Block-based environments are visual programming environments, which are becoming more and more popular because of their ease of use. The ease of use comes thanks to their intuitive graphical representation and structural metaphors (jigsaw-like puzzles) to display valid combinations of language constructs to the users. Part of the current popularity of block-based environments is thanks to Scratch. As a result they are often associated with tools for children or young learners. However, it is unclear how these types of programming environments are developed and used in general. So we conducted a systematic literature review on block-based environments by studying 152 papers published between 2014 and 2020, and a non-systematic tool review of 32 block-based environments. In particular, we provide a helpful inventory of block-based editors for end-users on different topics and domains. Likewise, we focused on identifying the main components of block-based environments, how they are engineered, and how they are used. This survey should be equally helpful for language engineering researchers and language engineers alike.
This work addresses one-shot set and graph generation, and, more specifically, the parametrization of probabilistic decoders that map a vector-shaped prior to a distribution over sets or graphs. Sets and graphs are most commonly generated by first sampling points i.i.d. from a normal distribution, and then processing these points along with the prior vector using Transformer layers or Graph Neural Networks. This architecture is designed to generate exchangeable distributions, i.e., all permutations of the generated outputs are equally likely. We however show that it only optimizes a proxy to the evidence lower bound, which makes it hard to train. We then study equivariance in generative settings and show that non-exchangeable methods can still achieve permutation equivariance. Using this result, we introduce Top-n creation, a differentiable generation mechanism that uses the latent vector to select the most relevant points from a trainable reference set. Top-n can replace i.i.d. generation in any Variational Autoencoder or Generative Adversarial Network. Experimentally, our method outperforms i.i.d. generation by 15% at SetMNIST reconstruction, by 33% at object detection on CLEVR, generates sets that are 74% closer to the true distribution on a synthetic molecule-like dataset, and generates more valid molecules on QM9.
We present a means of formulating and solving graph coloring problems with probabilistic graphical models. In contrast to the prevalent literature that uses factor graphs for this purpose, we instead approach it from a cluster graph perspective. Since there seems to be a lack of algorithms to automatically construct valid cluster graphs, we provide such an algorithm (termed LTRIP). Our experiments indicate a significant advantage for preferring cluster graphs over factor graphs, both in terms of accuracy as well as computational efficiency.
In percutaneous intervention for treatment of coronary plaques, guidewire navigation is a primary procedure for stent delivery. Steering a flexible guidewire within coronary arteries requires considerable training, and the non-linearity between the control operation and the movement of the guidewire makes precise manipulation difficult. Here, we introduce a deep reinforcement learning(RL) framework for autonomous guidewire navigation in a robot-assisted coronary intervention. Using Rainbow, a segment-wise learning approach is applied to determine how best to accelerate training using human demonstrations with deep Q-learning from demonstrations (DQfD), transfer learning, and weight initialization. `State' for RL is customized as a focus window near the guidewire tip, and subgoals are placed to mitigate a sparse reward problem. The RL agent improves performance, eventually enabling the guidewire to reach all valid targets in `stable' phase. Our framework opens anew direction in the automation of robot-assisted intervention, providing guidance on RL in physical spaces involving mechanical fatigue.
In this paper, we explore the task of automatically generating natural language descriptions of salient patterns in a time series, such as stock prices of a company over a week. A model for this task should be able to extract high-level patterns such as presence of a peak or a dip. While typical contemporary neural models with attention mechanisms can generate fluent output descriptions for this task, they often generate factually incorrect descriptions. We propose a computational model with a truth-conditional architecture which first runs small learned programs on the input time series, then identifies the programs/patterns which hold true for the given input, and finally conditions on only the chosen valid program (rather than the input time series) to generate the output text description. A program in our model is constructed from modules, which are small neural networks that are designed to capture numerical patterns and temporal information. The modules are shared across multiple programs, enabling compositionality as well as efficient learning of module parameters. The modules, as well as the composition of the modules, are unobserved in data, and we learn them in an end-to-end fashion with the only training signal coming from the accompanying natural language text descriptions. We find that the proposed model is able to generate high-precision captions even though we consider a small and simple space of module types.
