Resolving Shell Nouns

Kolhatkar, Varada; Hirst, Graeme

doi:10.3115/v1/d14-1056

Cited by 18 publications

(36 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They employ features modeling distance, containment, discourse structure, and -less effectively -content and lexical correlates. 4 Closest to our work is Kolhatkar et al (2013b) (KZH13) and Kolhatkar and Hirst (2014) (KH14) on shell noun resolution, using classical machine learning techniques. Shell nouns are abstract nouns, such as fact, possibility, or issue, which can only be interpreted jointly with their shell content (their embedded clause as in (2) or antecedent as in (3)).…”

Section: Introductionmentioning

confidence: 69%

See 1 more Smart Citation

A Mention-Ranking Model for Abstract Anaphora Resolution

Marasović

Born

Opitz

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Resolving abstract anaphora is an important, but difficult task for text understanding. Yet, with recent advances in representation learning this task becomes a more tangible aim. A central property of abstract anaphora is that it establishes a relation between the anaphor embedded in the anaphoric sentence and its (typically non-nominal) antecedent. We propose a mention-ranking model that learns how abstract anaphors relate to their antecedents with an LSTM-Siamese Net. We overcome the lack of training data by generating artificial anaphoric sentenceantecedent pairs. Our model outperforms state-of-the-art results on shell noun resolution. We also report first benchmark results on an abstract anaphora subset of the ARRAU corpus. This corpus presents a greater challenge due to a mixture of nominal and pronominal anaphors and a greater range of confounders. We found model variants that outperform the baselines for nominal anaphors, without training on individual anaphor data, but still lag behind for pronominal anaphors. Our model selects syntactically plausible candidates and -if disregarding syntax -discriminates candidates using deeper features.

show abstract

Section: Introductionmentioning

confidence: 69%

“…An example is given in (1) below. 1 While recent approaches address the resolution of selected abstract shell nouns (Kolhatkar and Hirst, 2014), we aim to resolve a wide range of abstract anaphors, such as the NP this trend in (1), as well as pronominal anaphors (this, that, or it).…”

Section: Introductionmentioning

confidence: 99%

A Mention-Ranking Model for Abstract Anaphora Resolution

Marasović

Born

Opitz

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…Evaluation script The evaluation script for Task 3 computes the Success@N metric proposed by Kolhatkar (e.g., (Kolhatkar and Hirst, 2014)) and also used by Marasović et al (2017). SUC-CESS@N is the proportion of instances where the gold answer-the unit label-occurs within a systems first n choices.…”

Section: Token Unit Markablementioning

confidence: 99%

Anaphora Resolution with the ARRAU Corpus

Poesio¹,

Grishina²,

Kolhatkar³

et al. 2018

Proceedings of the First Workshop on Computational Models Of Reference, Anaphora and Coreference

Self Cite

View full text Add to dashboard Cite

The ARRAU corpus is an anaphorically annotated corpus of English providing rich linguistic information about anaphora resolution. 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). Other distinctive features include treating all NPs as markables, including nonreferring NPs; and the annotation of a variety of morphosyntactic and semantic mention and entity attributes, including the genericity status of the entities referred to by markables. The corpus however has not been extensively used for anaphora resolution research so far. In this paper, we discuss three datasets extracted from the ARRAU corpus to support the three subtasks of the CRAC 2018 Shared Taskidentity anaphora resolution over ARRAU-style markables, bridging references resolution, and discourse deixis; the evaluation scripts assessing system performance on those datasets; and preliminary results on these three tasks that may serve as baseline for subsequent research in these phenomena.

show abstract

“…We required at least four human annotations per tweet as per the convention in related research (Thelwall, Buckley, Paltogou, Cai, & Kappas, ). CrowdFlower provides an agreement score for each annotated unit, which is based on the majority vote of the trusted workers (Kolhatkar, Zinsmeister, & Hirst, ). Because CrowdFlower continues to recruit workers until the task is complete, there is no guarantee that all workers will annotate the same set of units.…”

Section: Data Annotation—crowdsourcingmentioning

confidence: 99%

“…Therefore we cannot calculate traditional interrater reliability scores, such as Krippendorf's Alpha or Cohen's Kappa to determine agreement between all annotators. However, CrowdFlower has been shown to produce an agreement score that compares well to these classic measures (Kolhatkar et al, ).…”

Section: Data Annotation—crowdsourcingmentioning

confidence: 99%

Cyber Hate Speech on Twitter: An Application of Machine Classification and Statistical Modeling for Policy and Decision Making

Burnap¹,

Williams²

2015

Policy & Internet

482

347

View full text Add to dashboard Cite

In recent years, a new wave of hyperlocal community news websites has developed in the United Kingdom (UK), with many taking advantage of new opportunities provided by free open-source publishing platforms. Given the trend in the UK newspaper industry towards closure and retrenchment of their local and regional press titles, it is perhaps understandable that policy-makers have shifted their gaze to these sites. This article examines the viability of hyperlocal news services with a particular focus on those that are independently owned and managed. Such operations often have a longevity that sits in contrast to a number of failed attempts by major media organisations to operate in the hyperlocal space. Yet many of the business models that underpin these sites seem precarious, often benefiting from a degree of self-exploitation. Drawing on 35 interviews with hyperlocal news publishers from across the UK, this article argues that publishers draw upon a civic discourse in order to make sense of their practice. This framing may limit the potential to develop economic sustainability and risks alienating policy-makers keen to work with an idealised "fictive" hyperlocal entrepreneur.

show abstract

Resolving Shell Nouns

Cited by 18 publications

References 21 publications

A Mention-Ranking Model for Abstract Anaphora Resolution

A Mention-Ranking Model for Abstract Anaphora Resolution

Anaphora Resolution with the ARRAU Corpus

Cyber Hate Speech on Twitter: An Application of Machine Classification and Statistical Modeling for Policy and Decision Making

Contact Info

Product

Resources

About