Story ending generation aims at generating reasonable endings for a given story context. Most existing studies in this area focus on generating coherent or diversified story endings, while they ignore that different characters may lead to different endings for a given story. In this paper, we propose a Character-oriented Story Ending Generator (CoSEG) to customize an ending for each character in a story. Specifically, we first propose a character modeling module to learn the personalities of characters from their descriptive experiences extracted from the story context. Then, inspired by the ion exchange mechanism in chemical reactions, we design a novel vector breaking/forming module to learn the intrinsic interactions between each character and the corresponding context through an analogical information exchange procedure. Finally, we leverage the attention mechanism to learn effective character-specific interactions and feed each interaction into a decoder to generate character-orient endings. Extensive experimental results and case studies demonstrate that CoSEG achieves significant improvements in the quality of generated endings compared with state-of-the-art methods, and it effectively customizes the endings for different characters.
In malignant primary brain tumors, cancer cells infiltrate into the peritumoral brain structures which results in inevitable recurrence. Quantitative assessment of infiltrative heterogeneity in the peritumoral region, the area where biopsy or resection can be hazardous, is important for clinical decision making. Previous work on characterizing the infiltrative heterogeneity in the peritumoral region used various imaging modalities, but information of extracellular free water movement restriction has been limitedly explored. Here, we derive a unique set of Artificial Intelligence (AI)-based markers capturing the heterogeneity of tumor infiltration, by characterizing free water movement restriction in the peritumoral region using Diffusion Tensor Imaging (DTI)-based free water volume fraction maps. A novel voxel-wise deep learning-based peritumoral microenvironment index (PMI) is first extracted by leveraging the widely different water diffusivity properties of glioblastomas and brain metastases as regions with and without infiltrations in the peritumoral tissue. Descriptive characteristics of locoregional hubs of uniformly high PMI values are extracted as AI-based markers to capture distinct aspects of infiltrative heterogeneity. The proposed markers are applied to two clinical use cases on an independent population of 275 adult-type diffuse gliomas (CNS WHO grade 4), analyzing the duration of survival among Isocitrate-Dehydrogenase 1 (IDH1)-wildtypes and the differences with IDH1-mutants. Our findings provide a panel of markers as surrogates of infiltration that captures unique insight about underlying biology of peritumoral microstructural heterogeneity, establishing them as biomarkers of prognosis pertaining to survival and molecular stratification, with potential applicability in clinical decision making.
The concepts in knowledge graphs (KGs) enable machines to understand natural language, and thus play an indispensable role in many applications. However, existing KGs have the poor coverage of concepts, especially fine-grained concepts. In order to supply existing KGs with more fine-grained and new concepts, we propose a novel concept extraction framework, namely MRC-CE, to extract large-scale multi-granular concepts from the descriptive texts of entities. Specifically, MRC-CE is built with a machine reading comprehension model based on BERT, which can extract more fine-grained concepts with a pointer network. Furthermore, a random forest and rule-based pruning are also adopted to enhance MRC-CE's precision and recall simultaneously. Our experiments evaluated upon multilingual KGs, i.e., English Probase and Chinese CN-DBpedia, justify MRC-CE's superiority over the state-of-the-art extraction models in KG completion. Particularly, after running MRC-CE for each entity in CN-DBpedia, more than 7,053,900 new concepts (instanceOf relations) are supplied into the KG. The code and datasets have been released at https://github.com/fcihraeipnusnacwh/MRC-CE
Social employment, which is mostly carried by firms of different types, determines the prosperity and stability of a country. As time passing, the fluctuations of firm employment can reflect the process of creating or destroying jobs. Therefore, it is instructive to investigate the firm employment (size) dynamics. Drawing on the firm-level panel data extracted from the Chinese Industrial Enterprises Database 1998-2013, this paper proposes a Markov-chain-based descriptive approach to clearly demonstrate the firm size transfer dynamics between different size categories. With this method, any firm size transition path in a short time period can be intuitively demonstrated. Furthermore, by utilizing the properties of Markov transfer matrices, the definition of transition trend and the transition entropy are introduced and estimated. As a result, the tendency of firm size transfer between small, medium and large can be exactly revealed, and the uncertainty of size change can be quantified. Generally from the evidence of this paper, it can be inferred that small and medium manufacturing firms in China have greater job creation potentials compared to large firms over this time period.
