Prompt learning methods adapt pre-trained language models to downstream applications by using a task-specific prompt together with the input. Most of the current work on prompt learning in text generation relies on a shared dataset-level prompt for all examples in the dataset. We extend this approach and propose a dynamic method, Control Prefixes, which allows for the inclusion of conditional input-dependent information in each prompt. Control Prefixes is at the intersection of prompt learning and controlled generation, empowering the model to have finer-grained control during text generation. The method incorporates attribute-level learnable representations into different layers of a pre-trained transformer, allowing for the generated text to be guided in a particular direction. We provide a systematic evaluation of the technique and apply it to five datasets from the GEM benchmark for natural language generation (NLG). We present state-of-the-art results on several data-to-text datasets, including WebNLG.

Recommendation algorithms are susceptible to popularity bias: a tendency to recommend popular items even when they fail to meet user needs. A related issue is that the recommendation quality can vary by demographic groups. Marginalized groups or groups that are under-represented in the training data may receive less relevant recommendations from these algorithms compared to others. In a recent study, Ekstrand et al. [15] investigate how recommender performance varies according to popularity and demographics, and find statistically significant differences in recommendation utility between binary genders on two datasets, and significant effects based on age on one dataset. Here we reproduce those results and extend them with additional analyses. We find statistically significant differences in recommender performance by both age and gender. We observe that recommendation utility steadily degrades for older users, and is lower for women than men. We also find that the utility is higher for users from countries with more representation in the dataset. In addition, we find that total usage and the popularity of consumed content are strong predictors of recommender performance and also vary significantly across demographic groups.

Existing studies on semantic parsing focus primarily on mapping a natural-language utterance to a corresponding logical form in one turn. However, because natural language can contain a great deal of ambiguity and variability, this is a difficult challenge. In this work, we investigate an interactive semantic parsing framework that explains the predicted logical form step by step in natural language and enables the user to make corrections through natural-language feedback for individual steps. We focus on question answering over knowledge bases (KBQA) as an instantiation of our framework, aiming to increase the transparency of the parsing process and help the user appropriately trust the final answer. To do so, we construct INSPIRED, a crowdsourced dialogue dataset derived from the ComplexWebQuestions dataset. Our experiments show that the interactive framework with human feedback has the potential to greatly improve overall parse accuracy. Furthermore, we develop a pipeline for dialogue simulation to evaluate our framework w.r.t. a variety of state-of-the-art KBQA models without involving further crowdsourcing effort. The results demonstrate that our interactive semantic parsing framework promises to be effective across such models.

Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., BlenderBot) or goal-oriented systems (e.g., MinTL), are language models (LMs) fine-tuned on large conversational datasets. Training these models is expensive, both in terms of computational resources and time, and it is hard to keep them up to date with new conversational skills. A simple yet unexplored solution is prompt-based few-shot learning (Brown et al. 2020) which does not require gradient-based fine-tuning but instead uses a few examples in the LM context as the only source of learning. In this paper, we explore prompt-based few-shot learning in dialogue tasks. We benchmark LMs of different sizes in nine response generation tasks, which include four knowledge-grounded tasks, a task-oriented generations task, three open-chat tasks, and controlled stylistic generation, and five conversational parsing tasks, which include dialogue state tracking, graph path generation, persona information extraction, document retrieval, and internet query generation. The current largest released LM (GPT-J-6B) using prompt-based few-shot learning, and thus requiring no training, achieves competitive performance to fully trained state-of-the-art models. Moreover, we propose a novel prompt-based few-shot classifier, that also does not require any fine-tuning, to select the most appropriate prompt given a dialogue history. Finally, by combining the power of prompt-based few-shot learning and a Skill Selector, we create an end-to-end chatbot named the Few-Shot Bot (FSB), which automatically selects the most appropriate conversational skill, queries different knowledge bases or the internet, and uses the retrieved knowledge to generate a human-like response, all using only few dialogue examples per skill.

In this paper, we present an approach to Complex Event Processing (CEP) that is based on DeepProbLog. This approach has the following objectives: (i) allowing the use of subsymbolic data as an input, (ii) retaining the flexibility and modularity on the definitions of complex event rules, (iii) allowing the system to be trained in an end-to-end manner and (iv) being robust against noisily labelled data. Our approach makes use of DeepProbLog to create a neuro-symbolic architecture that combines a neural network to process the subsymbolic data with a probabilistic logic layer to allow the user to define the rules for the complex events. We demonstrate that our approach is capable of detecting complex events from an audio stream. We also demonstrate that our approach is capable of training even with a dataset that has a moderate proportion of noisy data.

