Given a text description, most existing semantic parsers synthesize a program in one shot. However, in reality, the description can be ambiguous or incomplete, solely based on which it is quite challenging to produce a correct program. In this paper, we investigate interactive semantic parsing for If-Then recipes where an agent can interact with users to resolve ambiguities. We develop a hierarchical reinforcement learning (HRL) based agent that can improve the parsing performance with minimal questions to users. Results under both simulation and human evaluation show that our agent substantially outperforms non-interactive semantic parsers and rule-based agents.

Nefarious actors on social media and other platforms often spread rumors and falsehoods through images whose metadata (e.g., captions) have been modified to provide visual substantiation of the rumor/falsehood. This type of modification is referred to as image repurposing, in which often an unmanipulated image is published along with incorrect or manipulated metadata to serve the actor's ulterior motives. We present the Multimodal Entity Image Repurposing (MEIR) dataset, a substantially challenging dataset over that which has been previously available to support research into image repurposing detection. The new dataset includes location, person, and organization manipulations on real-world data sourced from Flickr. We also present a novel, end-to-end, deep multimodal learning model for assessing the integrity of an image by combining information extracted from the image with related information from a knowledge base. The proposed method is compared against state-of-the-art techniques on existing datasets as well as MEIR, where it outperforms existing methods across the board, with AUC improvement up to 0.23.

As the World Economic Forum publishes the most extensive and in-depth report yet on artificial intelligence's transformation of the financial services sector, Internet of Business editor Chris Middleton presents a 3,500-word breakdown of the document's key findings and highlights. The financial services sector is in the vanguard of deploying artificial intelligence (AI) worldwide. However, the technology has the potential to be either a transformative and beneficial force, or a destabilising, even existential threat to the global financial system, according to the World Economic Forum. This risks of economic contagion spreading via the technology are real, it says. The WEF has published an in-depth report, The New Physics of Financial Services: Understanding how artificial intelligence is transforming the financial ecosystem, produced in collaboration with C-level executives, analysts, and technology specialists from across every part of the industry. The 166-page sector analysis finds that the bonds that have historically held financial institutions together are weakening as a result of new technologies. This is creating new threats, new opportunities, and new centres of gravity where emerging and established capabilities are being combined in unexpected ways.

The Nature Morte gallery in New Delhi opens its doors to a unique, one of kind show today. Titled'Gradient Descent', the show is the country's first Artificial Intelligence (AI) art exhibition. Curated by 64/1, a Bengaluru-based curation and research collective (founded by Raghava KK and Karthik Kalyanaraman that focuses on raising awareness on AI's place in the realm of contemporary art), 'Gradient Descent' showcases the works of seven, carefully picked artists from the US, Japan, Germany, Turkey, India, UK and New Zealand. Each of these artists, equipped with a strong foundational background in artificial neural networking, has collaborated with AI to produce art. Conceptualised and planned meticulously since February, the show will run till 15 September.

Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains. In this manuscript, we develop a novel method, transfer latent representation (TLR), to learn a better latent space. Specifically, we design an objective function based on a simple linear autoencoder to derive the latent representations of both domains. The encoder in the autoencoder aims to project the data of both domains into a robust latent space. Besides, the decoder imposes an additional constraint to reconstruct the original data, which can preserve the common properties of both domains and reduce the noise that causes domain shift. Experiments on cross-domain tasks demonstrate the advantages of TLR over competing methods.

A few years back, cloud computing transformed customer management, giving every small and medium business access to unified data and communication platforms without the need to make heavy investments in IT infrastructure and staff. This time around, the next revolution in the space is being driven by artificial intelligence algorithms that help businesses automate customer outreach and make optimal use of data. Beneath the surface of the roiling sea of data we're generating hide exceptional business and sales opportunities. But the problem is there's now more information available than limited human resources and legacy tools can handle. Fortunately, making sense of data, both structured and unstructured, is something that artificial intelligence is becoming increasingly proficient at.

In this paper, we propose exact passive-aggressive (PA) online algorithms for learning to rank. The proposed algorithms can be used even when we have interval labels instead of actual labels for examples. The proposed algorithms solve a convex optimization problem at every trial. We find exact solution to those optimization problems to determine the updated parameters. We propose support class algorithm (SCA) which finds the active constraints using the KKT conditions of the optimization problems. These active constrains form support set which determines the set of thresholds that need to be updated. We derive update rules for PA, PA-I and PA-II. We show that the proposed algorithms maintain the ordering of the thresholds after every trial. We provide the mistake bounds of the proposed algorithms in both ideal and general settings. We also show experimentally that the proposed algorithms successfully learn accurate classifiers using interval labels as well as exact labels. Proposed algorithms also do well compared to other approaches.

It is conventional wisdom in machine learning and data mining that logical models such as rule sets are more interpretable than other models, and that among such rule-based models, simpler models are more interpretable than more complex ones. In this position paper, we question this latter assumption by focusing on one particular aspect of interpretability, namely the plausibility of models. Roughly speaking, we equate the plausibility of a model with the likeliness that a user accepts it as an explanation for a prediction. In particular, we argue that, all other things being equal, longer explanations may be more convincing than shorter ones, and that the predominant bias for shorter models, which is typically necessary for learning powerful discriminative models, may not be suitable when it comes to user acceptance of the learned models. To that end, we first recapitulate evidence for and against this postulate, and then report the results of an evaluation in a crowd-sourcing study based on about 3.000 judgments. The results do not reveal a strong preference for simple rules, whereas we can observe a weak preference for longer rules in some domains. We then relate these results to well-known cognitive biases such as the conjunction fallacy, the representative heuristic, or the recogition heuristic, and investigate their relation to rule length and plausibility.

A time series can have different properties depending on the generating process and how the process is measured. There are many properties that describe a time series: 1) stationary 2) continuous 3) random 4) periodic. I'll focus on non-random signals for this post, but I would recommend Applied Stochastic Processes, Chaos Modeling, and Probabilistic Properties of Numeration Systems By Vincent Granville, Ph.D. to anyone interested in random processes. Most data scientist working with B2B or B2C time series are primarily working with non-continuous, or discrete, processes. Discrete means that the data are collected at fixed time intervals.

In scientific inference problems, the underlying statistical modeling assumptions have a crucial impact on the end results. There exist, however, only a few automatic means for validating these fundamental modelling assumptions. The contribution in this paper is a general criterion to evaluate the consistency of a set of statistical models with respect to observed data. This is achieved by automatically gauging the models' ability to generate data that is similar to the observed data. Importantly, the criterion follows from the model class itself and is therefore directly applicable to a broad range of inference problems with varying data types. The proposed data consistency criterion is illustrated and evaluated using three synthetic and two real data sets.