Most existing work in data selection for In-Context Learning (ICL) has focused on constructing demonstrations from ground truth annotations, with limited attention given to selecting reliable self-generated annotations. In this work, we propose a three-step semi-supervised ICL framework: annotation generation, demonstration selection, and semi-supervised inference. Our baseline, Naive-SemiICL, which prompts select high-confidence self-generated demonstrations for ICL prompting, outperforms a 16-shot baseline by an average of 9.94% across 16 datasets. We further introduce IterPSD, an annotation approach that refines pseudo-demonstrations iteratively, achieving up to 6.8% additional gains in classification tasks. Lastly, we reveal a scaling law for semi-supervised ICL, where models achieve optimal performance with over 1,000 demonstrations.

Large language models (LLM) have received label. Hence, as an alternative solution, we propose more spotlight for generative tasks such as a (p)araphrasing and (ag)gregating approach question answering, dialogue, summarization, etc (PAG) to fix LLM errors on intent classification (Peng et al., 2023; Beeching et al., 2023). We argue task, where input query is paraphrased to perform that key NLP tasks such as intent classification is intent classification on its multiple variations. Our widely utilized in real-world dialogue systems and approach is inspired by observations that often user thus should also be given high emphasis when evaluating queries are unclear which when rephrased, improve LLMs, considering their proven capability downstream systems (Brabant et al., 2022). PAG-to solve a wide range of NLP tasks (Beeching et al., LLM leverages the versatility of LLMs to perform 2023). In this work, we focus on studying LLMs three tasks: paraphrasing, intent classification, and for large intent classification tasks with two intent aggregation. We first generate N paraphrases of classification datasets: CLINC (Larson et al., 2019) the input query, then generate classification predictions which has 150 classes and Banking (Casanueva for the original query and its N paraphrases et al., 2020) which has 77 classes.

We introduce ClusterLLM, a novel text clustering framework that leverages feedback from an instruction-tuned large language model, such as ChatGPT. Compared with traditional unsupervised methods that builds upon "small" embedders, ClusterLLM exhibits two intriguing advantages: (1) it enjoys the emergent capability of LLM even if its embeddings are inaccessible; and (2) it understands the user's preference on clustering through textual instruction and/or a few annotated data. First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions , where A, B and C are similar data points that belong to different clusters according to small embedder. We empirically show that this strategy is both effective for fine-tuning small embedder and cost-efficient to query ChatGPT. Second, we prompt ChatGPT for helps on clustering granularity by carefully designed pairwise questions , and tune the granularity from cluster hierarchies that is the most consistent with the ChatGPT answers. Extensive experiments on 14 datasets show that ClusterLLM consistently improves clustering quality, at an average cost of ~$0.6 per dataset. The code will be available at https://github.com/zhang-yu-wei/ClusterLLM.

Conversational artificial intelligence has the potential to change the way you provide customer support. This technology can simulate human-computer interactions. These platforms may be a game-changer for your customer care staff because of their clever features. However, to receive the top-tier help that AI can provide, you must first choose the top conversational AI platforms for your company. Conversational AI platforms have a wide range of corporate applications, including client acquisition and retention.

"Breaking Bots" by Clinc's Founder CEO Jason Mars is released with ForbesBooks. This release is posted on behalf of ForbesBooks (operated by Advantage Media Group under license.) NEW YORK (March 16, 2021) -- Breaking Bots: Inventing a New Voice in the AI Revolution by Clinc's Founder CEO Dr. Jason Mars is available now. The book is published with ForbesBooks, the exclusive business book publishing imprint of Forbes. In setting the stage for his new book, Jason Mars considers how technology has shaped the arc of human history, time and again.

NVIDIA today announced breakthroughs in language understanding that allow businesses to engage more naturally with customers using real-time conversational AI. NVIDIA's AI platform is the first to train one of the most advanced AI language models -- BERT -- in less than an hour and complete AI inference in just over 2 milliseconds. This groundbreaking level of performance makes it possible for developers to use state-of-the-art language understanding for large-scale applications they can make available to hundreds of millions of consumers worldwide. Early adopters of NVIDIA's performance advances include Microsoft and some of the world's most innovative startups, which are harnessing NVIDIA's platform to develop highly intuitive, immediately responsive language-based services for their customers. Limited conversational AI services have existed for several years.

Nvidia says it's achieved significant advances in conversation natural language processing (NLP) training and inference, enabling more complex, immediate-response interchanges between customers and chatbots. And the company says it has a new language training model in the works that dwarfs existing ones. Nvidia said its DGX-2 AI platform trained the BERT-Large AI language model in less than an hour and performed AI inference in 2 milliseconds making "it possible for developers to use state-of-the-art language understanding for large-scale applications…." Training: Running the largest version of Bidirectional Encoder Representations from Transformers (BERT-Large) language model, an Nvidia DGX SuperPOD with 92 Nvidia DGX-2H systems running 1,472 V100 GPUs cut training from several days to 53 minutes. A single DGX-2 system trained BERT-Large in 2.8 days.

While new technologies continue to transform the healthcare industry in unprecedented ways administrative functions still burden the healthcare industry with 1 in every 3 dollars spent on administration. Olive the company that introduced healthcares first digital employee has joined forces with Clinc another trailblazer in Artificial Intelligence to free up time and resources by adding conversational AI capabilities to its existing technology. The combined offering allows Olives digital healthcare employee to bring hospitals and health systems broader applications across revenue cycle supply chain and other financial and operational departments.

Clinc, a four-year-old conversational AI startup, is teaming up with Ford to power voice recognition in the Detroit automaker's cars. The two companies announced the collaboration today during the Detroit Auto Show, at a panel hosted by Inforum about machine learning and the future of in-vehicle technology. According to Clinc CEO Dr. Jason Mars, the Ann Arbor company's automotive platform, which was announced in September 2018, is enabling drivers and passengers to control vehicle systems using natural language in Ford's connected car lab. They can make verbal requests to turn up the air conditioning, adjust cruise control, and check fuel mileage, or ask if there's enough gas for a trip to a specific address. "What we found in our collaboration with Ford is that when you bring in a conversational experience that allows you to talk to your car naturally, it improves the lives of people driving those cars," Mars said.

Clinc is expanding its focus on fintech into new verticals that could take advantage of its conversational artificial intelligence. The Ann Arbor-based company recently took the wraps off its new system that aims to provide quick-service restaurants like McDonald's and Taco Bell with a voice assist…