Commit messages have an important impact in software development, especially when working in large teams. Multiple developers who have a different style of writing may often be involved in the same project. For this reason, it may be difficult to maintain a strict pattern of writing informative commit messages, with the most frequent issue being that these messages are not descriptive enough. In this paper we apply neural machine translation (NMT) techniques to convert code diffs into commit messages and we present an improved sketch-based encoder for this task. We split the approach into three parts. Firstly, we focus on finding a more suitable NMT baseline for this problem. Secondly, we show that the performance of the NMT models can be improved by training on examples containing a specific file type. Lastly, we introduce a novel sketch-based neural model inspired by recent approaches used for code generation and we show that the sketch-based encoder significantly outperforms existing state of the art solutions. The results highlight that this improvement is relevant especially for Java source code files, by examining two different datasets introduced in recent years for this task.
An LBYL (`Look Before You Leap') Network is proposed for end-to-end trainable one-stage visual grounding. The idea behind LBYL-Net is intuitive and straightforward: we follow a language's description to localize the target object based on its relative spatial relation to `Landmarks', which is characterized by some spatial positional words and some descriptive words about the object. The core of our LBYL-Net is a landmark feature convolution module that transmits the visual features with the guidance of linguistic description along with different directions. Consequently, such a module encodes the relative spatial positional relations between the current object and its context. Then we combine the contextual information from the landmark feature convolution module with the target's visual features for grounding. To make this landmark feature convolution light-weight, we introduce a dynamic programming algorithm (termed dynamic max pooling) with low complexity to extract the landmark feature. Thanks to the landmark feature convolution module, we mimic the human behavior of `Look Before You Leap' to design an LBYL-Net, which takes full consideration of contextual information. Extensive experiments show our method's effectiveness in four grounding datasets. Specifically, our LBYL-Net outperforms all state-of-the-art two-stage and one-stage methods on ReferitGame. On RefCOCO and RefCOCO+, Our LBYL-Net also achieves comparable results or even better results than existing one-stage methods.
We present a novel surface convolution operator acting on vector fields that is based on a simple observation: instead of combining neighboring features with respect to a single coordinate parameterization defined at a given point, we have every neighbor describe the position of the point within its own coordinate frame. This formulation combines intrinsic spatial convolution with parallel transport in a scattering operation while placing no constraints on the filters themselves, providing a definition of convolution that commutes with the action of isometries, has increased descriptive potential, and is robust to noise and other nuisance factors. The result is a rich notion of convolution which we call field convolution, well-suited for CNNs on surfaces. Field convolutions are flexible, straight-forward to incorporate into surface learning frameworks, and their highly discriminating nature has cascading effects throughout the learning pipeline. Using simple networks constructed from residual field convolution blocks, we achieve state-of-the-art results on standard benchmarks in fundamental geometry processing tasks, such as shape classification, segmentation, correspondence, and sparse matching.
Over the last decade, the use of Deep Learning in many applications produced results that are comparable to and in some cases surpassing human expert performance. The application domains include diagnosing diseases, finance, agriculture, search engines, robot vision, and many others. In this paper, we are proposing an architecture that utilizes image/video captioning methods and Natural Language Processing systems to generate a title and a concise abstract for a video. Such a system can potentially be utilized in many application domains, including, the cinema industry, video search engines, security surveillance, video databases/warehouses, data centers, and others. The proposed system functions and operates as followed: it reads a video; representative image frames are identified and selected; the image frames are captioned; NLP is applied to all generated captions together with text summarization; and finally, a title and an abstract are generated for the video. All functions are performed automatically. Preliminary results are provided in this paper using publicly available datasets. This paper is not concerned about the efficiency of the system at the execution time. We hope to be able to address execution efficiency issues in our subsequent publications.
