Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets. We demonstrate that language models begin to learn these tasks without any explicit supervision when trained on a new dataset of millions of webpages called WebText. When conditioned on a document plus questions, the answers generated by the language model reach 55 F1 on the CoQA dataset – matching or exceeding the performance of 3 out of 4 baseline systems without using the 127,000+ training examples. The capacity of the language model is essential to the success of zero-shot task transfer and increasing it improves performance in a log-linear fashion across tasks. Our largest model, GPT-2, is a 1.5B parameter Transformer that achieves state of the art results on 7 out of 8 tested language modeling datasets in a zero-shot setting but still underfits WebText. Samples from the model reflect these improvements and contain coherent paragraphs of text. These findings suggest a promising path towards building language processing systems which learn to perform tasks from their naturally occurring demonstrations. Read More
Tag Archives: News Summarization
iPR Software Introduces the First Artificial Intelligence Application for Online Newsrooms and Digital Publishing
iPR Software, the leader in Online Newsrooms, Digital Publishing, Digital Asset Management (DAM) solutions, and customized integrated solutions, announced its largest technology rollout to date at Public Relations Society of America’s International Conference in San Diego, California. With the launch of “Metatron,” iPR Software’s new application empowers Artificial Intelligence (AI) cloud capabilities as well as integrating the power of machine learning into DAM and customized software platforms to increase productivity and corporate asset sharing across multiple customer ecosystems. This latest software release further advances the company’s vision for clients to publish their news and information to Traditional and Social media channels and better engage their B2B & B2C audiences while increasing traffic to their branded media and corporate assets. Read More
Detecting Kissing Scenes in a Database of Hollywood Films
Detecting scene types in a movie can be very useful for application such as video editing, ratings assignment, and personalization. We propose a system for detecting kissing scenes in a movie. This system consists of two components. The first component is a binary classifier that predicts a binary label (i.e. kissing or not) given a features exctracted from both the still frames and audio waves of a one-second segment. The second component aggregates the binary labels for contiguous non-overlapping segments into a set of kissing scenes. We experimented with a variety of 2D and 3D convolutional architectures such as ResNet, DesnseNet, and VGGish and developed a highly accurate kissing detector that achieves a validation F1 score of 0.95 on a diverse database of Hollywood films ranging many genres and spanning multiple decades. The code for this project is available at http://github.com/amirziai/kissing-detector. Read More
Artificial intelligence-enhanced journalism offers a glimpse of the future of the knowledge economy
Much as robots have transformed entire swaths of the manufacturing economy, artificial intelligence and automation are now changing information work, letting humans offload cognitive labor to computers. In journalism, for instance, data mining systems alert reporters to potential news stories, while newsbotsoffer new ways for audiences to explore information. Automated writing systems generate financial, sports and elections coverage.
A common question as these intelligent technologies infiltrate various industries is how work and labor will be affected. In this case, who—or what—will do journalism in this AI-enhanced and automated world, and how will they do it?
The evidence I’ve assembled in my new book “Automating the New: How Algorithms are Rewriting the Media” suggests that the future of AI-enabled journalism will still have plenty of people around. However, the jobs, roles and tasks of those people will evolve and look a bit different. Human work will be hybridized—blended together with algorithms—to suit AI’s capabilities and accommodate its limitations. Read More
How A.I. Could Be Weaponized to Spread Disinformation
In 2017, an online disinformation campaign spread against the “White Helmets,” claiming that the group of aid volunteers was serving as an arm of Western governments to sow unrest in Syria.
This false information was convincing. But the Russian organization behind the campaign ultimately gave itself away because it repeated the same text across many different fake news sites.
Now, researchers at the world’s top artificial intelligence labs are honing technology that can mimic how humans write, which could potentially help disinformation campaigns go undetected by generating huge amounts of subtly different messages. Read More
Text-based Editing of Talking-head Video
Editing talking-head video to change the speech content or to remove filler words is challenging. We propose a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified, while maintaining a seamless audio-visual flow (i.e. no jump cuts). Our method automatically annotates an input talking-head video with phonemes, visemes, 3D face pose and geometry, reflectance, expression and scene illumination per frame. To edit a video, the user has to only edit the transcript, and an optimization strategy then chooses segments of the input corpus as base material. The annotated parameters corresponding to the selected segments are seamlessly stitched together and used to produce an intermediate video representation in which the lower half of the face is rendered with a parametric face model. Finally,a recurrent video generation network transforms this representation to a photo realistic video that matches the edited transcript. We demonstrate a large variety of edits, such as the addition, removal, and alteration of words,as well as convincing language translation and full sentence synthesis. Read More
AI System Sorts News Articles By Whether or Not They Contain Actual Information
There’s a thing in journalism now where news is very often reframed in terms of personal anecdote and-or hot take. In an effort to have something new and clickable to say, we reach for the easiest, closest thing at hand, which is, well, ourselves—our opinions and experiences.
I worry about this a lot! I do it (and am doing it right now), and I think it’s not always for ill. But in a larger sense it’s worth wondering to what degree the larger news feed is being diluted by news stories that are not “content dense.” That is, what’s the real ratio between signal and noise, objectively speaking? To start, we’d need a reasonably objective metric of content density and a reasonably objective mechanism for evaluating news stories in terms of that metric. Read More
Detecting Content-dense News Texts Combining Lexical and Syntactic Features for Detecting Content-dense Texts in News
Content-dense news report important factual information about an event in direct, succinct manner. Information seeking applications such as information extraction, question answering and summarization normally assume all text they deal with is content-dense.Here we empirically test this assumption on news articles from the business, U.S. inter-national relations, sports and science journalism domains. Our findings clearly indicate that about half of the news texts in our study are in fact not content-dense and motivate the development of a supervised content-density detector. We heuristically label a large training corpus for the task and train a two-layer classifying model based on lexical and unlexicalized syntactic features. On manually annotated data, we compare the performance of domain-specific classifiers, trained on data only from a given news domain and a general classifier in which data from all four domains is pooled together. Our annotation and prediction experiments demonstrate that the concept of content density varies depending on the domain and that naive annotators provide judgement biased toward the stereotypical domain label. Domain-specific classifiers are more accurate for domains in which content-dense texts are typically fewer. Domain independent classifiers repro-duce better naive crowdsourced judgements. Classification prediction is high across all conditions, around 80%. Read More
Detecting (Un)Important Content for Single-Document News Summarization
We present a robust approach for detecting intrinsic sentence importance in news,by training on two corpora of document-summary pairs. When used for single-document summarization, our approach,combined with the “beginning of document” heuristic, outperforms a state-of-the-art summarizer and the beginning-of-article baseline in both automatic and manual evaluations. These results represent an important advance because in the absence of cross-document repetition, single document summarizers for news have not been able to consistently outperform the strong beginning-of-article baseline. Read More
Rick's Cafe AI 