PyTorchKR Papers

최신 논문

총 1,314편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2201.03546공식 코드 · Papers with Code

Language-driven Semantic Segmentation

We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "building") together with a transformer-based image encoder that computes dense per-pixel embeddings of the input image. The image encoder is trained with a contrastive objective to align pixel embeddings to the text embedding of the corresponding semantic class. The text embeddings provide a flexible label representation in which semantically similar labels map to similar regions in the embedding space (e.g., "cat" and "furry"). This allows LSeg to generalize to previously unseen categories at test time, without retraining or even requiring a single additional training sample. We demonstrate that our approach achieves highly competitive zero-shot performance compared to existing zero- and few-shot semantic segmentation methods, and even matches the accuracy of traditional segmentation algorithms when a fixed label set is provided. Code and demo are available at https://github.com/isl-org/lang-seg.

arXiv:2201.03215

Handwriting recognition and automatic scoring for descriptive answers in Japanese language tests

This paper presents an experiment of automatically scoring handwritten descriptive answers in the trial tests for the new Japanese university entrance examination, which were made for about 120,000 examinees in 2017 and 2018. There are about 400,000 answers with more than 20 million characters. Although all answers have been scored by human examiners, handwritten characters are not labeled. We present our attempt to adapt deep neural network-based handwriting recognizers trained on a labeled handwriting dataset into this unlabeled answer set. Our proposed method combines different training strategies, ensembles multiple recognizers, and uses a language model built from a large general corpus to avoid overfitting into specific data. In our experiment, the proposed method records character accuracy of over 97% using about 2,000 verified labeled answers that account for less than 0.5% of the dataset. Then, the recognized answers are fed into a pre-trained automatic scoring system based on the BERT model without correcting misrecognized characters and providing rubric annotations. The automatic scoring system achieves from 0.84 to 0.98 of Quadratic Weighted Kappa (QWK). As QWK is over 0.8, it represents an acceptable similarity of scoring between the automatic scoring system and the human examiners. These results are promising for further research on end-to-end automatic scoring of descriptive answers.

arXiv:2112.11565

Double Standards: The Implications of Near Certainty Drone Strikes in Pakistan

In 2013, U.S. President Barack Obama announced a policy to minimize civilian casualties following drone strikes in undeclared theaters of war. The policy calibrated Obamas approval of strikes against the near certainty of no civilian casualties. Scholars do not empirically study the merits of Obamas policy. Rather, they rely on descriptive trends for civilian casualties in Pakistan to justify competing claims for the policys impact. We provide a novel estimate for the impact of Obamas policy for civilian casualties in Pakistan following U.S. drone strikes. We employ a regression discontinuity design to estimate the effect of Obamas policy for civilian casualties, strike precision, and adverted civilian casualties. We find a discontinuity in civilian casualties approximately two years before Obamas policy announcement, corroborating our primary research including interviews with senior officials responsible for implementing the near certainty standard. After confirming the sharp cutoff, we estimate the policy resulted in a reduction of 12 civilian deaths per month or 2 casualties per strike. The policy also enhanced the precision of U.S. drone strikes to the point that they only killed the intended targets. Finally, we use a Monte Carlo simulation to estimate that the policy adverted 320 civilian casualties. We then conduct a Value of Statistical Life calculation to show that the adverted civilian casualties represent a gain of 80 to 260 million U.S. dollars. In addition to conditioning social and political outcomes, then, the near certainty standard also imposed economic implications that are much less studied.

arXiv:2201.00237공식 코드 · Papers with Code

Understanding Public Opinion on Using Hydroxychloroquine for COVID-19 Treatment via Social Media

Hydroxychloroquine (HCQ) is used to prevent or treat malaria caused by mosquito bites. Recently, the drug has been suggested to treat COVID-19, but that has not been supported by scientific evidence. The information regarding the drug efficacy has flooded social networks, posting potential threats to the community by perverting their perceptions of the drug efficacy. This paper studies the reactions of social network users on the recommendation of using HCQ for COVID-19 treatment by analyzing the reaction patterns and sentiment of the tweets. We collected 164,016 tweets from February to December 2020 and used a text mining approach to identify social reaction patterns and opinion change over time. Our descriptive analysis identified an irregularity of the users' reaction patterns associated tightly with the social and news feeds on the development of HCQ and COVID-19 treatment. The study linked the tweets and Google search frequencies to reveal the viewpoints of local communities on the use of HCQ for COVID-19 treatment across different states. Further, our tweet sentiment analysis reveals that public opinion changed significantly over time regarding the recommendation of using HCQ for COVID-19 treatment. The data showed that high support in the early dates but it significantly declined in October. Finally, using the manual classification of 4,850 tweets by humans as our benchmark, our sentiment analysis showed that the Google Cloud Natural Language algorithm outperformed the Valence Aware Dictionary and sEntiment Reasoner in classifying tweets, especially in the sarcastic tweet group.