In a conversational question answering scenario, a questioner seeks to extract information about a topic through a series of interdependent questions and answers. As the conversation progresses, they may switch to related topics, a phenomenon commonly observed in information-seeking search sessions. However, current datasets for conversational question answering are limiting in two ways: 1) they do not contain topic switches; and 2) they assume the reference text for the conversation is given, i.e., the setting is not open-domain. We introduce TopiOCQA (pronounced Tapioca), an open-domain conversational dataset with topic switches on Wikipedia. TopiOCQA contains 3,920 conversations with information-seeking questions and free-form answers. On average, a conversation in our dataset spans 13 question-answer turns and involves four topics (documents). TopiOCQA poses a challenging test-bed for models, where efficient retrieval is required on multiple turns of the same conversation, in conjunction with constructing valid responses using conversational history. We evaluate several baselines, by combining state-of-the-art document retrieval methods with neural reader models. Our best model achieves F1 of 55.8, falling short of human performance by 14.2 points, indicating the difficulty of our dataset. Our dataset and code is available at https://mcgill-nlp.github.io/topiocqa
Domain generalization (DG) aims to learn from multiple source domains a model that can generalize well on unseen target domains. Existing DG methods mainly learn the representations with invariant marginal distribution of the input features, however, the invariance of the conditional distribution of the labels given the input features is more essential for unknown domain prediction. Meanwhile, the existing of unobserved confounders which affect the input features and labels simultaneously cause spurious correlation and hinder the learning of the invariant relationship contained in the conditional distribution. Interestingly, with a causal view on the data generating process, we find that the input features of one domain are valid instrumental variables for other domains. Inspired by this finding, we propose an instrumental variable-driven DG method (IV-DG) by removing the bias of the unobserved confounders with two-stage learning. In the first stage, it learns the conditional distribution of the input features of one domain given input features of another domain. In the second stage, it estimates the relationship by predicting labels with the learned conditional distribution. Theoretical analyses and simulation experiments show that it accurately captures the invariant relationship. Extensive experiments on real-world datasets demonstrate that IV-DG method yields state-of-the-art results.
This PhD thesis contains several contributions to the field of statistical causal modeling. Statistical causal models are statistical models embedded with causal assumptions that allow for the inference and reasoning about the behavior of stochastic systems affected by external manipulation (interventions). This thesis contributes to the research areas concerning the estimation of causal effects, causal structure learning, and distributionally robust (out-of-distribution generalizing) prediction methods. We present novel and consistent linear and non-linear causal effects estimators in instrumental variable settings that employ data-dependent mean squared prediction error regularization. Our proposed estimators show, in certain settings, mean squared error improvements compared to both canonical and state-of-the-art estimators. We show that recent research on distributionally robust prediction methods has connections to well-studied estimators from econometrics. This connection leads us to prove that general K-class estimators possess distributional robustness properties. We, furthermore, propose a general framework for distributional robustness with respect to intervention-induced distributions. In this framework, we derive sufficient conditions for the identifiability of distributionally robust prediction methods and present impossibility results that show the necessity of several of these conditions. We present a new structure learning method applicable in additive noise models with directed trees as causal graphs. We prove consistency in a vanishing identifiability setup and provide a method for testing substructure hypotheses with asymptotic family-wise error control that remains valid post-selection. Finally, we present heuristic ideas for learning summary graphs of nonlinear time-series models.
Although fully autonomous mapping methods are becoming more and more common and reliable, still the human operator is regularly employed in many 3D surveying missions. In a number of underwater applications, divers or pilots of remotely operated vehicles (ROVs) are still considered irreplaceable, and tools for real-time visualization of the mapped scene are essential to support and maximize the navigation and surveying efforts. For underwater exploration, image mosaicing has proved to be a valid and effective approach to visualize large mapped areas, often employed in conjunction with autonomous underwater vehicles (AUVs) and ROVs. In this work, we propose the use of a modified image mosaicing algorithm that coupled with image-based real-time navigation and mapping algorithms provides two visual navigation aids. The first is a classic image mosaic, where the recorded and processed images are incrementally added, named 2D sequential image mosaicing (2DSIM). The second one geometrically transform the images so that they are projected as planar point clouds in the 3D space providing an incremental point cloud mosaicing, named 3D sequential image plane projection (3DSIP). In the paper, the implemented procedure is detailed, and experiments in different underwater scenarios presented and discussed. Technical considerations about computational efforts, frame rate capabilities and scalability to different and more compact architectures (i.e. embedded systems) is also provided.
