News Article Retrieval in Context for Event-centric Narrative Creation

• URL: http://arxiv.org/abs/2106.16053v1
• Date: Wed, 30 Jun 2021 13:27:54 GMT
• Title: News Article Retrieval in Context for Event-centric Narrative Creation
• Authors: Nikos Voskarides, Edgar Meij, Sabrina Sauer, Maarten de Rijke
• Abstract summary: Given an incomplete narrative, we aim to retrieve news articles that discuss relevant events that would enable the continuation of the narrative. Experiments show that state-of-the-art lexical and semantic rankers are not sufficient for this task. We show that combining those with a ranker that ranks articles by reverse chronological order outperforms those rankers alone.
• Score: 45.50837121213255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Writers such as journalists often use automatic tools to find relevant content to include in their narratives. In this paper, we focus on supporting writers in the news domain to develop event-centric narratives. Given an incomplete narrative that specifies a main event and a context, we aim to retrieve news articles that discuss relevant events that would enable the continuation of the narrative. We formally define this task and propose a retrieval dataset construction procedure that relies on existing news articles to simulate incomplete narratives and relevant articles. Experiments on two datasets derived from this procedure show that state-of-the-art lexical and semantic rankers are not sufficient for this task. We show that combining those with a ranker that ranks articles by reverse chronological order outperforms those rankers alone. We also perform an in-depth quantitative and qualitative analysis of the results that sheds light on the characteristics of this task.

Related papers

• Evaluating the Ability of Computationally Extracted Narrative Maps to Encode Media Framing [1.2277343096128712]
  This article explores the capabilities of a specific narrative extraction and representation approach -- narrative maps. Our results highlight the potential of narrative maps to provide users with insights into the intricate framing dynamics within news narratives. However, we note that directly leveraging framing information in the computational narrative extraction process remains an open challenge.
  arXiv  Detail & Related papers  (2024-05-04T14:40:28Z)
• SCStory: Self-supervised and Continual Online Story Discovery [53.72745249384159]
  SCStory helps people digest rapidly published news article streams in real-time without human annotations. SCStory employs self-supervised and continual learning with a novel idea of story-indicative adaptive modeling of news article streams.
  arXiv  Detail & Related papers  (2023-11-27T04:50:01Z)
• A Survey on Event-based News Narrative Extraction [10.193264105560862]
  This survey presents an extensive study of research in the area of event-based news narrative extraction. We screened over 900 articles that yielded 54 relevant articles. Based on the reviewed studies, we identify recent trends, open challenges, and potential research lines.
  arXiv  Detail & Related papers  (2023-02-16T15:11:53Z)
• Whats New? Identifying the Unfolding of New Events in Narratives [11.058053956455545]
  We study the Information Status (IS) of the events and propose a novel challenging task: the automatic identification of new events in a narrative. We define an event as a triplet of subject, predicate, and object. The event is categorized as new with respect to the discourse context. We annotated a publicly available corpus of narratives with the new events at sentence level using human annotators.
  arXiv  Detail & Related papers  (2023-02-15T15:54:01Z)
• CREATIVESUMM: Shared Task on Automatic Summarization for Creative Writing [90.58269243992318]
  This paper introduces the shared task of summarizing documents in several creative domains, namely literary texts, movie scripts, and television scripts. We introduce four sub-tasks and their corresponding datasets, focusing on summarizing books, movie scripts, primetime television scripts, and daytime soap opera scripts. As part of the CREATIVESUMM workshop at COLING 2022, the shared task attracted 18 submissions in total.
  arXiv  Detail & Related papers  (2022-11-10T21:31:03Z)
• NECE: Narrative Event Chain Extraction Toolkit [64.89332212585404]
  We introduce NECE, an open-access, document-level toolkit that automatically extracts and aligns narrative events in the temporal order of their occurrence. We show the high quality of the NECE toolkit and demonstrate its downstream application in analyzing narrative bias regarding gender. We also openly discuss the shortcomings of the current approach, and potential of leveraging generative models in future works.
  arXiv  Detail & Related papers  (2022-08-17T04:30:58Z)
• Context in Informational Bias Detection [4.386026071380442]
  We explore four kinds of context for informational bias in English news articles. We find that integrating event context improves classification performance over a very strong baseline. We find that the best-performing context-inclusive model outperforms the baseline on longer sentences.
  arXiv  Detail & Related papers  (2020-12-03T15:50:20Z)
• Paragraph-level Commonsense Transformers with Recurrent Memory [77.4133779538797]
  We train a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives. Our results show that PARA-COMET outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.
  arXiv  Detail & Related papers  (2020-10-04T05:24:12Z)
• CompRes: A Dataset for Narrative Structure in News [2.4578723416255754]
  We introduce CompRes -- the first dataset for narrative structure in news media. We use the annotated dataset to train several supervised models to identify the different narrative elements.
  arXiv  Detail & Related papers  (2020-07-09T15:21:59Z)
• Screenplay Summarization Using Latent Narrative Structure [78.45316339164133]
  We propose to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models. We formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays. Experimental results on the CSI corpus of TV screenplays, which we augment with scene-level summarization labels, show that latent turning points correlate with important aspects of a CSI episode.
  arXiv  Detail & Related papers  (2020-04-27T11:54:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.