arXiv:2201.00578공식 코드 · Papers with Code

'Moving On' -- Investigating Inventors' Ethnic Origins Using Supervised Learning

Patent data provides rich information about technical inventions, but does not disclose the ethnic origin of inventors. In this paper, I use supervised learning techniques to infer this information. To do so, I construct a dataset of 95'202 labeled names and train an artificial recurrent neural network with long-short-term memory (LSTM) to predict ethnic origins based on names. The trained network achieves an overall performance of 91% across 17 ethnic origins. I use this model to classify and investigate the ethnic origins of 2.68 million inventors and provide novel descriptive evidence regarding their ethnic origin composition over time and across countries and technological fields. The global ethnic origin composition has become more diverse over the last decades, which was mostly due to a relative increase of Asian origin inventors. Furthermore, the prevalence of foreign-origin inventors is especially high in the USA, but has also increased in other high-income economies. This increase was mainly driven by an inflow of non-western inventors into emerging high-technology fields for the USA, but not for other high-income countries.

arXiv:2112.09762공식 코드 · Papers with Code

Reproducible and Portable Big Data Analytics in the Cloud

Cloud computing has become a major approach to help reproduce computational experiments. Yet there are still two main difficulties in reproducing batch based big data analytics (including descriptive and predictive analytics) in the cloud. The first is how to automate end-to-end scalable execution of analytics including distributed environment provisioning, analytics pipeline description, parallel execution, and resource termination. The second is that an application developed for one cloud is difficult to be reproduced in another cloud, a.k.a. vendor lock-in problem. To tackle these problems, we leverage serverless computing and containerization techniques for automated scalable execution and reproducibility, and utilize the adapter design pattern to enable application portability and reproducibility across different clouds. We propose and develop an open-source toolkit that supports 1) fully automated end-to-end execution and reproduction via a single command, 2) automated data and configuration storage for each execution, 3) flexible client modes based on user preferences, 4) execution history query, and 5) simple reproduction of existing executions in the same environment or a different environment. We did extensive experiments on both AWS and Azure using four big data analytics applications that run on virtual CPU/GPU clusters. The experiments show our toolkit can achieve good execution performance, scalability, and efficient reproducibility for cloud-based big data analytics.

arXiv:2112.09976공식 코드 · Papers with Code

Tell me what you see: A zero-shot action recognition method based on natural language descriptions

This paper presents a novel approach to Zero-Shot Action Recognition. Recent works have explored the detection and classification of objects to obtain semantic information from videos with remarkable performance. Inspired by them, we propose using video captioning methods to extract semantic information about objects, scenes, humans, and their relationships. To the best of our knowledge, this is the first work to represent both videos and labels with descriptive sentences. More specifically, we represent videos using sentences generated via video captioning methods and classes using sentences extracted from documents acquired through search engines on the Internet. Using these representations, we build a shared semantic space employing BERT-based embedders pre-trained in the paraphrasing task on multiple text datasets. The projection of both visual and semantic information onto this space is straightforward, as they are sentences, enabling classification using the nearest neighbor rule. We demonstrate that representing videos and labels with sentences alleviates the domain adaptation problem. Additionally, we show that word vectors are unsuitable for building the semantic embedding space of our descriptions. Our method outperforms the state-of-the-art performance on the UCF101 dataset by 3.3 p.p. in accuracy under the TruZe protocol and achieves competitive results on both the UCF101 and HMDB51 datasets under the conventional protocol (0/50\% - training/testing split). Our code is available at https://github.com/valterlej/zsarcap.

arXiv:2112.07475공식 코드 · Papers with Code

Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks

Labelled data is the foundation of most natural language processing tasks. However, labelling data is difficult and there often are diverse valid beliefs about what the correct data labels should be. So far, dataset creators have acknowledged annotator subjectivity, but rarely actively managed it in the annotation process. This has led to partly-subjective datasets that fail to serve a clear downstream use. To address this issue, we propose two contrasting paradigms for data annotation. The descriptive paradigm encourages annotator subjectivity, whereas the prescriptive paradigm discourages it. Descriptive annotation allows for the surveying and modelling of different beliefs, whereas prescriptive annotation enables the training of models that consistently apply one belief. We discuss benefits and challenges in implementing both paradigms, and argue that dataset creators should explicitly aim for one or the other to facilitate the intended use of their dataset. Lastly, we conduct an annotation experiment using hate speech data that illustrates the contrast between the two paradigms.

arXiv:2112.06979

The Brain Tumor Sequence Registration (BraTS-Reg) Challenge: Establishing Correspondence Between Pre-Operative and Follow-up MRI Scans of Diffuse Glioma Patients

