Interactions between Narrative Schemas and Document Categories

Simonson, Dan; Davis, Anthony R.

doi:10.18653/v1/w15-4501

Cited by 3 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such datasets inadvertently facilitate the development of machine readers. In the past, such similar text mining research was conducted as the unsupervised mining of Schemas (also called scripts, templates, or frames)-as a generalization of recurring event knowledge with various participants [39]-primarily over newswire articles [7,[11][12][13][41][42][43]. They were a potent task at generalizing over similar but distinct narratives-can be seen as knowledge units-with the goal of revealing their underlying common elements.…”

Section: Introductionmentioning

confidence: 99%

NLPContributions: An Annotation Scheme for Machine Reading of Scholarly Contributions in Natural Language Processing Literature

D'Souza,

Auer

2020

Preprint

View full text Add to dashboard Cite

We describe an annotation initiative to capture the scholarly contributions in natural language processing (NLP) articles, particularly, for the articles that discuss machine learning (ML) approaches for various information extraction tasks. We develop the annotation task based on a pilot annotation exercise on 50 NLP-ML scholarly articles presenting contributions to the five information extraction tasks 1. machine translation, 2. named entity recognition, 3. question answering, 4. relation classification, and 5. text classification. In this article, we describe the outcomes of this pilot annotation phase. Through the exercise we have obtained an annotation methodology; and found eight core information units that reflect the contribution of the NLP-ML scholarly investigations. The resulting annotation scheme we developed based on these information units is called NLPContributions.The overarching goal of our endeavor is four-fold: 1) to find a systematic set of patterns of subject-predicate-object statements for the semantic structuring of scholarly contributions that are more or less generically applicable for NLP-ML research articles; 2) to apply the discovered patterns in the creation of a larger annotated dataset for training machine readers [17] of research contributions; 3) to ingest the dataset into the Open Research Knowledge Graph (ORKG) infrastructure as a showcase for creating user-friendly state-of-the-art overviews; 4) to integrate the machine readers into the ORKG to assist users in the manual curation of their respective article contributions. We envision that the NLPContributions methodology engenders a wider discussion on the topic toward its further refinement and development. Our pilot annotated dataset of 50 NLP-ML scholarly articles according to the NLPContributions scheme is openly available to the research community at https: //github.com/jenlindadsouza/NLPContributions.

show abstract

Section: Introductionmentioning

confidence: 99%

NLPContributions: An Annotation Scheme for Machine Reading of Scholarly Contributions in Natural Language Processing Literature

D'Souza,

Auer

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, little work has been done exploring the properties of Chambers' narrative schemas. Simonson and Davis (2015) attempt to determine whether the events in narrative schemas can be used as especially sensitive features for a naïve Bayes classifier. They demonstrate that schema events alone do not seem to predict document category (e.g.…”

Section: Introductionmentioning

confidence: 99%

“…

…”

mentioning

confidence: 99%

NASTEA: Investigating Narrative Schemas through Annotated Entities

Simonson¹,

Davis²

2016

Proceedings of the 2nd Workshop on Computing News Storylines (CNS 2016)

Self Cite

View full text Add to dashboard Cite

In this paper, we investigate the distribution of narrative schemas (Chambers and Jurafsky, 2009) throughout different document categories and how the structure of narrative schemas is conditioned by document category, the converse of the relationship explored in Simonson and Davis (2015). We evaluate cross-category narrative differences by assessing the predictability of verbs in each category and the salience of arguments to events that narrative schemas highlight. For the former, we use the narrative cloze task employed in previous work on schemas. For the latter, we introduce a task that employs narrative schemas called narrative argument salience through entities annotated, or NASTEA. We compare the schemas induced from the entire corpus to those from the subcorpora for each topic using these two types of evaluation. Results of each evaluation vary by each topical subcorpus, in some cases showing improvement, but the NASTEA task additionally reveals that some the documents within some topics are significantly more rigid in their narrative structure, instantiating a limited number of schemas in a highly predictable fashion.

show abstract

“…In this paper, we investigate the distribution of narrative schemas ) throughout different document categories and how the structure of narrative schemas is conditioned by document category, the converse of the relationship explored in Simonson and Davis (2015). We evaluate cross-category narrative differences by assessing the predictability of verbs in each category and the salience of arguments to events that narrative schemas highlight.…”

Section: Introductionmentioning

confidence: 99%

“…Simonson and Davis (2015) attempt to determine whether the events in narrative schemas can be used as especially sensitive features for a naïve Bayes classifier. They demonstrate that schema events alone do not seem to predict document category (e.g.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 2nd Workshop on Computing News Storylines (CNS 2016)

Caselli

Miller²,

Erp³

et al. 2016

View full text Add to dashboard Cite

at the heart of information sharing. Ever since people began to share their experiences, they have connected them to form narratives. The study of storytelling and the field of literary theory called narratology have developed complex frameworks and models related to various aspects of narrative such as plots structures, narrative embeddings, characters' perspectives, reader response, point of view, narrative voice, narrative goals, and many others. These notions from narratology have been applied mainly in Artificial Intelligence and to model formal semantic approaches to narratives (e.g. Plot Units developed by Lehnert (1981)). In recent years, computational narratology has qualified as an autonomous field of study and research. Narrative has been the focus of a number of workshops and conferences (AAAI Symposia, Interactive Storytelling Conference (ICIDS), Computational Models of Narrative). Furthermore, reference annotation schemes for narratives have been proposed (NarrativeML by Mani (2013)).The workshop aims to bring together researchers from different communities working on representing and extracting narrative structures in news, a text genre popular in NLP research but which has received little attention in research into narrative structure, representation and analysis.Current advances in NLP technology have made it possible to look beyond scenario-driven, atomic extraction of events from single documents and work towards extracting story structures from multiple documents, while these documents are published over time as news streams. Policy makers and information specialists are increasingly in need of tools that support them in finding salient stories in large amounts of information to more effectively implement policies, monitor actions of "big players" in society and check facts. Their tasks often revolve around reconstructing cases either with respect to specific entities (e.g. person or organisations) or events (e.g. the 2016 presidential elections). Storylines represent explanatory schemas that enable us to make better selections of relevant information but also projections for the future. They constitute a huge potential for exploiting news data in an innovative way.Of the 14 submissions we received, 8 were accepted that touch upon different aspects of narrative research in news. Three contributions describe approaches to detect storylines either from news (Brüggermann et al.), from Tweets (Krishnan and Eisenstein), or from news but with metadata added via Twitter (Poghosyan and Ifrim). Besides detecting storylines, different aspects of storylines such as diegesis and point of view are also addressed (Eisenberg and Finlayson). The second topic that is addressed is annotation and representation of storylines (Caselli and Vossen and O'Gorman et al.). Related to this is the analysis of the distribution of narrative schemas in a corpus, which may help further the discussion on corpus creation (Simonson and Davis). Finally, ideas on how to put storylines to use in a newsroom are discussed in Caswel...

show abstract

Interactions between Narrative Schemas and Document Categories

Cited by 3 publications

References 9 publications

NLPContributions: An Annotation Scheme for Machine Reading of Scholarly Contributions in Natural Language Processing Literature

NLPContributions: An Annotation Scheme for Machine Reading of Scholarly Contributions in Natural Language Processing Literature

NASTEA: Investigating Narrative Schemas through Annotated Entities

Proceedings of the 2nd Workshop on Computing News Storylines (CNS 2016)

Contact Info

Product

Resources

About