Context: The number of TV series offered nowadays is very high. Due to its large amount, many series are canceled due to a lack of originality that generates a low audience. Problem: Having a decision support system that can show why some shows are a huge success or not would facilitate the choices of renewing or starting a show. Solution: We studied the case of the series Arrow broadcasted by CW Network and used descriptive and predictive modeling techniques to predict the IMDb rating. We assumed that the theme of the episode would affect its evaluation by users, so the dataset is composed only by the director of the episode, the number of reviews that episode got, the percentual of each theme extracted by the Latent Dirichlet Allocation (LDA) model of an episode, the number of viewers from Wikipedia and the rating from IMDb. The LDA model is a generative probabilistic model of a collection of documents made up of words. Method: In this prescriptive research, the case study method was used, and its results were analyzed using a quantitative approach. Summary of Results: With the features of each episode, the model that performed the best to predict the rating was Catboost due to a similar mean squared error of the KNN model but a better standard deviation during the test phase. It was possible to predict IMDb ratings with an acceptable root mean squared error of 0.55.
Deep neural networks are becoming increasingly powerful and large and always require more labelled data to be trained. However, since annotating data is time-consuming, it is now necessary to develop systems that show good performance while learning on a limited amount of data. These data must be correctly chosen to obtain models that are still efficient. For this, the systems must be able to determine which data should be annotated to achieve the best results. In this paper, we propose four estimators to estimate the confidence of object detection predictions. The first two are based on Monte Carlo dropout, the third one on descriptive statistics and the last one on the detector posterior probabilities. In the active learning framework, the three first estimators show a significant improvement in performance for the detection of document physical pages and text lines compared to a random selection of images. We also show that the proposed estimator based on descriptive statistics can replace MC dropout, reducing the computational cost without compromising the performances.
Goal-oriented generative script learning aims to generate subsequent steps to reach a particular goal, which is an essential task to assist robots or humans in performing stereotypical activities. An important aspect of this process is the ability to capture historical states visually, which provides detailed information that is not covered by text and will guide subsequent steps. Therefore, we propose a new task, Multimedia Generative Script Learning, to generate subsequent steps by tracking historical states in both text and vision modalities, as well as presenting the first benchmark containing 5,652 tasks and 79,089 multimedia steps. This task is challenging in three aspects: the multimedia challenge of capturing the visual states in images, the induction challenge of performing unseen tasks, and the diversity challenge of covering different information in individual steps. We propose to encode visual state changes through a selective multimedia encoder to address the multimedia challenge, transfer knowledge from previously observed tasks using a retrieval-augmented decoder to overcome the induction challenge, and further present distinct information at each step by optimizing a diversity-oriented contrastive learning objective. We define metrics to evaluate both generation and inductive quality. Experiment results demonstrate that our approach significantly outperforms strong baselines.
As one of the most intuitive interfaces known to humans, natural language has the potential to mediate many tasks that involve human-computer interaction, especially in application-focused fields like Music Information Retrieval. In this work, we explore cross-modal learning in an attempt to bridge audio and language in the music domain. To this end, we propose MusCALL, a framework for Music Contrastive Audio-Language Learning. Our approach consists of a dual-encoder architecture that learns the alignment between pairs of music audio and descriptive sentences, producing multimodal embeddings that can be used for text-to-audio and audio-to-text retrieval out-of-the-box. Thanks to this property, MusCALL can be transferred to virtually any task that can be cast as text-based retrieval. Our experiments show that our method performs significantly better than the baselines at retrieving audio that matches a textual description and, conversely, text that matches an audio query. We also demonstrate that the multimodal alignment capability of our model can be successfully extended to the zero-shot transfer scenario for genre classification and auto-tagging on two public datasets.
Distant viewing approaches have typically used image datasets close to the contemporary image data used to train machine learning models. To work with images from other historical periods requires expert annotated data, and the quality of labels is crucial for the quality of results. Especially when working with cultural heritage collections that contain myriad uncertainties, annotating data, or re-annotating, legacy data is an arduous task. In this paper, we describe working with two pre-annotated sets of medieval manuscript images that exhibit conflicting and overlapping metadata. Since a manual reconciliation of the two legacy ontologies would be very expensive, we aim (1) to create a more uniform set of descriptive labels to serve as a "bridge" in the combined dataset, and (2) to establish a high quality hierarchical classification that can be used as a valuable input for subsequent supervised machine learning. To achieve these goals, we developed visualization and interaction mechanisms, enabling medievalists to combine, regularize and extend the vocabulary used to describe these, and other cognate, image datasets. The visual interfaces provide experts an overview of relationships in the data going beyond the sum total of the metadata. Word and image embeddings as well as co-occurrences of labels across the datasets, enable batch re-annotation of images, recommendation of label candidates and support composing a hierarchical classification of labels.
Phenomenology is the rigorous descriptive study of conscious experience. Recent attempts to formalize Husserlian phenomenology provide us with a mathematical model of perception as a function of prior knowledge and expectation. In this paper, we re-examine elements of Husserlian phenomenology through the lens of active inference. In doing so, we aim to advance the project of computational phenomenology, as recently outlined by proponents of active inference. We propose that key aspects of Husserl's descriptions of consciousness can be mapped onto aspects of the generative models associated with the active inference approach. We first briefly review active inference. We then discuss Husserl's phenomenology, with a focus on time consciousness. Finally, we present our mapping from Husserlian phenomenology to active inference.