Science fiction movies like "Blade Runner" and "The Terminator" have defined the perception of artificial intelligence within popular culture. For most people, the term AI conjures up images of a dystopian future dominated by humanoid robots that have taken over the world. This common conception leads to the dismissal of the technology as impossible, or at least faroff in the future. Few people realize that we are already delving into a world dominated by AI, and it's nothing like "The Terminator." The actual risks posed by artificial intelligence have nothing to do with killer robots; they relate to the machine-learning algorithms that recommend content on the internet.

If you missed the chance to grab the new Echo Show 8 during Amazon's Prime Day event in July, you may want to check the smart display's listing on Amazon. That's only $5 more than what it was listed for during Prime Day, and it's certainly not a bad deal for a relatively new device that was only released in June. We gave the Echo Show 8 a score of 87 in our review. Between this device and its smaller 5-inch sibling, it received more upgrades from the previous generation, including a faster octa-core processor. It also has a 13-megapixel wide-angle camera that's a huge improvement over the previous version's one-megapixel sensor.

PLEASANTON CA, Sept. 30, 2021 (GLOBE NEWSWIRE) -- The latest study titled "Global Artificial Intelligence in Manufacturing Market Ecosystem By Components; By Deployment; By Technology; By Application; By Device; By Region; By End Users (Logistics, Healthcare, Automotive, Retail, BFSI, Defence, Aerospace, Oil & Gas, Others) Forecast by 2027" published by AllTheResearch, features an analysis of the current and future scenario of the global Artificial Intelligence (AI) in Manufacturing Market. The Global Artificial Intelligence (AI) in Manufacturing Market was valued at USD 2.1 Bn in 2020 and is expected to reach USD 11.5 Bn by 2027, with a growing CAGR of 27.2% during the forecast period. The Artificial Intelligence in manufacturing market is forecasted to grow at a high rate owing to the accelerating innovations in industrial IoT and automation. The manufacturing industry is expected to be among the market leader in the artificial intelligence market. Further, the manufacturing industry is also expected to display the fastest growth during the forecast period due to rapid digital transformation to promote smart solutions in factories, logistics and management.

With a rise in false, inaccurate, and misleading information in propaganda, news, and social media, real-world Question Answering (QA) systems face the challenges of synthesizing and reasoning over contradicting information to derive correct answers. This urgency gives rise to the need to make QA systems robust to misinformation, a topic previously unexplored. We study the risk of misinformation to QA models by investigating the behavior of the QA model under contradicting contexts that are mixed with both real and fake information. QA, which contains over 10K human-written and model-generated contradicting pairs of contexts. Experiments show that QA models are vulnerable under contradicting contexts brought by misinformation. To defend against such threat, we build a misinformation-aware QA system as a counter-measure that integrates question answering and misinformation detection in a joint fashion. A typical Question Answering (QA) system (Chen et al., 2017; Yang et al., 2019; Karpukhin et al., 2020; Lewis et al., 2020b) starts by retrieving a set of relevant context documents from the Web, which are then examined by a machine reader to identify the correct answer. Existing work equate Wikipedia as the web corpus. Therefore, all retrieved context documents are assumed to be clean and trustable. However, real-world QA faces a much noisier environment, where the web corpus is tainted with misinformation.

Semantic parsing is the task of producing a structured meaning representation for natural language utterances or questions. Recent research has pointed out that the commonly-used sequence-to-sequence (seq2seq) semantic parsers struggle to generalize systematically, i.e. to handle examples that require recombining known knowledge in novel settings. In this work, we show that better systematic generalization can be achieved by producing the meaning representation (MR) directly as a graph and not as a sequence. To this end we propose LAGr, the Labeling Aligned Graphs algorithm that produces semantic parses by predicting node and edge labels for a complete multi-layer input-aligned graph. The strongly-supervised LAGr algorithm requires aligned graphs as inputs, whereas weakly-supervised LAGr infers alignments for originally unaligned target graphs using an approximate MAP inference procedure. On the COGS and CFQ compositional generalization benchmarks the strongly- and weakly- supervised LAGr algorithms achieve significant improvements upon the baseline seq2seq parsers.