3D delineation of anatomical structures is a cardinal goal in medical imaging analysis. Prior to deep learning, statistical shape models that imposed anatomical constraints and produced high quality surfaces were a core technology. Prior to deep learning, statistical shape models that imposed anatomical constraints and produced high quality surfaces were a core technology. Today fully-convolutional networks (FCNs), while dominant, do not offer these capabilities. We present deep implicit statistical shape models (DISSMs), a new approach to delineation that marries the representation power of convolutional neural networks (CNNs) with the robustness of SSMs. DISSMs use a deep implicit surface representation to produce a compact and descriptive shape latent space that permits statistical models of anatomical variance. To reliably fit anatomically plausible shapes to an image, we introduce a novel rigid and non-rigid pose estimation pipeline that is modelled as a Markov decision process(MDP). We outline a training regime that includes inverted episodic training and a deep realization of marginal space learning (MSL). Intra-dataset experiments on the task of pathological liver segmentation demonstrate that DISSMs can perform more robustly than three leading FCN models, including nnU-Net: reducing the mean Hausdorff distance (HD) by 7.7-14.3mm and improving the worst case Dice-Sorensen coefficient (DSC) by 1.2-2.3%. More critically, cross-dataset experiments on a dataset directly reflecting clinical deployment scenarios demonstrate that DISSMs improve the mean DSC and HD by 3.5-5.9% and 12.3-24.5mm, respectively, and the worst-case DSC by 5.4-7.3%. These improvements are over and above any benefits from representing delineations with high-quality surface.
This paper focuses on building of models of stochastic systems with aleatoric uncertainty. The nature of the considered systems is such that the identical inputs can result in different outputs, i.e. the output is a random variable. The suggested in this paper algorithm targets an identification of multi-modal properties of the output distributions, even when they depend on the inputs and vary significantly throughout the dataset. This ability of the suggested method to recognise complex and not only bell-shaped distributions follows from its construction and is backed up by provided experimental results. In general, the suggested method belongs to the category of boosted ensemble learning techniques, where the single deterministic component can be an arbitrarily-chosen regression model. The algorithm does not require any special properties of the chosen regression model, other than having descriptive capabilities with some expected accuracy for the training data type.
Considering processes of a business in a recommender system is highly advantageous. Although most studies in the business process analysis domain are of descriptive and predictive nature, the feasibility of constructing a process-aware recommender system is assessed in a few works. One reason can be the lack of knowledge on process mining potential for recommendation problems. Therefore, this paper aims to identify and analyze the published studies on process-aware recommender system techniques in business process management and process mining domain. A systematic review was conducted on 33 academic articles published between 2008 and 2020 according to several aspects. In this regard, we provide a state-of-the-art review with critical details and researchers with a better perception of which path to pursue in this field. Moreover, based on a knowledge base and holistic perspective, we discuss some research gaps and open challenges in this field.
In this paper, we investigate whether mixing cryptocurrencies to a German investor portfolio improves portfolio diversification. We analyse this research question by applying a (mean variance) portfolio analysis using a toolbox consisting of (i) the comparison of descriptive statistics, (ii) graphical methods and (iii) econometric spanning tests. In contrast to most of the former studies we use a (broad) customized, Equally-Weighted Cryptocurrency Index (EWCI) to capture the average development of a whole ex ante defined cryptocurrency universe and to mitigate possible survivorship biases in the data. According to Glas/Poddig (2018), this bias could have led to misleading results in some already existing studies. We find that cryptocurrencies can improve portfolio diversification in a few of the analyzed windows from our dataset (consisting of weekly observations from 2014-01-01 to 2019-05-31). However, we cannot confirm this pattern as the normal case. By including cryptocurrencies in their portfolios, investors predominantly cannot reach a significantly higher efficient frontier. These results also hold, if the non-normality of cryptocurrency returns is considered. Moreover, we control for changes of the results, if transaction costs/illiquidities on the cryptocurrency market are additionally considered.
This paper presents a detailed analysis of how liquid money market instruments -- sterling bills of exchange -- were produced during the first globalisation. We rely on a unique data set that reports systematic information on all 23,493 bills re-discounted by the Bank of England in the year 1906. Using descriptive statistics and network analysis, we reconstruct the complete network of linkages between agents involved in the origination and distribution of these bills. Our analysis reveals the truly global dimension of the London bill market before the First World War and underscores the crucial role played by London intermediaries (acceptors and discounters) in overcoming information asymmetries between borrowers and lenders on this market. The complex industrial organisation of the London money market ensured that risky private debts could be transformed into extremely liquid and safe monetary instruments traded throughout the global financial system.