We propose the Vision-and-Augmented-Language Transformer (VAuLT). VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs than image captions while having minimal impact on training and inference efficiency. ViLT, importantly, enables efficient training and inference in VL tasks, achieved by encoding images using a linear projection of patches instead of an object detector. However, it is pretrained on captioning datasets, where the language input is simple, literal, and descriptive, therefore lacking linguistic diversity. So, when working with multimedia data in the wild, such as multimodal social media data, there is a notable shift from captioning language data, as well as diversity of tasks. We indeed find evidence that the language capacity of ViLT is lacking. The key insight and novelty of VAuLT is to propagate the output representations of a large language model (LM) like BERT to the language input of ViLT. We show that joint training of the LM and ViLT can yield relative improvements up to 20% over ViLT and achieve state-of-the-art or comparable performance on VL tasks involving richer language inputs and affective constructs, such as for Target-Oriented Sentiment Classification in TWITTER-2015 and TWITTER-2017, and Sentiment Classification in MVSA-Single and MVSA-Multiple. Our code is available at https://github.com/gchochla/VAuLT.
Celebrity Endorsement is one of the most significant strategies in brand communication. Nowadays, more and more companies try to build a vivid characteristic for themselves. Therefore, their brand identity communications should accord with some characteristics as humans and regulations. However, the previous works mostly stop by assumptions, instead of proposing a specific way to perform matching between brands and celebrities. In this paper, we propose a brand celebrity matching model (BCM) based on Natural Language Processing (NLP) techniques. Given a brand and a celebrity, we firstly obtain some descriptive documents of them from the Internet, then summarize these documents, and finally calculate a matching degree between the brand and the celebrity to determine whether they are matched. According to the experimental result, our proposed model outperforms the best baselines with a 0.362 F1 score and 6.3% of accuracy, which indicates the effectiveness and application value of our model in the real-world scene. What's more, to our best knowledge, the proposed BCM model is the first work on using NLP to solve endorsement issues, so it can provide some novel research ideas and methodologies for the following works.
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist of a cascade of graph wavelet filters. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations. The incorporation of our LEGS-module in GNNs enables the learning of longer-range graph relations compared to many popular GNNs, which often rely on encoding graph structure via smoothness or similarity between neighbors. Further, its wavelet priors result in simplified architectures with significantly fewer learned parameters compared to competing GNNs. We demonstrate the predictive performance of LEGS-based networks on graph classification benchmarks, as well as the descriptive quality of their learned features in biochemical graph data exploration tasks. Our results show that LEGS-based networks match or outperforms popular GNNs, as well as the original geometric scattering construction, on many datasets, in particular in biochemical domains, while retaining certain mathematical properties of handcrafted (non-learned) geometric scattering.
This paper discusses a facial expression recognition model and a description generation model to build descriptive sentences for images and facial expressions of people in images. Our study shows that YOLOv5 achieves better results than a traditional CNN for all emotions on the KDEF dataset. In particular, the accuracies of the CNN and YOLOv5 models for emotion recognition are 0.853 and 0.938, respectively. A model for generating descriptions for images based on a merged architecture is proposed using VGG16 with the descriptions encoded over an LSTM model. YOLOv5 is also used to recognize dominant colors of objects in the images and correct the color words in the descriptions generated if it is necessary. If the description contains words referring to a person, we recognize the emotion of the person in the image. Finally, we combine the results of all models to create sentences that describe the visual content and the human emotions in the images. Experimental results on the Flickr8k dataset in Vietnamese achieve BLEU-1, BLEU-2, BLEU-3, BLEU-4 scores of 0.628; 0.425; 0.280; and 0.174, respectively.
Experimental research publications provide figure form resources including graphs, charts, and any type of images to effectively support and convey methods and results. To describe figures, authors add captions, which are often incomplete, and more descriptions reside in body text. This work presents a method to extract figure descriptive text from the body of scientific articles. We adopted ontological semantics to aid concept recognition of figure-related information, which generates human- and machine-readable knowledge representations from sentences. Our results show that conceptual models bring an improvement in figure descriptive sentence classification over word-based approaches.
Advancements in Telemedicine as an approach to healthcare delivery have heralded a new dawn in modern Medicine. Its fast-paced development in our contemporary society is credence to the advances in Artificial Intelligence and Information Technology. This paper carries out a descriptive study to broadly explore AI's implementations in healthcare delivery with a more holistic view of the usability of various Telemedical Innovations in enhancing Virtual Diagnostic Solutions (VDS). This research further explores notable developments in Deep Learning model optimizations for Virtual Diagnostic Solutions. A further research review on the prospects of Virtual Diagnostic Solutions (VDS) and foreseeable challenges was also highlighted. Conclusively, this research gives a general overview of Artificial Intelligence in Telemedicine with a central focus on Deep Learning-based approaches to Virtual Diagnostic Solutions.
