scholarly journals SAM-Net: Integrating Event-Level and Chain-Level Attentions to Predict What Happens Next

Author(s):  
Shangwen Lv ◽  
Wanhui Qian ◽  
Longtao Huang ◽  
Jizhong Han ◽  
Songlin Hu

Scripts represent knowledge of event sequences that can help text understanding. Script event prediction requires to measure the relation between an existing chain and the subsequent event. The dominant approaches either focus on the effects of individual events, or the influence of the chain sequence. However, only considering individual events will lose much semantic relations within the event chain, and only considering the sequence of the chain will introduce much noise. With our observations, both the individual events and the event segments within the chain can facilitate the prediction of the subsequent event. This paper develops self attention mechanism to focus on diverse event segments within the chain and the event chain is represented as a set of event segments. We utilize the event-level attention to model the relations between subsequent events and individual events. Then, we propose the chain-level attention to model the relations between subsequent events and event segments within the chain. Finally, we integrate event-level and chain-level attentions to interact with the chain to predict what happens next. Comprehensive experiment results on the widely used New York Times corpus demonstrate that our model achieves better results than other state-of-the-art baselines by adopting the evaluation of Multi-Choice Narrative Cloze task.

Author(s):  
Zhongyang Li ◽  
Xiao Ding ◽  
Ting Liu

Script event prediction requires a model to predict the subsequent event given an existing event context. Previous models based on event pairs or event chains cannot make full use of dense event connections, which may limit their capability of event prediction. To remedy this, we propose constructing an event graph to better utilize the event network information for script event prediction. In particular, we first extract narrative event chains from large quantities of news corpus, and then construct a narrative event evolutionary graph (NEEG) based on the extracted chains. NEEG can be seen as a knowledge base that describes event evolutionary principles and patterns. To solve the inference problem on NEEG, we present a scaled graph neural network (SGNN) to model event interactions and learn better event representations. Instead of computing the representations on the whole graph, SGNN processes only the concerned nodes each time, which makes our model feasible to large-scale graphs. By comparing the similarity between input context event representations and candidate event representations, we can choose the most reasonable subsequent event. Experimental results on widely used New York Times corpus demonstrate that our model significantly outperforms state-of-the-art baseline methods, by using standard multiple choice narrative cloze evaluation.


2021 ◽  
Author(s):  
Belén Agulló ◽  
◽  
Anna Matamala ◽  

Virtual reality has attracted the attention of industry and researchers. Its applications for entertainment and audiovisual content creation are endless. Filmmakers are experimenting with different techniques to create immersive stories. Also, subtitle creators and researchers are finding new ways to implement (sub)titles in this new medium. In this article, the state-of-the-art of cinematic virtual reality content is presented and the current challenges faced by filmmakers when dealing with this medium and the impact of immersive content on subtitling practices are discussed. Moreover, the different studies on subtitles in 360º videos carried out so far and the obtained results are reviewed. Finally, the results of a corpus analysis are presented in order to illustrate the current subtitle practices by The New York Times and the BBC. The results have shed some light on issues such as position, innovative graphic strategies or the different functions, challenging current subtitling standard practices in 2D content.


2021 ◽  

According to the New York Times, Noam Chomsky is the most important intellectual of our time. He has not only revolutionised the theories of language and the human mind, but his concept of human nature has prompted him to fight for freedom and democracy and led to political analyses which concern the role of the state and the function of democracy (among others). The contributions to this book deal with the most important topics of his political work: human nature and the emergence of social institutions the relationship of the individual to the state and the gist of anarchism human rights and the notion of freedom power and resistance <b>With contributions by</b> Robert Barsky, Željko Bošković, Jean Bricmont, Günther Grewendorf, Georg Meggle, Milan Rai, Tom Roeper, Michael Schiffmann and Juan Uriagereka.


