Accessing GermaNet data and computing semantic relatedness

Gurevych, Iryna; Niederlich, Hendrik

doi:10.3115/1225753.1225755

Cited by 8 publications

(5 citation statements)

References 9 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practice, although the performance of different methods for different languages are generally consistent, some may require specialization due to different characteristics (e.g., morphological, syntactical) of languages. For example, Gurevych and Niederlich (2005) showed that for strongly inflected languages such as German, methods that require counting word frequencies such as IC-based methods can be biased, and it is necessary to apply stemming or lemmatization to reduce inflected words to certain base forms to obtain more accurate predictions. Such insights can be valuable references but they are currently rare due to lack of literature on multilingual semantic relatedness.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Recent advances in methods of lexical semantic relatedness – a survey

Zhang¹,

Gentile²,

Ciravegna³

2012

Nat. Lang. Eng.

View full text Add to dashboard Cite

AbstractMeasuring lexical semantic relatedness is an important task in Natural Language Processing (NLP). It is often a prerequisite to many complex NLP tasks. Despite an extensive amount of work dedicated to this area of research, there is a lack of an up-to-date survey in the field. This paper aims to address this issue with a study that is focused on four perspectives: (i) a comparative analysis of background information resources that are essential for measuring lexical semantic relatedness; (ii) a review of the literature with a focus on recent methods that are not covered in previous surveys; (iii) discussion of the studies in the biomedical domain where novel methods have been introduced but inadequately communicated across the domain boundaries; and (iv) an evaluation of lexical semantic relatedness methods and a discussion of useful lessons for the development and application of such methods. In addition, we discuss a number of issues in this field and suggest future research directions. It is believed that this work will be a valuable reference to researchers of lexical semantic relatedness and substantially support the research activities in this field.

show abstract

Section: Discussionmentioning

confidence: 99%

“…A few recent studies have explored this direction. Gurevych and Niederlich (2005) adapted the methods by Resnik (1995), Jiang and Conrath (1997), and Lin (1998b) to a German lexical knowledge base and tested them on a German dataset. Zesch et al .…”

Section: Methods Of Lexical Semantic Relatednessmentioning

confidence: 99%

Recent advances in methods of lexical semantic relatedness – a survey

Zhang¹,

Gentile²,

Ciravegna³

2012

Nat. Lang. Eng.

View full text Add to dashboard Cite

show abstract

“…To cluster tweets by hashtags, we rely on K-means as a classic hard clustering approach. Similarity was computed as semantic relatedness according to GermaNet [33], similar methods exist for other data and languages [34]. However, for some small datasets no meaningful clustering of the data can be obtained.…”

Section: B Clusteringmentioning

confidence: 99%

The reception of holidays in social networks: A case study on Twitter

Hakius

2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

This study aims to push the boundaries of research in practical theology by applying methods from computational social science to identify the reception of holidays in online social networks in German tweets. Can we identify how people talk about holidays and especially Christian holidays on Twitter? As a subquestion, we try to find relevant information for interreligious topics, especially between Christians and Jews: Can we see how Christian holidays are related to or embedded in their Jewish counterparts? Is there an awareness of the Jewish roots of certain Christian holidays? While there is a growing awareness of these issues, there are still a number of unanswered questions. In addition to analysing and discussing these questions, we will also discuss methodological issues. First, we will discuss how computational methods fit in with common research in practical theology. Secondly, we will discuss the challenges of working with digital data beyond quantitative and qualitative research.

show abstract

“…The linearization of the resulting tree (or graph) is done with a trigram language model. To adapt this system to German, we use the Ger-maNet API (Gurevych & Niederlich, 2005) instead of WordNet. We do not use a paraphrase lexicon, because there is no comparable corpus of sufficient size available for German.…”

Section: Baselinementioning

confidence: 99%

Sentence fusion via dependency graph compression

Filippova

Strube

2008

Proceedings of the Conference on Empirical Methods in Natural Language Processing - EMNLP '08

View full text Add to dashboard Cite

We present a novel unsupervised sentence fusion method which we apply to a corpus of biographies in German. Given a group of related sentences, we align their dependency trees and build a dependency graph. Using integer linear programming we compress this graph to a new tree, which we then linearize. We use GermaNet and Wikipedia for checking semantic compatibility of co-arguments. In an evaluation with human judges our method outperforms the fusion approach of Barzilay & McKeown (2005) with respect to readability.

show abstract

Accessing GermaNet data and computing semantic relatedness

Cited by 8 publications

References 9 publications

Recent advances in methods of lexical semantic relatedness – a survey

Recent advances in methods of lexical semantic relatedness – a survey

The reception of holidays in social networks: A case study on Twitter

Sentence fusion via dependency graph compression

Contact Info

Product

Resources

About