With the rise of social media and online news sources, fake news has become a significant issue globally. However, the detection of fake news in low resource languages like Bengali has received limited attention in research. In this paper, we propose a methodology consisting of four distinct approaches to classify fake news articles in Bengali using summarization and augmentation techniques with five pre-trained language models. Our approach includes translating English news articles and using augmentation techniques to curb the deficit of fake news articles. Our research also focused on summarizing the news to tackle the token length limitation of BERT based models. Through extensive experimentation and rigorous evaluation, we show the effectiveness of summarization and augmentation in the case of Bengali fake news detection. We evaluated our models using three separate test datasets. The BanglaBERT Base model, when combined with augmentation techniques, achieved an impressive accuracy of 96% on the first test dataset. On the second test dataset, the BanglaBERT model, trained with summarized augmented news articles achieved 97% accuracy. Lastly, the mBERT Base model achieved an accuracy of 86% on the third test dataset which was reserved for generalization performance evaluation. The datasets and implementations are available at https://github.com/arman-sakif/Bengali-Fake-News-Detection

The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary. In this paper, we formulate text generation as progressively copying text segments (e.g., words or phrases) from an existing text collection. We compute the contextualized representations of meaningful text segments and index them using efficient vector search toolkits. The task of text generation is then decomposed into a series of copy-and-paste operations: at each time step, we seek suitable text spans from the text collection rather than selecting from a standalone vocabulary. Experiments on the standard language modeling benchmark (WikiText-103) show that our approach achieves better generation quality according to both automatic and human evaluations. Besides, its inference efficiency is comparable to token-level autoregressive models thanks to the reduction of decoding steps. We also show that our approach allows for effective domain adaptation by simply switching to domain-specific text collection without extra training. Finally, we observe that our approach attains additional performance gains by simply scaling up to larger text collections, again without further training. Specifically, LMs generate the next-token distribution over a fixed vocabulary for any given prefix.

Before deploying a language model (LM) within a given domain, it is important to measure its tendency to generate factually incorrect information in that domain. Existing factual generation evaluation methods focus on facts sampled from the LM itself, and thus do not control the set of evaluated facts and might under-represent rare and unlikely facts. We propose FACTOR: Factual Assessment via Corpus TransfORmation, a scalable approach for evaluating LM factuality. FACTOR automatically transforms a factual corpus of interest into a benchmark evaluating an LM's propensity to generate true facts from the corpus vs. similar but incorrect statements. We use our framework to create two benchmarks: Wiki-FACTOR and News-FACTOR. We show that: (i) our benchmark scores increase with model size and improve when the LM is augmented with retrieval; (ii) benchmark score correlates with perplexity, but the two metrics do not always agree on model ranking; and (iii) when perplexity and benchmark score disagree, the latter better reflects factuality in open-ended generation, as measured by human annotators. We make our data and code publicly available in https://github.com/AI21Labs/factor.

While summarization has been extensively researched in natural language processing (NLP), cross-lingual cross-temporal summarization (CLCTS) is a largely unexplored area that has the potential to improve cross-cultural accessibility and understanding. This paper comprehensively addresses the CLCTS task, including dataset creation, modeling, and evaluation. We build the first CLCTS corpus, leveraging historical fictive texts and Wikipedia summaries in English and German, and examine the effectiveness of popular transformer end-to-end models with different intermediate finetuning tasks. Additionally, we explore the potential of ChatGPT for CLCTS as a summarizer and an evaluator. Overall, we report evaluations from humans, ChatGPT, and several recent automatic evaluation metrics where we find that our intermediate task finetuned end-to-end models generate bad to moderate quality summaries; ChatGPT as a summarizer (without any finetuning) provides moderate to good quality outputs and as an evaluator correlates moderately with human evaluations but is prone to giving lower scores. ChatGPT also seems very adept at normalizing historical text and outperforms context-unaware spelling normalization tools such as Norma. We finally test ChatGPT in a scenario with adversarially attacked and unseen source documents and find that ChatGPT profits from its prior knowledge to a certain degree, with better performances for omission and entity swap than negation against its prior knowledge. This benefit inflates its assessed quality as ChatGPT performs slightly worse for unseen source documents compared to seen documents. We additionally introspect our models' performances to find that longer, older and more complex source texts (all of which are more characteristic for historical language variants) are harder to summarize for all models, indicating the difficulty of the CLCTS task.

Amazon Prime Day is back again. It wasn't that long since the last one--the retailer held its first-ever fall Prime Day sales event in 2022, and there will be another one this fall as well. But right now, the two-day event runs through July 12. We've spent hours combing through thousands of lists to find the best Prime Day deals 2023 on WIRED-tested gear, from Fire tablets to video games and Apple Watches to standing desks. Updated Wednesday, July 12: We added a bunch more deals we love and added prices and links. If you buy something using links in our stories, we may earn a commission. This helps support our journalism. See the rest of our Phone and Tablet Deals for Prime Day here. Even with the addition of the 10th-generation iPad, we still think the ninth-generation iPad (8/10, WIRED Recommends) from 2021 is the best iPad for most people. It has the same shape and size as its predecessors, so all current accessories will work, including the first-generation Apple Pencil and Apple's Smart Keyboard. It retains the classic Home button with Touch ID plus thick borders around the 10.2-inch screen. This is the lowest price we've tracked. The Apple Pencil is one of the most useful tools you can add to the iPad. The second-gen pencil works with nearly every iPad in Apple's current lineup (except for the 9th- and 10th-gen iPad; if you have one, the first-gen Pencil is also on sale). Like a normal pencil, your lines get thicker as you press down harder. The Pencil is also great for navigating iPadOS, which has handwriting support in various search fields so you don't need to switch to the keyboard to type. It pairs and charges automatically when you stick it to the edge of the slate. Logitech's Combo Touch case is detachable, so you can ditch the keyboard when you don't need it and still have a kickstand case. It's fairly slim, with a lovely fabric texture, and the kickstand easily passes the lap test--it didn't wobble much or make the iPad fall off while you typed with it on your lap. If you want a bigger screen for travel, the iPad Mini (8/10, WIRED Recommends) has the edge over its peers. The design mimics the iPad Pro, with slim bezels around the 8.3-inch screen. Its compact size makes it the best slate to take with you everywhere. You might even be able to fit it into your cargo pants.

