Grouping business news stories based on salience of named entities

Escoter, Llorenc; Pivovarova, Lidia; Du, Mian; Katinskaia, Anisia; Yangarber, Roman

doi:10.18653/v1/e17-1103

Cited by 6 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We determined the degree of salience to establish the proportion of the entire text taken up by each theme as coded text. 31 32 It helps in determining emphasis given to themes or concepts in the document thereby further improving clustering performance. 31 32 Salience statistics were derived based on the percentage of text the thematic codes took up in each of the five documents.…”

Section: Methodsmentioning

confidence: 99%

Content analysis of reported activities of the United Nations Road Safety Collaboration Members during the Decade of Action for Road Safety 2011–2020

Flannigan¹,

Khayesi²

2021

BMJ Open

View full text Add to dashboard Cite

ObjectiveSeveral activities were planned for the Decade of Action (DOA) for Road Safety 2011–2020, covering key policies and interventions on road safety. Knowledge of the activities implemented by key actors is currently lacking in the literature. This study answers the question: what activities were implemented during the DOA by the United Nations Road Safety Collaboration (UNRSC) members?DesignThe study used content analysis techniques to extract and analyse information from five United Nations Secretary General’s reports, which summarise the activities reported by UNRSC members.SettingThe primary setting for this study are 116 countries in which activities supporting the DOA were conducted.Outcome measuresFrequency of themes and subthemes that emerged from reported activities are identified and cross-tabulated by year of report, country level of income, geographical region and organisation type.ResultsOver the entire DOA, establishment of institutions and lead agencies as well as the development of national strategies featured prominently under the theme of management. This theme was steadily reported across regions, country income level and organisation type. Workshops, training and major events regarding road safety increased in frequency of reporting throughout the decade as did developing and promoting the basic road and vehicle systems supportive of road safety. It is further noted that other key activities like infrastructure and behaviour change that are required for a balanced approach to road safety policy were also attended to by various organisations. Activities related to road safety enforcement and post-crash response as well as activities in low-income countries appeared to be less reported.ConclusionThe wide range of activities reported by UNRSC members over the entire DOA need to be sustained and evaluated in years to come if they are to have a significant impact on reducing road traffic deaths and injuries at national and international levels.

show abstract

Section: Methodsmentioning

confidence: 99%

Content analysis of reported activities of the United Nations Road Safety Collaboration Members during the Decade of Action for Road Safety 2011–2020

Flannigan¹,

Khayesi²

2021

BMJ Open

View full text Add to dashboard Cite

show abstract

“…Recent topic model extensions are either designed for specific tasks, such as multi-label classification (Li, Ouyang, and Zhou 2015a,b) and opinion mining (Wang, Chen, and Liu 2016), or particular kinds of texts, such as short texts (Zhang, Mao, and Zeng 2016;Bicalho et al 2017;Qiu and Shen 2017;Li et al 2018). On the other hand, the notion of entity salience is attracting more attention (Gamon et al 2013;Tran et al 2015;Escoter et al 2017;Xiong et al 2018). Gamon et al (2013) propose the task of identifying salient entities on web pages.…”

Section: Related Workmentioning

confidence: 99%

“…Tran et al (2015) take entity salience into consideration in ranking entities for summarization of high-impact events. Escoter et al (2017) group business news stories based on the salience of named entities. Xiong et al (2018) propose a Kernel Entity Salience Model to better estimate entity salience in documents so as to improve text understanding and retrieval.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

“…On the other hand, the notion of entity salience is attracting more attention (Gamon et al . 2013; Tran et al 2015; Escoter et al 2017; Xiong et al . 2018).…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

It all starts with entities: A Salient entity topic model

Kanoulas

Rijke

2019

Nat. Lang. Eng.

View full text Add to dashboard Cite

Entities play an essential role in understanding textual documents, regardless of whether the documents are short, such as tweets, or long, such as news articles. In short textual documents, all entities mentioned are usually considered equally important because of the limited amount of information. In long textual documents, however, not all entities are equally important: some are salient and others are not. Traditional entity topic models (ETMs) focus on ways to incorporate entity information into topic models to better explain the generative process of documents. However, entities are usually treated equally, without considering whether they are salient or not. In this work, we propose a novel ETM, Salient Entity Topic Model, to take salient entities into consideration in the document generation process. In particular, we model salient entities as a source of topics used to generate words in documents, in addition to the topic distribution of documents used in traditional topic models. Qualitative and quantitative analysis is performed on the proposed model. Application to entity salience detection demonstrates the effectiveness of our model compared to the state-of-the-art topic model baselines.

show abstract