Author(s):  
N. Blynova ◽  
N. Polishko ◽  
A. Mykhailova

The specificity of image copywriting, the features of storytelling as a method of writing image materials are considered. Image copywriting involves the creation of texts that shape and enshrine the image of the brand, the person and the service in the consumer’s mind. Historically, in Ukraine image texts were first circulated through the traditional and electronic media, and with the development of network communication an active functioning of such texts started on Internet, which proved its extraordinary effectiveness precisely when reaching the network audience. At the same time, the text does not only emphasize the positive aspects of the institution, product or service, does not call for something to buy or order. This is its key difference from the Direct-Response copywriting materials. Image copywriting has much in common with such journalistic genres as: review, press release, interview, biography, invitation, expert opinion, media statement. In the web space, the most prominent examples of the implementation of the image copywriting is the section "About Us", which is mandatory for many companies' sites, and is obligatory for any resource “Home” page.Today, the most commercially viable way of writing image texts is storytelling. It was first approached in the early 2010s in the New York Times. Simply and unobtrusively speaking about yourself, the company and the product is the best way to establish a connection with the consumer and the market is. A professionally created story not only create big interest but also arouse empathy in the readers, who begin to agree with the author. The unobtrusive presentation of information leads to the goal set by marketers: it is up to the individual to decide how to treat the material. Today, special storytelling techniques are being developed and actively operating to help copywriters to create image text of high quality.Such materials increase the trust of the target audience to the object of the image campaign, have lasting effect and remarkable commercial results.


Author(s):  
Sarah Doerksen

The individual has been an enduring figure in American history, claiming prominence even in the turbulent decades of the nineteenth century characterized by conflict between industrialists and collective unions. Andrew Carnegie captured the American press’ headlines during this period. However, his appearance in American publications, such as the New York Times and Harper’s Weekly, frequently coincided with news coverage of his adversary, the Knights of Labor (KOL). This conceptual binary provides an opportunity to explore the place of the individual and conversely the group in American history. Neither Carnegie nor the KOL escaped censure by the mainstream media or by extension, the American public. But despite Carnegie’s immigrant background and endorsement of his Scottish heritage, the media portrayed the industrialist as distinctly American while they depicted the KOL as distinct from Americans. Historiography attributes the dichotomy between representations of the elite and the working class to a disparity of capital. However, claims to patriotism had to be accepted by the mass public. Focus should be redirected to the publicized accounts of Carnegie’s public commitments which coincided with American conceptions of civic involvement and reinforced this individual’s place in American society. In contrast, the media’s portrayal of the KOL’s activities, which reflected their members’ interests, emphasized the union’s collective unity and insularity. In exploring definitions of patriotism and American identity, the contrasting representations of Carnegie and the Knights of Labor speak to the importance ascribed to individualism in America and the expectation that Americans pledge allegiance to a single, national Union.


2021 ◽  
Vol 118 (51) ◽  
pp. e2107848118
Author(s):  
Marten Scheffer ◽  
Ingrid van de Leemput ◽  
Els Weinans ◽  
Johan Bollen

The surge of post-truth political argumentation suggests that we are living in a special historical period when it comes to the balance between emotion and reasoning. To explore if this is indeed the case, we analyze language in millions of books covering the period from 1850 to 2019 represented in Google nGram data. We show that the use of words associated with rationality, such as “determine” and “conclusion,” rose systematically after 1850, while words related to human experience such as “feel” and “believe” declined. This pattern reversed over the past decades, paralleled by a shift from a collectivistic to an individualistic focus as reflected, among other things, by the ratio of singular to plural pronouns such as “I”/”we” and “he”/”they.” Interpreting this synchronous sea change in book language remains challenging. However, as we show, the nature of this reversal occurs in fiction as well as nonfiction. Moreover, the pattern of change in the ratio between sentiment and rationality flag words since 1850 also occurs in New York Times articles, suggesting that it is not an artifact of the book corpora we analyzed. Finally, we show that word trends in books parallel trends in corresponding Google search terms, supporting the idea that changes in book language do in part reflect changes in interest. All in all, our results suggest that over the past decades, there has been a marked shift in public interest from the collective to the individual, and from rationality toward emotion.


