Search Results for author: Ina Roesiger

Found 11 papers, 0 papers with code

Towards Coreference for Literary Text: Analyzing Domain-Specific Phenomena

no code implementations COLING 2018 Ina Roesiger, Sarah Schulz, Nils Reiter

As some of the adaptations have profound impact, we also present a new annotation tool for coreference, with a focus on enabling annotation of long texts with many discourse entities.

coreference-resolution Coreference Resolution +2

Bridging resolution: Task definition, corpus resources and rule-based experiments

no code implementations COLING 2018 Ina Roesiger, Arndt Riester, Jonas Kuhn

Recent work on bridging resolution has so far been based on the corpus ISNotes (Markert et al. 2012), as this was the only corpus available with unrestricted bridging annotation.

Coreference Resolution

Anaphora Resolution with the ARRAU Corpus

no code implementations WS 2018 Massimo Poesio, Yulia Grishina, Varada Kolhatkar, Nafise Moosavi, Ina Roesiger, Adam Roussel, Fabian Simonjetz, Alex Uma, ra, Olga Uryupina, Juntao Yu, Heike Zinsmeister

The most distinctive feature of the corpus is the annotation of a wide range of anaphoric relations, including bridging references and discourse deixis in addition to identity (coreference).

Rule- and Learning-based Methods for Bridging Resolution in the ARRAU Corpus

no code implementations WS 2018 Ina Roesiger

We present two systems for bridging resolution, which we submitted to the CRAC shared task on bridging anaphora resolution in the ARRAU corpus (track 2): a rule-based approach following Hou et al. 2014 and a learning-based approach.

Bridging Anaphora Resolution

Towards Bridging Resolution in German: Data Analysis and Rule-based Experiments

no code implementations WS 2018 Janis Pagel, Ina Roesiger

Bridging resolution is the task of recognising bridging anaphors and linking them to their antecedents.

Re-Ranking

Acquisition of semantic relations between terms: how far can we get with standard NLP tools?

no code implementations WS 2016 Ina Roesiger, Julia Bettinger, Johannes Sch{\"a}fer, Michael Dorna, Ulrich Heid

The extraction of data exemplifying relations between terms can make use, at least to a large extent, of techniques that are similar to those used in standard hybrid term candidate extraction, namely basic corpus analysis tools (e. g. tagging, lemmatization, parsing), as well as morphological analysis of complex words (compounds and derived items).

Coreference Resolution Lemmatization +2

IMS HotCoref DE: A Data-driven Co-reference Resolver for German

no code implementations LREC 2016 Ina Roesiger, Jonas Kuhn

This paper presents a data-driven co-reference resolution system for German that has been adapted from IMS HotCoref, a co-reference resolver for English.

SciCorp: A Corpus of English Scientific Articles Annotated for Information Status Analysis

no code implementations LREC 2016 Ina Roesiger

The corpus comprises co-reference and bridging information as well as information status labels.

Cannot find the paper you are looking for? You can Submit a new open access paper.