A significant number of the non-financial firms listed at Nairobi Securities Exchange (NSE) have been experiencing declining financial performance which deter investors from investing in such firms. The lenders are also not willing to lend to such firms. As such, the firms struggle to raise funds for their operations. Prudent financing decisions can lead to financial growth of the firm. The purpose of this study is to assess the effect of short-term debt on financial growth of non-financial firms listed at Nairobi Securities Exchange for a period of ten years from 2008 to 2017. Financial firms were excluded because of their specific sector characteristics and stringent regulatory framework. The study is guided by Agency Theory and Theory of Growth of the Firm. Explanatory research design was adopted. The target population of the study comprised of 45 non-financial firms listed at the NSE for a period of ten years from 2008 to 2017. The study conducted both descriptive statistics analysis and panel data analysis. The result indicates that, short term debt explains 45.99% and 25.6% of variations in financial growth as measured by growth in earnings per share and growth in market capitalization respectively. Short term debt positively and significantly influences financial growth measured using both growth in earnings per share and growth in market capitalization. The study recommends that, the management of non-financial firms listed at Nairobi Securities Exchange to employ financing means that can improve the earnings per share, market capitalization and enhance the value of the firm for the benefit of its stakeholders.
A century ago physicists and mathematicians worked in tandem and established quantum mechanism. Indeed, algebras, partial differential equations, group theory, and functional analysis underpin the foundation of quantum mechanism. Currently, biology is undergoing a historic transition from qualitative, phenomenological and descriptive to quantitative, analytical and predictive. Mathematics, again, becomes a driving force behind this new transition in biology.
The expectation is an example of a descriptive statistic that is monotone with respect to stochastic dominance, and additive for sums of independent random variables. We provide a complete characterization of such statistics, and explore a number of applications to models of individual and group decision-making. These include a representation of stationary monotone time preferences, extending the work of Fishburn and Rubinstein (1982) to time lotteries. This extension offers a new perspective on risk attitudes toward time, as well as on the aggregation of multiple discount factors. We also offer a novel class of nonexpected utility preferences over gambles which satisfy invariance to background risk as well as betweenness, but are versatile enough to capture mixed risk attitudes.
This paper proposes a simple descriptive model of discrete-time double auction markets for divisible assets. As in the classical models of exchange economies, we consider a finite set of agents described by their initial endowments and preferences. Instead of the classical Walrasian-type market models, however, we assume that all trades take place in a centralized double auction where the agents communicate through sealed limit orders for buying and selling. We find that, under nonstrategic bidding, the double auction clears with zero trades precisely when the agents' current holdings are on the Pareto frontier. More interestingly, the double auctions implement Adam Smith's "invisible hand" in the sense that, when starting from disequilibrium, repeated double auctions lead to a sequence of allocations that converges to individually rational Pareto allocations.
Descriptive code comments are essential for supporting code comprehension and maintenance. We propose the task of automatically generating comments for overriding methods. We formulate a novel framework which accommodates the unique contextual and linguistic reasoning that is required for performing this task. Our approach features: (1) incorporating context from the class hierarchy; (2) conditioning on learned, latent representations of specificity to generate comments that capture the more specialized behavior of the overriding method; and (3) unlikelihood training to discourage predictions which do not conform to invariant characteristics of the comment corresponding to the overridden method. Our experiments show that the proposed approach is able to generate comments for overriding methods of higher quality compared to prevailing comment generation techniques.
This paper introduces the Descriptive Variational Autoencoder (DVAE), an unsupervised and end-to-end trainable neural network for predicting vehicle trajectories that provides partial interpretability. The novel approach is based on the architecture and objective of common variational autoencoders. By introducing expert knowledge within the decoder part of the autoencoder, the encoder learns to extract latent parameters that provide a graspable meaning in human terms. Such an interpretable latent space enables the validation by expert defined rule sets. The evaluation of the DVAE is performed using the publicly available highD dataset for highway traffic scenarios. In comparison to a conventional variational autoencoder with equivalent complexity, the proposed model provides a similar prediction accuracy but with the great advantage of having an interpretable latent space. For crucial decision making and assessing trustworthiness of a prediction this property is highly desirable.
Graph-based semi-supervised learning methods, which deal well with the situation of limited labeled data, have shown dominant performance in practical applications. However, the high dimensionality of hyperspectral images (HSI) makes it hard to construct the pairwise adjacent graph. Besides, the fine spatial features that help improve the discriminability of the model are often overlooked. To handle the problems, this paper proposes a novel spatial-spectral HSI classification method via multiple random anchor graphs ensemble learning (RAGE). Firstly, the local binary pattern is adopted to extract the more descriptive features on each selected band, which preserves local structures and subtle changes of a region. Secondly, the adaptive neighbors assignment is introduced in the construction of anchor graph, to reduce the computational complexity. Finally, an ensemble model is built by utilizing multiple anchor graphs, such that the diversity of HSI is learned. Extensive experiments show that RAGE is competitive against the state-of-the-art approaches.