This work addresses the problem of Question Answering (QA) on handwritten document collections. Unlike typical QA and Visual Question Answering (VQA) formulations where the answer is a short text, we aim to locate a document snippet where the answer lies. The proposed approach works without recognizing the text in the documents. We argue that the recognition-free approach is suitable for handwritten documents and historical collections where robust text recognition is often difficult. At the same time, for human users, document image snippets containing answers act as a valid alternative to textual answers. The proposed approach uses an off-the-shelf deep embedding network which can project both textual words and word images into a common sub-space. This embedding bridges the textual and visual domains and helps us retrieve document snippets that potentially answer a question. We evaluate results of the proposed approach on two new datasets: (i) HW-SQuAD: a synthetic, handwritten document image counterpart of SQuAD1.0 dataset and (ii) BenthamQA: a smaller set of QA pairs defined on documents from the popular Bentham manuscripts collection. We also present a thorough analysis of the proposed recognition-free approach compared to a recognition-based approach which uses text recognized from the images using an OCR. Datasets presented in this work are available to download at docvqa.org
In this paper, we present and implement a multi-dimensional, modular framework for performing deep argument analysis (DeepA2) using current pre-trained language models (PTLMs). ArgumentAnalyst -- a T5 model (Raffel et al. 2020) set up and trained within DeepA2 -- reconstructs argumentative texts, which advance an informal argumentation, as valid arguments: It inserts, e.g., missing premises and conclusions, formalizes inferences, and coherently links the logical reconstruction to the source text. We create a synthetic corpus for deep argument analysis, and evaluate ArgumentAnalyst on this new dataset as well as on existing data, specifically EntailmentBank (Dalvi et al. 2021). Our empirical findings vindicate the overall framework and highlight the advantages of a modular design, in particular its ability to emulate established heuristics (such as hermeneutic cycles), to explore the model's uncertainty, to cope with the plurality of correct solutions (underdetermination), and to exploit higher-order evidence.
Consider two forecasters, each making a single prediction for a sequence of events over time. We ask a relatively basic question: how might we compare these forecasters, either online or post-hoc, while avoiding unverifiable assumptions on how the forecasts and outcomes were generated? In this paper, we present a rigorous answer to this question by designing novel sequential inference procedures for estimating the time-varying difference in forecast scores. To do this, we employ confidence sequences (CS), which are sequences of confidence intervals that can be continuously monitored and are valid at arbitrary data-dependent stopping times ("anytime-valid"). The widths of our CSs are adaptive to the underlying variance of the score differences. Underlying their construction is a game-theoretic statistical framework, in which we further identify e-processes and p-processes for sequentially testing a weak null hypothesis -- whether one forecaster outperforms another on average (rather than always). Our methods do not make distributional assumptions on the forecasts or outcomes; our main theorems apply to any bounded scores, and we later provide alternative methods for unbounded scores. We empirically validate our approaches by comparing real-world baseball and weather forecasters.
Persian Poetry has consistently expressed its philosophy, wisdom, speech, and rationale on the basis of its couplets, making it an enigmatic language on its own to both native and non-native speakers. Nevertheless, the notice able gap between Persian prose and poem has left the two pieces of literature medium-less. Having curated a parallel corpus of prose and their equivalent poems, we introduce a novel Neural Machine Translation (NMT) approach to translate prose to ancient Persian poetry using transformer-based Language Models in an extremely low-resource setting. More specifically, we trained a Transformer model from scratch to obtain initial translations and pretrained different variations of BERT to obtain final translations. To address the challenge of using masked language modelling under poeticness criteria, we heuristically joined the two models and generated valid poems in terms of automatic and human assessments. Final results demonstrate the eligibility and creativity of our novel heuristically aided approach among Literature professionals and non-professionals in generating novel Persian poems.
Knowledge-intensive NLP tasks can benefit from linking natural language text with facts from a Knowledge Graph (KG). Although facts themselves are language-agnostic, the fact labels (i.e., language-specific representation of the fact) in the KG are often present only in a few languages. This makes it challenging to link KG facts to sentences in languages other than the limited set of languages. To address this problem, we introduce the task of Multilingual Fact Linking (MFL) where the goal is to link fact expressed in a sentence to corresponding fact in the KG, even when the fact label in the KG is not available in the language of the sentence. To facilitate research in this area, we present a new evaluation dataset, IndicLink. This dataset contains 11,293 linked WikiData facts and 6,429 sentences spanning English and six Indian languages. We propose a Retrieval+Generation model, ReFCoG, that can scale to millions of KG facts by combining Dual Encoder based retrieval with a Seq2Seq based generation model which is constrained to output only valid KG facts. ReFCoG outperforms standard Retrieval+Re-ranking models by 10.7 pts in Precision@1. In spite of this gain, the model achieves an overall score of 52.1, showing ample scope for improvement in the task.ReFCoG code and IndicLink data are available at https://github.com/SaiKeshav/mfl
In this paper, we study statistical inference for the Wasserstein distance, which has attracted much attention and has been applied to various machine learning tasks. Several studies have been proposed in the literature, but almost all of them are based on asymptotic approximation and do not have finite-sample validity. In this study, we propose an exact (non-asymptotic) inference method for the Wasserstein distance inspired by the concept of conditional Selective Inference (SI). To our knowledge, this is the first method that can provide a valid confidence interval (CI) for the Wasserstein distance with finite-sample coverage guarantee, which can be applied not only to one-dimensional problems but also to multi-dimensional problems. We evaluate the performance of the proposed method on both synthetic and real-world datasets.
