This paper presents DynRank, a novel framework for enhancing passage retrieval in open-domain question-answering systems through dynamic zero-shot question classification. Traditional approaches rely on static prompts and pre-defined templates, which may limit model adaptability across different questions and contexts. In contrast, DynRank introduces a dynamic prompting mechanism, leveraging a pre-trained question classification model that categorizes questions into fine-grained types. Based on these classifications, contextually relevant prompts are generated, enabling more effective passage retrieval. We integrate DynRank into existing retrieval frameworks and conduct extensive experiments on multiple QA benchmark datasets.

Node Importance Estimation (NIE) is a task that quantifies the importance of node in a graph. Recent research has investigated to exploit various information from Knowledge Graphs (KGs) to estimate node importance scores. However, the semantic information in KGs could be insufficient, missing, and inaccurate, which would limit the performance of existing NIE models. To address these issues, we leverage Large Language Models (LLMs) for semantic augmentation thanks to the LLMs' extra knowledge and ability of integrating knowledge from both LLMs and KGs. To this end, we propose the LLMs Empowered Node Importance Estimation (LENIE) method to enhance the semantic information in KGs for better supporting NIE tasks. To our best knowledge, this is the first work incorporating LLMs into NIE. Specifically, LENIE employs a novel clustering-based triplet sampling strategy to extract diverse knowledge of a node sampled from the given KG. After that, LENIE adopts the node-specific adaptive prompts to integrate the sampled triplets and the original node descriptions, which are then fed into LLMs for generating richer and more precise augmented node descriptions. These augmented descriptions finally initialize node embeddings for boosting the downstream NIE model performance. Extensive experiments demonstrate LENIE's effectiveness in addressing semantic deficiencies in KGs, enabling more informative semantic augmentation and enhancing existing NIE models to achieve the state-of-the-art performance. The source code of LENIE is freely available at \url{https://github.com/XinyuLin-FZ/LENIE}.

Movie posters are not just decorative; they are meticulously designed to capture the essence of a movie, such as its genre, storyline, and tone/vibe. For decades, movie posters have graced cinema walls, billboards, and now our digital screens as a form of digital posters. Movie genre classification plays a pivotal role in film marketing, audience engagement, and recommendation systems. Previous explorations into movie genre classification have been mostly examined in plot summaries, subtitles, trailers and movie scenes. Movie posters provide a pre-release tantalizing glimpse into a film's key aspects, which can ignite public interest. In this paper, we presented the framework that exploits movie posters from a visual and textual perspective to address the multilabel movie genre classification problem. Firstly, we extracted text from movie posters using an OCR and retrieved the relevant embedding. Next, we introduce a cross-attention-based fusion module to allocate attention weights to visual and textual embedding. In validating our framework, we utilized 13882 posters sourced from the Internet Movie Database (IMDb). The outcomes of the experiments indicate that our model exhibited promising performance and outperformed even some prominent contemporary architectures.

When it comes to new tech, 50 doesn't get you a lot-- except perhaps during Black Friday sales. Surprisingly, quite a few of the smaller electronics and accessories we recommend are currently on sale right now for less than 50. These deals include picks from our guides to accessories guides, portable batteries, budget earbuds and smart speakers. Everything on this list has earned the Engadget nod of approval -- like Anker's Nano charger ( 13), Belkin's AirTag holder ( 15) and PopSocket phone grips ( 15). These picks come from stuff we tested for our reviews and buying guides or from personal use and brands we know to be reputable -- so you don't have to guess whether these Black Friday tech deals are worth your (less than) 50. Amazon Echo Pop (2023) for 18 ( 22 off): Amazon's smallest Echo will fit in any room in your home, so Alexa can add things to your shopping list, set a timer, or answer questions (like "What's a bomb cyclone?" or "Who is Penelope Cruz married to?") from anywhere. Anker Nano Charger 30W USB-C for 13 ( 7 off): This compact 30-watt wall charger is smaller than others of its wattage and can speedily juice up an iPhone or Android handset.