Explainable artificial intelligence (XAI) seeks to produce explanations for those machine learning methods which are deemed opaque. However, there is considerable disagreement about what this means and how to achieve it. Authors disagree on what should be explained (topic), to whom something should be explained (stakeholder), how something should be explained (instrument), and why something should be explained (goal). In this paper, I employ insights from means-end epistemology to structure the field. According to means-end epistemology, different means ought to be rationally adopted to achieve different epistemic ends. Applied to XAI, different topics, stakeholders, and goals thus require different instruments. I call this the means-end account of XAI. The means-end account has a descriptive and a normative component: on the one hand, I show how the specific means-end relations give rise to a taxonomy of existing contributions to the field of XAI; on the other hand, I argue that the suitability of XAI methods can be assessed by analyzing whether they are prescribed by a given topic, stakeholder, and goal.
Despite the continuous efforts in improving both the effectiveness and efficiency of code search, two issues remained unsolved. First, programming languages have inherent strong structural linkages, and feature mining of code as text form would omit the structural information contained inside it. Second, there is a potential semantic relationship between code and query, it is challenging to align code and text across sequences so that vectors are spatially consistent during similarity matching. To tackle both issues, in this paper, a code search model named CSSAM (Code Semantics and Structures Attention Matching) is proposed. By introducing semantic and structural matching mechanisms, CSSAM effectively extracts and fuses multidimensional code features. Specifically, the cross and residual layer was developed to facilitate high-latitude spatial alignment of code and query at the token level. By leveraging the residual interaction, a matching module is designed to preserve more code semantics and descriptive features, that enhances the adhesion between the code and its corresponding query text. Besides, to improve the model's comprehension of the code's inherent structure, a code representation structure named CSRG (Code Semantic Representation Graph) is proposed for jointly representing abstract syntax tree nodes and the data flow of the codes. According to the experimental results on two publicly available datasets containing 540k and 330k code segments, CSSAM significantly outperforms the baselines in terms of achieving the highest SR@1/5/10, MRR, and NDCG@50 on both datasets respectively. Moreover, the ablation study is conducted to quantitatively measure the impact of each key component of CSSAM on the efficiency and effectiveness of code search, which offers the insights into the improvement of advanced code search solutions.
This study aims to enable more reliable automated post-disaster building damage classification using artificial intelligence (AI) and multi-view imagery. The current practices and research efforts in adopting AI for post-disaster damage assessment are generally (a) qualitative, lacking refined classification of building damage levels based on standard damage scales, and (b) trained based on aerial or satellite imagery with limited views, which, although indicative, are not completely descriptive of the damage scale. To enable more accurate and reliable automated quantification of damage levels, the present study proposes the use of more comprehensive visual data in the form of multiple ground and aerial views of the buildings. To have such a spatially-aware damage prediction model, a Multi-view Convolution Neural Network (MV-CNN) architecture is used that combines the information from different views of a damaged building. This spatial 3D context damage information will result in more accurate identification of damages and reliable quantification of damage levels. The proposed model is trained and validated on reconnaissance visual dataset containing expert-labeled, geotagged images of the inspected buildings following hurricane Harvey. The developed model demonstrates reasonably good accuracy in predicting the damage levels and can be used to support more informed and reliable AI-assisted disaster management practices.
With the development of generative-based self-supervised learning (SSL) approaches like BeiT and MAE, how to learn good representations by masking random patches of the input image and reconstructing the missing information has grown in concern. However, BeiT and PeCo need a "pre-pretraining" stage to produce discrete codebooks for masked patches representing. MAE does not require a pre-training codebook process, but setting pixels as reconstruction targets may introduce an optimization gap between pre-training and downstream tasks that good reconstruction quality may not always lead to the high descriptive capability for the model. Considering the above issues, in this paper, we propose a simple Self-distillated masked AutoEncoder network, namely SdAE. SdAE consists of a student branch using an encoder-decoder structure to reconstruct the missing information, and a teacher branch producing latent representation of masked tokens. We also analyze how to build good views for the teacher branch to produce latent representation from the perspective of information bottleneck. After that, we propose a multi-fold masking strategy to provide multiple masked views with balanced information for boosting the performance, which can also reduce the computational complexity. Our approach generalizes well: with only 300 epochs pre-training, a vanilla ViT-Base model achieves an 84.1% fine-tuning accuracy on ImageNet-1k classification, 48.6 mIOU on ADE20K segmentation, and 48.9 mAP on COCO detection, which surpasses other methods by a considerable margin. Code is available at https://github.com/AbrahamYabo/SdAE.