PMLA ◽  
2016 ◽  
Vol 131 (5) ◽  
pp. 1495-1503 ◽  
Author(s):  
Jennifer Wallace

In the Autumn of 2002, I Gave a Lecture on Mourning the Dead to Final-Year Undergraduates at the University of Cambridge studying the compulsory course on tragedy. The lecture covered the care devoted to the dead body in Sophocles's Antigone and Hamlet's reflections, over Ophelia's grave, on the “fine revolution” of the material corpse (5.1.82-83). But it also extended its range to include the then very recent excavation, for eight and a half months, at Ground Zero in search of the remains of the dead victims of the attack on the World Trade Center, and the simultaneous daily publication in the New York Times of “Portraits of Grief.” These portraits, I maintained, fulfilled a similar function to tragic drama by refocusing attention on the individual life and by finding a narrative arc to each victim's story, like Aristotle's tragic plots, which must have “a beginning, a middle, and an end” (26). While the firefighters' digging equipment at Ground Zero searched in vain for the missing remains of about 1800 people and eventually hit bedrock, the newspaper reinvested each lost person with significance, finding a value and a pattern in the person's life.


Ethnicities ◽  
2018 ◽  
Vol 19 (1) ◽  
pp. 66-94 ◽  
Author(s):  
Claire Chambers ◽  
Richard Phillips ◽  
Nafhesa Ali ◽  
Peter Hopkins ◽  
Raksha Pande

We begin this article with a close look at some contemporary pictures of sexual life in the Muslim world that have been painted in certain sections of the Western media, asking how and why these pictures matter. Across a range of mainstream print media from the New York Times to the Daily Mail, and across reported events from several countries, can be found pictures of ‘sexual misery’. These ‘frame’ Muslim men as tyrannical, Muslim women as downtrodden or exploited, and the wider world of Islam as culpable. Crucially, this is not the whole story. We then consider how these negative representations are being challenged and how they can be challenged further. In doing so, we will not simply set pictures of sexual misery against their binary opposites, namely pictures abounding in the promise of sexual happiness. Instead, we search for a more complex picture, one that unsettles stereotypes about the sexual lives of Muslims without simply idealising its subjects. This takes us to the journalism, life writing and creative non-fiction of Shelina Zahra Janmohamed and the fiction of Ayisha Malik and Amjeed Kabil. We read this long-form work critically, attending to manifest advances in depictions of the relationships of Muslim-identified individuals over the last decade or so, while also remaining alert to lacunae and limitations in the individual representations. More broadly, we hope to signal our intention to avoid both Islamophobia and Islamophilia in scrutinising literary texts.


2007 ◽  
Vol 55 (4) ◽  
pp. 325-346 ◽  
Author(s):  
Jason B. Phillips

Obituaries from the New York Times are examined at three points to illuminate changing conceptions of death. The findings are twofold. Changes in the obituary demonstrate how the locus of social control over death has shifted from nature and God, to medicine and most recently to the individual. Additionally, it is shown that descriptions of biophysical aspects of the dying process are marginalized over time and that there is more frequent use of language that emphasizes death-resistant themes in the most recent obituaries. This finding exemplifies the observation of increasing claims to authority over mortality by individuals in recent decades.


2021 ◽  
Vol 3 (1) ◽  
pp. 123-167
Author(s):  
Lars Hillebrand ◽  
David Biesner ◽  
Christian Bauckhage ◽  
Rafet Sifa

Unsupervised topic extraction is a vital step in automatically extracting concise contentual information from large text corpora. Existing topic extraction methods lack the capability of linking relations between these topics which would further help text understanding. Therefore we propose utilizing the Decomposition into Directional Components (DEDICOM) algorithm which provides a uniquely interpretable matrix factorization for symmetric and asymmetric square matrices and tensors. We constrain DEDICOM to row-stochasticity and non-negativity in order to factorize pointwise mutual information matrices and tensors of text corpora. We identify latent topic clusters and their relations within the vocabulary and simultaneously learn interpretable word embeddings. Further, we introduce multiple methods based on alternating gradient descent to efficiently train constrained DEDICOM algorithms. We evaluate the qualitative topic modeling and word embedding performance of our proposed methods on several datasets, including a novel New York Times news dataset, and demonstrate how the DEDICOM algorithm provides deeper text analysis than competing matrix factorization approaches.


Sign in / Sign up

Export Citation Format

Share Document