Fox News contributor Dr. Marc Siegel weighs in on how artificial intelligence can change the patient-doctor relationship on'America's Newsroom.' Japanese police have admitted that they allowed artificial intelligence (AI) to influence their decision not to provide protective custody to a child who later died in her mother's care. "The AI figures are only for reference," Mie Prefecture Gov. Katsuyuki Ichimi said at a press conference on Tuesday, stressing the importance of the judgment of those in charge. "We are not in a position to draw a conclusion whether the method of utilizing this data used this time was 100% good," indicating he intended to refer the matter to a third-party committee consisting of outside experts to determine further use of the system, Japanese outlet Jiji reported. Police considered the case of a 4-year-old girl in the city of Tsu, running it through an AI program introduced in 2020 and trained with the data of 6,000 to 13,000 cases.

Amazon Prime Day is back again. It wasn't that long since the last one--the retailer held its first-ever fall Prime Day sales event in 2022, and there will be another one this fall as well. But right now, the two-day event runs through July 12. We've spent hours combing through thousands of lists to find the best Prime Day deals 2023 on WIRED-tested gear, from Fire tablets to video games and Apple Watches to standing desks. Updated Wednesday, July 12: We added a bunch more deals we love and added prices and links. If you buy something using links in our stories, we may earn a commission. This helps support our journalism. See the rest of our Phone and Tablet Deals for Prime Day here. Even with the addition of the 10th-generation iPad, we still think the ninth-generation iPad (8/10, WIRED Recommends) from 2021 is the best iPad for most people. It has the same shape and size as its predecessors, so all current accessories will work, including the first-generation Apple Pencil and Apple's Smart Keyboard. It retains the classic Home button with Touch ID plus thick borders around the 10.2-inch screen. This is the lowest price we've tracked. The Apple Pencil is one of the most useful tools you can add to the iPad. The second-gen pencil works with nearly every iPad in Apple's current lineup (except for the 9th- and 10th-gen iPad; if you have one, the first-gen Pencil is also on sale). Like a normal pencil, your lines get thicker as you press down harder. The Pencil is also great for navigating iPadOS, which has handwriting support in various search fields so you don't need to switch to the keyboard to type. It pairs and charges automatically when you stick it to the edge of the slate. Logitech's Combo Touch case is detachable, so you can ditch the keyboard when you don't need it and still have a kickstand case. It's fairly slim, with a lovely fabric texture, and the kickstand easily passes the lap test--it didn't wobble much or make the iPad fall off while you typed with it on your lap. If you want a bigger screen for travel, the iPad Mini (8/10, WIRED Recommends) has the edge over its peers. The design mimics the iPad Pro, with slim bezels around the 8.3-inch screen. Its compact size makes it the best slate to take with you everywhere. You might even be able to fit it into your cargo pants.

American action movie villains have always acted as a sort of paranoia litmus test, capturing a snapshot of the particular anxieties plaguing the country and its citizens at any given time. In the 1990s and '00s, with the Red Menace long forgotten, movies leaned heavily on the awful "bad Arab" trope, pulling their villains from the Middle East. Other recent smash-'em-ups have made bad guys out of rogue spies, shadowy cyber terrorists, and self-interested arms dealers, all common players in the global news landscape. But for Mission: Impossible--Dead Reckoning Part One, out this week, writers Bruce Geller, Erik Jendresen, and Christopher McQuarrie (who also directed the movie) made their big bad--known as The Entity--out of a slightly more amorphous fear: that of an all-powerful, all-seeing, sentient AI. It has access to anything with an online network and can use those evil techno powers to manipulate everything from global military superpowers to a grandma with a gun.

Discord has updated its policy meant to protect children and teens on its platform after reports came out that predators have been using the app to create and spread child sexual abuse materials (CSAM), as well as to groom young teens. The platform now explicitly prohibits AI-generated photorealistic CSAM. As The Washington Post recently reported, the rise in generative AI has also led to the explosion of lifelike images with sexual depictions of children. The publication had seen conversations about the use of Midjourney -- a text-to-image generative AI on Discord -- to create inappropriate images of children. In addition to banning AI-generated CSAM, Discord now also explicitly prohibits any other kind of text or media content that sexualizes children.

Dropped off at a bus stop after dark, she finds herself standing alone in an eerily quiet town. With her new colleagues nowhere in sight, she surveys the quaint seaside square, muttering a curse under her breath. It turns out, no matter how long you're gone, home is always exactly how you left it. It's not just our pixel-art protagonist that's struck by a sense of deja vu. Part walking simulator, part branching-dialogue talk'em up, Oxenfree II blends the paranormal with the interpersonal, seeing players fend off vengeful ghosts while carefully navigating the ever-perilous minefield of human relationships.