In this paper, we describe our shared task submissions for Subtask 2 in CASE-2022, Event Causality Identification with Casual News Corpus. The challenge focused on the automatic detection of all cause-effect-signal spans present in the sentence from news-media. We detect cause-effect-signal spans in a sentence using T5 -- a pre-trained autoregressive language model. We iteratively identify all cause-effect-signal span triplets, always conditioning the prediction of the next triplet on the previously predicted ones. To predict the triplet itself, we consider different causal relationships such as cause$\rightarrow$effect$\rightarrow$signal. Each triplet component is generated via a language model conditioned on the sentence, the previous parts of the current triplet, and previously predicted triplets. Despite training on an extremely small dataset of 160 samples, our approach achieved competitive performance, being placed second in the competition. Furthermore, we show that assuming either cause$\rightarrow$effect or effect$\rightarrow$cause order achieves similar results.

Variational quantum algorithms (VQAs) are among the most promising algorithms in the era of Noisy Intermediate Scale Quantum Devices. Such algorithms are constructed using a parameterization U($\pmb{\theta}$) with a classical optimizer that updates the parameters $\pmb{\theta}$ in order to minimize a cost function $C$. For this task, in general the gradient descent method, or one of its variants, is used. This is a method where the circuit parameters are updated iteratively using the cost function gradient. However, several works in the literature have shown that this method suffers from a phenomenon known as the Barren Plateaus (BP). In this work, we propose a new method to mitigate BPs. In general, the parameters $\pmb{\theta}$ used in the parameterization $U$ are randomly generated. In our method they are obtained from a classical neural network (CNN). We show that this method, besides to being able to mitigate BPs during startup, is also able to mitigate the effect of BPs during the VQA training. In addition, we also show how this method behaves for different CNN architectures.

This work focuses on drones or UAVs (Unmanned Aerial Vehicles) for use in industry in general. These vehicles have a large number of uses and potential in the industry, as a tool for civil engineering, medicine, mining, among others. However, this vehicle is limited for use indoors due to the need for GPS and it does not work indoors. In this way, this work presents a UAV that works without GPS, thus being able to be used in closed spaces for example and have good precision. The work is based on an approach that uses computer vision and GPS.

Demand forecasting applications have immensely benefited from the state-of-the-art Deep Learning methods used for time series forecasting. Traditional uni-modal models are predominantly seasonality driven which attempt to model the demand as a function of historic sales along with information on holidays and promotional events. However, accurate and robust sales forecasting calls for accommodating multiple other factors, such as natural calamities, pandemics, elections, etc., impacting the demand for products and product categories in general. We propose a multi-modal sales forecasting network that combines real-life events from news articles with traditional data such as historical sales and holiday information. Further, we fuse information from general product trends published by Google trends. Empirical results show statistically significant improvements in the SMAPE error metric with an average improvement of 7.37% against the existing state-of-the-art sales forecasting techniques on a real-world supermarket dataset.

We report a closed-loop control system for paramagnetic catalytically self-propelled Janus microrobots. We achieve this control by employing electromagnetic coils that direct the magnetic field in a desired orientation to steer the microrobots. The microrobots move due to the catalytic decomposition of hydrogen peroxide, during which they align themselves to the magnetic torques applied to them. Because the angle between their direction of motion and their magnetic orientation is a priori unknown, an algorithm is used to determine this angular offset and adjust the magnetic field appropriately. The microrobots are located using real-time particle tracking that integrates with a video camera. A target location or desired trajectory can be drawn by the user for the microrobots to follow.