Controllable Image Captioning (CIC) -- generating image descriptions following designated control signals -- has received unprecedented attention over the last few years. To emulate the human ability in controlling caption generation, current CIC studies focus exclusively on control signals concerning objective properties, such as contents of interest or descriptive patterns. However, we argue that almost all existing objective control signals have overlooked two indispensable characteristics of an ideal control signal: 1) Event-compatible: all visual contents referred to in a single sentence should be compatible with the described activity. 2) Sample-suitable: the control signals should be suitable for a specific image sample. To this end, we propose a new control signal for CIC: Verb-specific Semantic Roles (VSR). VSR consists of a verb and some semantic roles, which represents a targeted activity and the roles of entities involved in this activity. Given a designated VSR, we first train a grounded semantic role labeling (GSRL) model to identify and ground all entities for each role. Then, we propose a semantic structure planner (SSP) to learn human-like descriptive semantic structures. Lastly, we use a role-shift captioning model to generate the captions. Extensive experiments and ablations demonstrate that our framework can achieve better controllability than several strong baselines on two challenging CIC benchmarks. Besides, we can generate multi-level diverse captions easily. The code is available at: https://github.com/mad-red/VSR-guided-CIC.
Continuous Sign Language Recognition (CSLR) refers to the challenging problem of recognizing sign language glosses and their temporal boundaries from weakly annotated video sequences. Previous methods focus mostly on visual feature extraction neglecting text information and failing to effectively model the intra-gloss dependencies. In this work, a cross-modal learning approach that leverages text information to improve vision-based CSLR is proposed. To this end, two powerful encoding networks are initially used to produce video and text embeddings prior to their mapping and alignment into a joint latent representation. The purpose of the proposed cross-modal alignment is the modelling of intra-gloss dependencies and the creation of more descriptive video-based latent representations for CSLR. The proposed method is trained jointly with video and text latent representations. Finally, the aligned video latent representations are classified using a jointly trained decoder. Extensive experiments on three well-known sign language recognition datasets and comparison with state-of-the-art approaches demonstrate the great potential of the proposed approach.
Language model pre-training and derived methods are incredibly impactful in machine learning. However, there remains considerable uncertainty on exactly why pre-training helps improve performance for fine-tuning tasks. This is especially true when attempting to adapt language-model pre-training to domains outside of natural language. Here, we analyze this problem by exploring how existing pre-training methods impose relational structure in their induced per-sample latent spaces -- i.e., what constraints do pre-training methods impose on the distance or geometry between the pre-trained embeddings of two samples $\vec x_i$ and $\vec x_j$. Through a comprehensive review of existing pre-training methods, we find that this question remains open. This is true despite theoretical analyses demonstrating the importance of understanding this form of induced structure. Based on this review, we introduce a descriptive framework for pre-training that allows for a granular, comprehensive understanding of how relational structure can be induced. We present a theoretical analysis of this framework from first principles and establish a connection between the relational inductive bias of pre-training and fine-tuning performance. We also show how to use the framework to define new pre-training methods. We build upon these findings with empirical studies on benchmarks spanning 3 data modalities and ten fine-tuning tasks. These experiments validate our theoretical analyses, inform the design of novel pre-training methods, and establish consistent improvements over a compelling suite of baseline methods.
Image captioning is a widely known problem in the area of AI. Caption generation from floor plan images has applications in indoor path planning, real estate, and providing architectural solutions. Several methods have been explored in literature for generating captions or semi-structured descriptions from floor plan images. Since only the caption is insufficient to capture fine-grained details, researchers also proposed descriptive paragraphs from images. However, these descriptions have a rigid structure and lack flexibility, making it difficult to use them in real-time scenarios. This paper offers two models, Description Synthesis from Image Cue (DSIC) and Transformer Based Description Generation (TBDG), for the floor plan image to text generation to fill the gaps in existing methods. These two models take advantage of modern deep neural networks for visual feature extraction and text generation. The difference between both models is in the way they take input from the floor plan image. The DSIC model takes only visual features automatically extracted by a deep neural network, while the TBDG model learns textual captions extracted from input floor plan images with paragraphs. The specific keywords generated in TBDG and understanding them with paragraphs make it more robust in a general floor plan image. Experiments were carried out on a large-scale publicly available dataset and compared with state-of-the-art techniques to show the proposed model's superiority.