Refine
Year of publication
Document Type
- Article (185)
- Part of Periodical (69)
- Preprint (62)
- Book (37)
- Part of a Book (29)
- Conference Proceeding (27)
- Working Paper (15)
- Report (8)
- Doctoral Thesis (4)
- Other (3)
Language
- English (443) (remove)
Has Fulltext
- yes (443) (remove)
Keywords
- Computerlinguistik (28)
- Deutsch (20)
- Syntax (16)
- Japanisch (15)
- new species (11)
- Grammatik (10)
- Multicomponent Tree Adjoining Grammar (9)
- Optimalitätstheorie (9)
- Maschinelle Übersetzung (8)
- Syntaktische Analyse (8)
Institute
- Extern (443) (remove)
Another accruing and evolving collection holding published university documents (documents made publicly available) and non-official institutional records, plus 'grey literature' and ephemera relating to UB and its forerunner institutions. It includes documents harvested from UB Website. This is an artificially created collection. Some of these records may also exist in the homogenous institutional archive collections and in the BDSC.
The Conference on Computational Natural Language Learning features a shared task, in which participants train and test their learning systems on the same data sets. In 2007, as in 2006, the shared task has been devoted to dependency parsing, this year with both a multilingual track and a domain adaptation track. In this paper, we define the tasks of the different tracks and describe how the data sets were created from existing treebanks for ten languages. In addition, we characterize the different approaches of the participating systems, report the test results, and provide a first analysis of these results.
Recent approaches to Word Sense Disambiguation (WSD) generally fall into two classes: (1) information-intensive approaches and (2) information-poor approaches. Our hypothesis is that for memory-based learning (MBL), a reduced amount of data is more beneficial than the full range of features used in the past. Our experiments show that MBL combined with a restricted set of features and a feature selection method that minimizes the feature set leads to competitive results, outperforming all systems that participated in the SENSEVAL-3 competition on the Romanian data. Thus, with this specific method, a tightly controlled feature set improves the accuracy of the classifier, reaching 74.0% in the fine-grained and 78.7% in the coarse-grained evaluation.
Prepositional phrase (PP) attachment is one of the major sources for errors in traditional statistical parsers. The reason for that lies in the type of information necessary for resolving structural ambiguities. For parsing, it is assumed that distributional information of parts-of-speech and phrases is sufficient for disambiguation. For PP attachment, in contrast, lexical information is needed. The problem of PP attachment has sparked much interest ever since Hindle and Rooth (1993) formulated the problem in a way that can be easily handled by machine learning approaches: In their approach, PP attachment is reduced to the decision between noun and verb attachment; and the relevant information is reduced to the two possible attachment sites (the noun and the verb) and the preposition of the PP. Brill and Resnik (1994) extended the feature set to the now standard 4-tupel also containing the noun inside the PP. Among many publications on the problem of PP attachment, Volk (2001; 2002) describes the only system for German. He uses a combination of supervised and unsupervised methods. The supervised method is based on the back-off model by Collins and Brooks (1995), the unsupervised part consists of heuristics such as ”If there is a support verb construction present, choose verb attachment”. Volk trains his back-off model on the Negra treebank (Skut et al., 1998) and extracts frequencies for the heuristics from the ”Computerzeitung”. The latter also serves as test data set. Consequently, it is difficult to compare Volk’s results to other results for German, including the results presented here, since not only he uses a combination of supervised and unsupervised learning, but he also performs domain adaptation. Most of the researchers working on PP attachment seem to be satisfied with a PP attachment system; we have found hardly any work on integrating the results of such approaches into actual parsers. The only exceptions are Mehl et al. (1998) and Foth and Menzel (2006), both working with German data. Mehl et al. report a slight improvement of PP attachment from 475 correct PPs out of 681 PPs for the original parser to 481 PPs. Foth and Menzel report an improvement of overall accuracy from 90.7% to 92.2%. Both integrate statistical attachment preferences into a parser. First, we will investigate whether dependency parsing, which generally uses lexical information, shows the same performance on PP attachment as an independent PP attachment classifier does. Then we will investigate an approach that allows the integration of PP attachment information into the output of a parser without having to modify the parser: The results of an independent PP attachment classifier are integrated into the parse of a dependency parser for German in a postprocessing step.
We investigate methods to improve the recall in coreference resolution by also trying to resolve those definite descriptions where no earlier mention of the referent shares the same lexical head (coreferent bridging). The problem, which is notably harder than identifying coreference relations among mentions which have the same lexical head, has been tackled with several rather different approaches, and we attempt to provide a meaningful classification along with a quantitative comparison. Based on the different merits of the methods, we discuss possibilities to improve them and show how they can be effectively combined.
This paper presents an LTAG analysis of reflexives like himself and reciprocals like each other. These items need to find a c-commanding antecedent from which they retrieve (part of) their own denotation and with which they syntactically agree. The relation between anaphoric item and antecendent must satisfy the following important locality conditions (Chomsky (1981)).
Intrinsic motivation, the causal mechanism for spontaneous exploration and curiosity, is a central concept in developmental psychology. It has been argued to be a crucial mechanism for open-ended cognitive development in humans, and as such has gathered a growing interest from developmental roboticists in the recent years. The goal of this paper is threefold. First, it provides a synthesis of the different approaches of intrinsic motivation in psychology. Second, by interpreting these approaches in a computational reinforcement learning framework, we argue that they are not operational and even sometimes inconsistent. Third, we set the ground for a systematic operational study of intrinsic motivation by presenting a formal typology of possible computational approaches. This typology is partly based on existing computational models, but also presents new ways of conceptualizing intrinsic motivation. We argue that this kind of computational typology might be useful for opening new avenues for research both in psychology and developmental robotics.
Children […] growing up with highly inflected languages such as Modern Greek will frequently hear different grammatical forms of a given lexeme used in different grammatical and semantic-pragmatic contexts. In spite of the fact that the Greek noun is not as highly inflected as the verb, acquisition of nominal inflection of this inflecting-fusional language is quite complex, comprising the three categories of case, number, and gender. As is usual in this type of language, the formation of case-number forms obeys different patterns that apply to largely arbitrary classes of nominal lexemes partially based on gender. Further, frequency of the occurrence of the three gender classes and case-number forms of nouns greatly differs in spoken Greek, regarding both the types and tokens. […] [A] child learning an inflecting-fusional language like Greek must construct different inflectional patterns depending not only on parts of speech but also on subclasses within a given part of speech, such as gender classes of nouns and inflectional classes within or (exceptionally) across genders. It is therefore to be expected that the early development of case and number distinctions will apply to specific nouns and subclasses of nouns rather than the totality of Greek nouns. The two main theoretical approaches of morphological development that will be discussed in the present paper are the usage-based approach and the pre- and protomorphology approach.
This report arises from research carried out in Iganga and Namutumba districts in late 2006/early 2007 by the Cultural Research Centre (CRC), based in Jinja. Our research focus was to gauge the impact of using Lusoga as a medium of instruction (since 2005 in "pilot" lower primary classes) within and outside the classroom. This initiative was in response to a new set of circumstances in the education sector in Uganda, especially the introduction by Government of teaching in local languages in lower primary countrywide from February 2007. This followed an experimental period, in selected pilot districts, including Iganga, where fifteen pilot schools had been chosen: all these became part of this study.