Refine
Year of publication
Document Type
- Conference Proceeding (13)
- Part of a Book (2)
- Doctoral Thesis (1)
Has Fulltext
- yes (16)
Keywords
- Syntaktische Analyse (16) (remove)
Publicationstate
- Veröffentlichungsversion (16) (remove)
Reviewstate
Publisher
- Association for Computational Linguistics (4)
- European Language Resources Association (2)
- BBAW (1)
- Cambridge Scholars Publishing (1)
- Charles University (1)
- Dublin City University (1)
- Northern European Association for Language Technology (1)
- The Association for Computational Linguistics (1)
- University of Tartu (1)
- University of Tübingen (1)
Annotating Spoken Language
(2014)
To improve grammatical function labelling for German, we augment the labelling component of a neural dependency parser with a decision history. We present different ways to encode the history, using different LSTM architectures, and show that our models yield significant improvements, resulting in a LAS for German that is close to the best result from the SPMRL 2014 shared task (without the reranker).
The annotation of parts of speech (POS) in linguistically annotated corpora is a fundamental annotation layer which provides the basis for further syntactic analyses, and many NLP tools rely on POS information as input. However, most POS annotation schemes have been developed with written (newspaper) text in mind and thus do not carry over well to text from other domains and genres. Recent discussions have concentrated on the shortcomings of present POS annotation schemes with regard to their applicability to data from domains other than newspaper text.
In the NLP literature, adapting a parser to new text with properties different from the training data is commonly referred to as domain adaptation. In practice, however, the differences between texts from different sources often reflect a mixture of domain and genre properties, and it is by no means clear what impact each of those has on statistical parsing. In this paper, we investigate how differences between articles in a newspaper corpus relate to the concepts of genre and domain and how they influence parsing performance of a transition-based dependency parser. We do this by applying various similarity measures for data point selection and testing their adequacy for creating genre-aware parsing models.
We present a method and a software tool, the FrameNet Transformer, for deriving customized versions of the FrameNet database based on frame and frame element relations. The FrameNet Transformer allows users to iteratively coarsen the FrameNet sense inventory in two ways. First, the tool can merge entire frames that are related by user-specified relations. Second, it can merge word senses that belong to frames related by specified relations. Both methods can be interleaved. The Transformer automatically outputs format-compliant FrameNet versions, including modified corpus annotation files that can be used for automatic processing. The customized FrameNet versions can be used to determine which granularity is suitable for particular applications. In our evaluation of the tool, we show that our method increases accuracy of statistical semantic parsers by reducing the number of word-senses (frames) per lemma, and increasing the number of annotated sentences per lexical unit and frame. We further show in an experiment on the FATE corpus that by coarsening FrameNet we do not incur a significant loss of information that is relevant to the Recognizing Textual Entailment task.
We present the IUCL system, based on supervised learning, for the shared task on stance detection. Our official submission, the random forest model, reaches a score of 63.60, and is ranked 6th out of 19 teams. We also use gradient boosting decision trees and SVM and merge all classifiers into an ensemble method. Our analysis shows that random forest is good at retrieving minority classes and gradient boosting majority classes. The strengths of different classifiers wrt. precision and recall complement each other in the ensemble.
We investigate whether non-configurational languages, which display more word order variation than configurational ones, require more training data for a phenomenon to be parsed successfully. We perform a tightly controlled study comparing the dative alternation for English (a configurational language), German, and Russian (both non-configurational). More specifically, we compare the performance of a dependency parser when only canonical word order is present with its performance on data sets when all word orders are present. Our results show that for all languages, canonical data not only is easier to parse, but there exists no direct correspondence between the size of training sets containing free(er) word order variation and performance.
We investigate how the granularity of POS tags influences POS tagging, and furthermore, how POS tagging performance relates to parsing results. For this, we use the standard “pipeline” approach, in which a parser builds its output on previously tagged input. The experiments are performed on two German treebanks, using three POS tagsets of different granularity, and six different POS taggers, together with the Berkeley parser. Our findings show that less granularity of the POS tagset leads to better tagging results. However, both too coarse-grained and too fine-grained distinctions on POS level decrease parsing performance.
This paper is a contribution to the ongoing discussion on treebank annotation schemes and their impact on PCFG parsing results. We provide a thorough comparison of two German treebanks: the TIGER treebank and the TüBa-D/Z. We use simple statistics on sentence length and vocabulary size, and more refined methods such as perplexity and its correlation with PCFG parsing results, as well as a Principal Components Analysis. Finally we present a qualitative evaluation of a set of 100 sentences from the TüBa- D/Z, manually annotated in the TIGER as well as in the TüBa-D/Z annotation scheme, and show that even the existence of a parallel subcorpus does not support a straightforward and easy comparison of both annotation schemes.
This paper presents a thorough examination of the validity of three evaluation measures on parser output. We assess parser performance of an unlexicalised probabilistic parser trained on two German treebanks with different annotation schemes and evaluate parsing results using the PARSEVAL metric, the Leaf-Ancestor metric and a dependency-based evaluation. We reject the claim that the TüBa-D/Z annotation scheme is more adequate then the TIGER scheme for PCFG parsing and show that PARSEVAL should not be used to compare parser performance for parsers trained on treebanks with different annotation schemes. An analysis of specific error types indicates that the dependency-based evaluation is most appropriate to reflect parse quality.