This paper introduces the equiwide clustering problem, where valid partitions must satisfy intra-cluster dissimilarity constraints. Unlike most existing clustering algorithms, equiwide clustering relies neither on density nor on a predefined number of expected classes, but on a dissimilarity threshold. Its main goal is to ensure an upper bound on the error induced by ultimately replacing any object with its cluster representative. Under this constraint, we then primarily focus on minimizing the number of clusters, along with potential sub-objectives. We argue that equiwide clustering is a sound clustering problem, and discuss its relationship with other optimization problems, existing and novel implementations as well as approximation strategies. We review and evaluate suitable clustering algorithms to identify trade-offs between the various practical solutions for this clustering problem.
Digital learning platforms enable students to learn on a flexible and individual schedule as well as providing instant feedback mechanisms. The field of STEM education requires students to solve numerous training exercises to grasp underlying concepts. It is apparent that there are restrictions in current online education in terms of exercise diversity and individuality. Many exercises show little variance in structure and content, hindering the adoption of abstraction capabilities by students. This thesis proposes an approach to generate diverse, context rich word problems. In addition to requiring the generated language to be grammatically correct, the nature of word problems implies additional constraints on the validity of contents. The proposed approach is proven to be effective in generating valid word problems for mathematical statistics. The experimental results present a tradeoff between generation time and exercise validity. The system can easily be parametrized to handle this tradeoff according to the requirements of specific use cases.
Remaining useful life (RUL) refers to the expected remaining lifespan of a component or system. Accurate RUL prediction is critical for prognostic and health management and for maintenance planning. In this work, we address three prevalent challenges in data-driven RUL prediction, namely the handling of high dimensional input features, the robustness to noise in sensor data and prognostic datasets, and the capturing of the time-dependency between system degradation and RUL prediction. We devise a highly accurate RUL prediction model with uncertainty quantification, which integrates and leverages the advantages of deep learning and nonstationary Gaussian process regression (DL-NSGPR). We examine and benchmark our model against other advanced data-driven RUL prediction models using the turbofan engine dataset from the NASA prognostic repository. Our computational experiments show that the DL-NSGPR predictions are highly accurate with root mean square error 1.7 to 6.2 times smaller than those of competing RUL models. Furthermore, the results demonstrate that RUL uncertainty bounds with the proposed DL-NSGPR are both valid and significantly tighter than other stochastic RUL prediction models. We unpack and discuss the reasons for this excellent performance of the DL-NSGPR.
Rotating machinery is essential to modern life, from power generation to transportation and a host of other industrial applications. Since such equipment generally operates under challenging working conditions, which can lead to untimely failures, accurate remaining useful life (RUL) prediction is essential for maintenance planning and to prevent catastrophic failures. In this work, we address current challenges in data-driven RUL prediction for rotating machinery. The challenges revolve around the accuracy and uncertainty quantification of the prediction, and the non-stationarity of the system degradation and RUL estimation given sensor data. We devise a novel architecture and RUL prediction model with uncertainty quantification, termed VisPro, which integrates time-frequency analysis, deep learning image recognition, and nonstationary Gaussian process regression. We analyze and benchmark the results obtained with our model against those of other advanced data-driven RUL prediction models for rotating machinery using the PHM12 bearing vibration dataset. The computational experiments show that (1) the VisPro predictions are highly accurate and provide significant improvements over existing prediction models (three times more accurate than the second-best model), and (2) the RUL uncertainty bounds are valid and informative. We identify and discuss the architectural and modeling choices made that explain this excellent predictive performance of VisPro.
This research is aimed to propose an artificial intelligence algorithm comprising an ontology-based design, text mining, and natural language processing for automatically generating gap-fill multiple choice questions (MCQs). The simulation of this research demonstrated an application of the algorithm in generating gap-fill MCQs about software testing. The simulation results revealed that by using 103 online documents as inputs, the algorithm could automatically produce more than 16 thousand valid gap-fill MCQs covering a variety of topics in the software testing domain. Finally, in the discussion section of this paper we suggest how the proposed algorithm should be applied to produce gap-fill MCQs being collected in a question pool used by a knowledge expert system.