Proceedings of the Workshop on Coreference Resolution Beyond OntoNotes (CORBON 2016) 2016
DOI: 10.18653/v1/w16-0704
|View full text |Cite
|
Sign up to set email alerts
|

Beyond Identity Coreference: Contrasting Indicators of Textual Coherence in English and German

Abstract: This paper focuses on the interaction of chains of coreference identity with other types of relations, comparing English and German data sets in terms of language, mode (written vs. spoken) and register. We first describe the types of coreference and the chain features analysed as indicators of textual coherence and topic continuity. After sketching the feature categories under analysis and the methods used for statistical evaluation, we present the findings from our analysis and interpret them in terms of the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
11
0

Year Published

2017
2017
2022
2022

Publication Types

Select...
4
1

Relationship

2
3

Authors

Journals

citations
Cited by 10 publications
(11 citation statements)
references
References 9 publications
0
11
0
Order By: Relevance
“…introduction and synopsis). Moreover, a more precise interpretation of the role of intersections to explicit discourse topics can be obtained if the features introduced in this study are related to the other chain features (as it was discussed in Kunz et al 2016): chain length, distance in chains and number of different chains. The features of this study have to be brought together with the features of other models dealing with chain interaction and cohesive harmony, as mentioned in Section 1.…”
Section: Discussionmentioning
confidence: 96%
See 3 more Smart Citations
“…introduction and synopsis). Moreover, a more precise interpretation of the role of intersections to explicit discourse topics can be obtained if the features introduced in this study are related to the other chain features (as it was discussed in Kunz et al 2016): chain length, distance in chains and number of different chains. The features of this study have to be brought together with the features of other models dealing with chain interaction and cohesive harmony, as mentioned in Section 1.…”
Section: Discussionmentioning
confidence: 96%
“…The fictional texts outperform all other registers again. This may generally be connected to two facts: First, a low number of multiple nouns in noun phrases and second, a very high number of different chains of both chain types in both languages (based on the findings by Kunz et al 2016). In interviews and political essays, the number of coreference chains with only one intersection is higher in German than in English.…”
Section: Number Of Intersections Per Coreferring Element 43mentioning
confidence: 92%
See 2 more Smart Citations
“…Corpora annotated for bridging references. At the time the ARRAU annotation started, there had not been many other attempts to annotate bridging reference apart from our own work as part of the Viera / Poesio corpus [59] and GNOME corpus [29], 20 but there have been a number of efforts since, many of which have attempted to annotate a broader range of the bridging relations identified in the early literature [43,58,102].…”
Section: Other Corpora Annotated For More Complex Forms Of Anaphoric mentioning
confidence: 99%