Microsoft is OpenAI's major backer. In a statement, Torstar, Postmedia, The Globe and Mail, The Canadian Press, and CBC/Radio-Canada said OpenAI was scraping large swaths of content to develop its products without getting permission or compensating content owners. "Journalism is in the public interest. OpenAI using other companies' journalism for their own commercial gain is not. A New York federal judge dismissed a lawsuit on November 7 against OpenAI that claimed it misused articles from news outlets Raw Story and AlterNet.

The joint lawsuit accuses the company of "capitalizing and profiting" from the unauthorized use of their content for ChatGPT. The legal action was filed in the Ontario Superior Court of Justice. The plaintiffs include CBC/Radio-Canada, Postmedia, Metroland, the Toronto Star, the Globe and Mail and The Canadian Press. They're seeking punitive damages from OpenAI, payments for any profits the ChatGPT creator made from using their news articles and a ban on further use of their content. "OpenAI is capitalizing and profiting from the use of this content, without getting permission or compensating content owners."

The football is over, the turkey is picked clean, and the fam is heading home. Now, it's time to shop, shop, shop, and we have the absolute best Black Friday deals of 2024 for you. The WIRED team has been diligently digging to find the bargains worth your while, and we'll be here, working shifts for the next four days, to bring you every deal you need to know about. So grab a beverage, a turkey sandwich, and your wallet or purse. For Black Friday, we cross-reference our buying guide recommendations with the latest sale prices to find the absolute best Black Friday deals on the gadgetry worth owning. An actual person from the WIRED Reviews team has tested every product we list in our deals coverage, and we don't recommend anything we don't like. We always strive to find deals at their best price ever, or very close to it (some match previous discounts, but we have never seen them lower unless stated). We test products year-round and handpicked these deals. The discount amounts we show ...

The Agency

We survey clinical document corpora, with focus on German textual data. Due to rigid data privacy legislation in Germany these resources, with only few exceptions, are stored in safe clinical data spaces and locked against clinic-external researchers. This situation stands in stark contrast with established workflows in the field of natural language processing where easy accessibility and reuse of data collections are common practice. Hence, alternative corpus designs have been examined to escape from this data poverty. Besides machine translation of English clinical datasets and the generation of synthetic corpora with fictitious clinical contents, several other types of domain proxies have come up as substitutes for authentic clinical documents. Common instances of close proxies are medical journal publications, clinical therapy guidelines, drug labels, etc., more distant proxies include online encyclopedic medical articles or medical contents from social media channels. After PRISM-conformant screening of 359 hits from four bibliographic systems, 75 relevant documents were finally selected for this review and 59 distinct corpora were determined. We identified 24 real clinical corpora (from 40 publications) out of which only 5 are publicly distributable. 2 translations of real corpora and 3 synthetic ones complement the set of clinical corpora. 14 corpora were categorized as close domain proxies, 16 as distant ones. There is a clear divide between the large number of non-accessible authentic clinical German-language corpora and their publicly accessible substitutes: translated or synthetic, close or more distant proxies. So on first sight, the data bottleneck seems broken. Intuitively yet, differences in genre-specific writing style, wording and medical domain expertise in this typological space are also obvious. This raises the question how valid alternative corpus designs really are.

The tokenization of speech with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context. Traditionally such tokenization models have concentrated on low parameter-count architectures using only components with strong inductive biases. In this work we show that by scaling a transformer architecture with large parameter count to this problem, and applying a flexible Finite Scalar Quantization (FSQ) based bottleneck, it is possible to reach state-of-the-art speech quality at extremely low bit-rates of 400 or 700 bits-per-second. The trained models strongly out-perform existing baselines in both objective and subjective tests. Compressed coding of audio and speech data in digital format has been an active area of research since the 1970s, and reached particular prominence in the late 1990s with the emergence of mp3 (Painter & Spanias, 2000).