Submodular functions and variants, through their ability to characterize diversity and coverage, have emerged as a key tool for data selection and summarization. Many recent approaches to learn submodular functions suffer from limited expressiveness. In this work, we propose FLEXSUBNET, a family of flexible neural models for both monotone and non-monotone submodular functions. To fit a latent submodular function from (set, value) observations, FLEXSUBNET applies a concave function on modular functions in a recursive manner. We do not draw the concave function from a restricted family, but rather learn from data using a highly expressive neural network that implements a differentiable quadrature procedure. Such an expressive neural model for concave functions may be of independent interest. Next, we extend this setup to provide a novel characterization of monotone \alpha-submodular functions, a recently introduced notion of approximate submodular functions. We then use this characterization to design a novel neural model for such functions. Finally, we consider learning submodular set functions under distant supervision in the form of (perimeter-set, high-value-subset) pairs. This yields a novel subset selection method based on an order-invariant, yet greedy sampler built around the above neural set functions. Our experiments on synthetic and real data show that FLEXSUBNET outperforms several baselines.

The graph retrieval problem is to search in a large corpus of graphs for ones that are most similar to a query graph. A common consideration for scoring similarity is the maximum common subgraph (MCS) between the query and corpus graphs, usually counting the number of common edges (i.e., MCES). In some applications, it is also desirable that the common subgraph be connected, i.e., the maximum common connected subgraph (MCCS). Finding exact MCES and MCCS is intractable, but may be unnecessary if ranking corpus graphs by relevance is the goal. We design fast and trainable neural functions that approximate MCES and MCCS well. Late interaction methods compute dense representations for the query and corpus graph separately, and compare these representations using simple similarity functions at the last stage, leading to highly scalable systems. Early interaction methods combine information from both graphs right from the input stages, are usually considerably more accurate, but slower. We propose both late and early interaction neural MCES and MCCS formulations. They are both based on a continuous relaxation of a node alignment matrix between query and corpus nodes. For MCCS, we propose a novel differentiable network for estimating the size of the largest connected common subgraph. Extensive experiments with seven data sets show that our proposals are superior among late interaction models in terms of both accuracy and speed. Our early interaction models provide accuracy competitive with the state of the art, at substantially greater speeds.

Many real-world problems can be naturally described by mathematical formulas. The task of finding formulas from a set of observed inputs and outputs is called symbolic regression. Recently, neural networks have been applied to symbolic regression, among which the transformer-based ones seem to be the most promising. After training the transformer on a large number of formulas (in the order of days), the actual inference, i.e., finding a formula for new, unseen data, is very fast (in the order of seconds). This is considerably faster than state-of-the-art evolutionary methods. The main drawback of transformers is that they generate formulas without numerical constants, which have to be optimized separately, so yielding suboptimal results. We propose a transformer-based approach called SymFormer, which predicts the formula by outputting the individual symbols and the corresponding constants simultaneously. This leads to better performance in terms of fitting the available data. In addition, the constants provided by SymFormer serve as a good starting point for subsequent tuning via gradient descent to further improve the performance. We show on a set of benchmarks that SymFormer outperforms two state-of-the-art methods while having faster inference.

Recent work on enhancing BERT-based language representation models with knowledge graphs (KGs) and knowledge bases (KBs) has yielded promising results on multiple NLP tasks. State-of-the-art approaches typically integrate the original input sentences with KG triples and feed the combined representation into a BERT model. However, as the sequence length of a BERT model is limited, such a framework supports little knowledge other than the original input sentences and is thus forced to discard some knowledge. This problem is especially severe for downstream tasks for which the input is a long paragraph or even a document, such as QA or reading comprehension tasks. We address this problem with Roof-Transformer, a model with two underlying BERTs and a fusion layer on top. One underlying BERT encodes the knowledge resources and the other one encodes the original input sentences, and the fusion layer integrates the two resultant encodings. Experimental results on a QA task and the GLUE benchmark attest the effectiveness of the proposed model.

Universidad Tecnológica del Uruguay, Rivera, Uruguay 2 ABSTRACT The implementation of robots to enhance some processes has become popular in recent years due to the accelerated way of production in some factories. Within this context was where robotics has emerged, firstly with stationary robots and more recently mobile robots, namely aerial and terrestrial robots. They can be used for delimited processes within a function, mainly the stationary robots, but also for research in wider areas and even competition. This work summarizes the construction of a model of terrestrial mobile robot that makes the use of artificial intelligence for the purpose of research and competitions, all of that with the basic sensing that can be used in industry. (Rovas, 2015).