Refine
Year of publication
- 2008 (26) (remove)
Document Type
- Preprint (26) (remove)
Has Fulltext
- yes (26)
Is part of the Bibliography
- no (26) (remove)
Keywords
- Deutsch (8)
- Multicomponent Tree Adjoining Grammar (4)
- Range Concatenation Grammar (4)
- Syntaktische Analyse (4)
- Nominalisierung (3)
- German (2)
- Grammatik (2)
- Griechisch (2)
- Präposition (2)
- Rumänisch (2)
Institute
- Extern (12)
- Informatik (1)
- Physik (1)
This paper investigates the relation between TT-MCTAG, a formalism used in computational linguistics, and RCG. RCGs are known to describe exactly the class PTIME; simple RCG even have been shown to be equivalent to linear context-free rewriting systems, i.e., to be mildly context-sensitive. TT-MCTAG has been proposed to model free word order languages. In general, it is NP-complete. In this paper, we will put an additional limitation on the derivations licensed in TT-MCTAG. We show that TT-MCTAG with this additional limitation can be transformed into equivalent simple RCGs. This result is interesting for theoretical reasons (since it shows that TT-MCTAG in this limited form is mildly context-sensitive) and, furthermore, even for practical reasons: We use the proposed transformation from TT-MCTAG to RCG in an actual parser that we have implemented.
The dynamics of many systems are described by ordinary differential equations (ODE). Solving ODEs with standard methods (i.e. numerical integration) needs a high amount of computing time but only a small amount of storage memory. For some applications, e.g. short time weather forecast or real time robot control, long computation times are prohibitive. Is there a method which uses less computing time (but has drawbacks in other aspects, e.g. memory), so that the computation of ODEs gets faster? We will try to discuss this question for the assumption that the alternative computation method is a neural network which was trained on ODE dynamics and compare both methods using the same approximation error. This comparison is done with two different errors. First, we use the standard error that measures the difference between the approximation and the solution of the ODE which is hard to characterize. But in many cases, as for physics engines used in computer games, the shape of the approximation curve is important and not the exact values of the approximation. Therefore, we introduce a subjective error based on the Total Least Square Error (TLSE) which gives more consistent results. For the final performance comparison, we calculate the optimal resource usage for the neural network and evaluate it depending on the resolution of the interpolation points and the inter-point distance. Our conclusion gives a method to evaluate where neural nets are advantageous over numerical ODE integration and where this is not the case. Index Terms—ODE, neural nets, Euler method, approximation complexity, storage optimization.
This paper deals with the variable position of adjectives in the Romanian DP. As all other Romance languages, Romanian allows for adjectives to appear in both prenominal and post-nominal position. In addition, however, Romanian has a third pattern: the so-called cel construction, in which the adjective in the post-nominal position is preceded by a determiner-like element, cel. This pattern is superficially similar to Determiner Spreading in Greek. In this paper we contrast the cel construction to Greek DS and discuss the similarities and differences between the two. We then present an analysis of cel as involving an appositive specification clause, building on de Vries (2002). We argue that the same structure is also involved in the context of nominal ellipsis, the second environment in which cel is found.
The ACL 2008 Workshop on Parsing German features a shared task on parsing German. The goal of the shared task was to find reasons for the radically different behavior of parsers on the different treebanks and between constituent and dependency representations. In this paper, we describe the task and the data sets. In addition, we provide an overview of the test results and a first analysis.
The problem of vocalization, or diacritization, is essential to many tasks in Arabic NLP. Arabic is generally written without the short vowels, which leads to one written form having several pronunciations with each pronunciation carrying its own meaning(s). In the experiments reported here, we define vocalization as a classification problem in which we decide for each character in the unvocalized word whether it is followed by a short vowel. We investigate the importance of different types of context. Our results show that the combination of using memory-based learning with only a word internal context leads to a word error rate of 6.64%. If a lexical context is added, the results deteriorate slowly.
How to compare treebanks
(2008)
Recent years have seen an increasing interest in developing standards for linguistic annotation, with a focus on the interoperability of the resources. This effort, however, requires a profound knowledge of the advantages and disadvantages of linguistic annotation schemes in order to avoid importing the flaws and weaknesses of existing encoding schemes into the new standards. This paper addresses the question how to compare syntactically annotated corpora and gain insights into the usefulness of specific design decisions. We present an exhaustive evaluation of two German treebanks with crucially different encoding schemes. We evaluate three different parsers trained on the two treebanks and compare results using EVALB, the Leaf-Ancestor metric, and a dependency-based evaluation. Furthermore, we present TePaCoC, a new testsuite for the evaluation of parsers on complex German grammatical constructions. The testsuite provides a well thought-out error classification, which enables us to compare parser output for parsers trained on treebanks with different encoding schemes and provides interesting insights into the impact of treebank annotation schemes on specific constructions like PP attachment or non-constituent coordination.
Part-of-Speech tagging is generally performed by Markov models, based on bigram or trigram models. While Markov models have a strong concentration on the left context of a word, many languages require the inclusion of right context for correct disambiguation. We show for German that the best results are reached by a combination of left and right context. If only left context is available, then changing the direction of analysis and going from right to left improves the results. In a version of MBT (Daelemans et al., 1996) with default parameter settings, the inclusion of the right context improved POS tagging accuracy from 94.00% to 96.08%, thus corroborating our hypothesis. The version with optimized parameters reaches 96.73%.
Class features as probes
(2008)
In this article, we adress (i) the form and (ii) the function on inflection class features in minimalist grammar. The empirical evidence comes from noun inflection systems involving fusional markers in German, Greek, and Russian. As for (i), we argue (based on instances of transparadigmatic syncretism) that class features are not privative; rather, class information must be decomposed into more abstract, binary features. Concerning (ii), we propose that class features qualify as the very device that brings about fusional infection: They are uninterpretable in syntax and actas probes on stems, with matching inflection markers as goels, and thus trigger morphological Agree operations that merge stem and inflection marker before syntax is reached.