-structured translation models. Systems involving tree-structured translation models tend to be complex. This article aims to reduce the conceptual complexity of such systems, in order to make them easier to design, implement, debug, use, study, understand, explain, modify, and improve. In service of this goal, the article extends the theory of semiring parsing to arrive at a novel abstract parsing algorithm with five functional parameters: a logic, a grammar, a semiring, a search strategy, and a termination condition. The article then shows that all the common algorithms that revolve around tree-structured translation models, including hierarchical alignment, inference for parameter estimation, translation, and structured evaluation, can be derived by generalizing two of these parameters -- the grammar and the logic. The article culminates with a recipe for using such generalized parsers to train, apply, and evaluate an SMT system that is driven by tree-structured translation models.

We have developed a web-based human-computer-intera ction system with natural language for foreign language learning: CSI EC (Computer Simulator in Educational Communication) [1]. The kernel of this system is the natural language understanding mechanism (NLML, NLOMJ and NLDB) and the communicational response (CR). NLML(Natural Language Markup Languag e) is a markup language to describe the grammar of an expression in a natur al language. It is produced to an expression of this natural language by a parser wri tten according to the grammar rules and lexicon of this language [2]. We use English as the experiment language in our system. For example, the NLML for the sentence " I come " is

We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We consider two ways of applying this intuition to the problem of unsupervised part-of-speech tagging: a model that directly merges tag structures for a pair of languages into a single sequence and a second model which instead incorporates multilingual context using latent variables. Both approaches are formulated as hierarchical Bayesian models, using Markov Chain Monte Carlo sampling techniques for inference. Our results demonstrate that by incorporating multilingual evidence we can achieve impressive performance gains across a range of scenarios. We also found that performance improves steadily as the number of available languages increases.

We investigate the global GRAMMAR constraint over restricted classes of context free grammars like deterministic and unambiguous context-free grammars. We show that detecting disentailment for the GRAMMAR constraint in these cases is as hard as parsing an unrestricted context free grammar.We also consider the class of linear grammars and give a propagator that runs in quadratic time. Finally, to demonstrate the use of linear grammars, we show that a weighted linear GRAMMAR constraint can efficiently encode the EDITDISTANCE constraint, and a conjunction of the EDITDISTANCE constraint and the REGULAR constraint

While much work on learning in planning focused on learning domain physics (i.e., action models), and search control knowledge, little attention has been paid towards learning user preferences on desirable plans. Hierarchical task networks (HTN) are known to provide an effective way to encode user prescriptions about what constitute good plans. However, manual construction of these methods is complex and error prone. In this paper, we propose a novel approach to learning probabilistic hierarchical task networks that capture user preferences by examining user-produced plans given no prior information about the methods (in contrast, most prior work on learning within the HTN framework focused on learning “method preconditions”—i.e., domain physics—assuming that the structure of the methods is given as input). We will show that this problem has close parallels to the problem of probabilistic grammar induction, and describe how grammar induction methods can be adapted to learn task networks. We will empirically demonstrate the effectiveness of our approach by showing that task networks we learn are able to generate plans with a distribution close to the distribution of the userpreferred plans.

This paper investigates a generative history-based parsing model that synchronises the derivation of non-planar graphs representing semantic dependencies with the derivation of dependency trees representing syntactic structures. To process non-planarity online, the semantic transition-based parser uses a new technique to dynamically reorder nodes during the derivation. While the synchronised derivations allow different structures to be built for the semantic non-planar graphs and syntactic dependency trees, useful statistical dependencies between these structures are modeled using latent variables. The resulting synchronous parser achieves competitive performance on the CoNLL-2008 shared task, achieving relative error reduction of 12% in semantic F score over previously proposed synchronous models that cannot process non-planarity online.

Web-scale data has been used in a diverse range of language research. Most of this research has used web counts for only short, fixed spans of context. We present a unified view of using web counts for lexical disambiguation. Unlike previous approaches, our supervised and unsupervised systems combine information from multiple and overlapping segments of context. On the tasks of preposition selection and context-sensitive spelling correction, the supervised system reduces disambiguation error by 20-24% over the current state-of-the-art.

Arabic Subject Markers are interface phenomena (specifically between morphology and syntax). In this paper, I describe them briefly, I give my linguistic analysis within the framework of the Head-Driven Phrase Structure Grammar and I show how I implement them in the LKB system. I show that this system, despite its strength, does not allow for a proper implementation of these units.