Registration of longitudinal brain MRI scans containing pathologies is challenging due to dramatic changes in tissue appearance. Although there has been progress in developing general-purpose medical image registration techniques, they have not yet attained the requisite precision and reliability for this task, highlighting its inherent complexity. Here we describe the Brain Tumor Sequence Registration (BraTS-Reg) challenge, as the first public benchmark environment for deformable registration algorithms focusing on estimating correspondences between pre-operative and follow-up scans of the same patient diagnosed with a diffuse brain glioma. The BraTS-Reg data comprise de-identified multi-institutional multi-parametric MRI (mpMRI) scans, curated for size and resolution according to a canonical anatomical template, and divided into training, validation, and testing sets. Clinical experts annotated ground truth (GT) landmark points of anatomical locations distinct across the temporal domain. Quantitative evaluation and ranking were based on the Median Euclidean Error (MEE), Robustness, and the determinant of the Jacobian of the displacement field. The top-ranked methodologies yielded similar performance across all evaluation metrics and shared several methodological commonalities, including pre-alignment, deep neural networks, inverse consistency analysis, and test-time instance optimization per-case basis as a post-processing step. The top-ranked method attained the MEE at or below that of the inter-rater variability for approximately 60% of the evaluated landmarks, underscoring the scope for further accuracy and robustness improvements, especially relative to human experts. The aim of BraTS-Reg is to continue to serve as an active resource for research, with the data and online evaluation tools accessible at https://bratsreg.github.io/.

arXiv:2112.06724공식 코드 · Papers with Code

ANEA: Automated (Named) Entity Annotation for German Domain-Specific Texts

Named entity recognition (NER) is an important task that aims to resolve universal categories of named entities, e.g., persons, locations, organizations, and times. Despite its common and viable use in many use cases, NER is barely applicable in domains where general categories are suboptimal, such as engineering or medicine. To facilitate NER of domain-specific types, we propose ANEA, an automated (named) entity annotator to assist human annotators in creating domain-specific NER corpora for German text collections when given a set of domain-specific texts. In our evaluation, we find that ANEA automatically identifies terms that best represent the texts' content, identifies groups of coherent terms, and extracts and assigns descriptive labels to these groups, i.e., annotates text datasets into the domain (named) entities.

arXiv:2112.06318공식 코드 · Papers with Code

Contextualized Scene Imagination for Generative Commonsense Reasoning

Humans use natural language to compose common concepts from their environment into plausible, day-to-day scene descriptions. However, such generative commonsense reasoning (GCSR) skills are lacking in state-of-the-art text generation methods. Descriptive sentences about arbitrary concepts generated by neural text generation models (e.g., pre-trained text-to-text Transformers) are often grammatically fluent but may not correspond to human common sense, largely due to their lack of mechanisms to capture concept relations, to identify implicit concepts, and to perform generalizable reasoning about unseen concept compositions. In this paper, we propose an Imagine-and-Verbalize (I&V) method, which learns to imagine a relational scene knowledge graph (SKG) with relations between the input concepts, and leverage the SKG as a constraint when generating a plausible scene description. We collect and harmonize a set of knowledge resources from different domains and modalities, providing a rich auxiliary supervision signal for I&V. The experiments demonstrate the effectiveness of I&V in improving language models on both concept-to-sentence and concept-to-story generation tasks, while enabling the model to learn well from fewer task examples and generate SKGs that make common sense to human annotators.

arXiv:2112.06558

MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning

Text-based image captioning (TextCap) requires simultaneous comprehension of visual content and reading the text of images to generate a natural language description. Although a task can teach machines to understand the complex human environment further given that text is omnipresent in our daily surroundings, it poses additional challenges in normal captioning. A text-based image intuitively contains abundant and complex multimodal relational content, that is, image details can be described diversely from multiview rather than a single caption. Certainly, we can introduce additional paired training data to show the diversity of images' descriptions, this process is labor-intensive and time-consuming for TextCap pair annotations with extra texts. Based on the insight mentioned above, we investigate how to generate diverse captions that focus on different image parts using an unpaired training paradigm. We propose the Multimodal relAtional Graph adversarIal inferenCe (MAGIC) framework for diverse and unpaired TextCap. This framework can adaptively construct multiple multimodal relational graphs of images and model complex relationships among graphs to represent descriptive diversity. Moreover, a cascaded generative adversarial network is developed from modeled graphs to infer the unpaired caption generation in image-sentence feature alignment and linguistic coherence levels. We validate the effectiveness of MAGIC in generating diverse captions from different relational information items of an image. Experimental results show that MAGIC can generate very promising outcomes without using any image-caption training pairs.

arXiv:2112.05218

Learning Generalizable Behavior via Visual Rewrite Rules

Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations. The black-box nature of the neural network learning dynamics makes it impossible to audit trained deep agents and recover from such failures. In this paper, we propose a novel representation and learning approach to capture environment dynamics without using neural networks. It originates from the observation that, in games designed for people, the effect of an action can often be perceived in the form of local changes in consecutive visual observations. Our algorithm is designed to extract such vision-based changes and condense them into a set of action-dependent descriptive rules, which we call ''visual rewrite rules'' (VRRs). We also present preliminary results from a VRR agent that can explore, expand its rule set, and solve a game via planning with its learned VRR world model. In several classical games, our non-deep agent demonstrates superior performance, extreme sample efficiency, and robust generalization ability compared with several mainstream deep agents.

arXiv:2112.04366

La mujer a través de los personajes femeninos en el cine de temática financiera -- Women through female characters in financial topics films

Analysis and assessment of female characters in economic financial themes films that have appeared in some thirty relevant films, from the beginning of cinema, selected from various bibliographies. Descriptive, comparative and impartial study. Quantitative techniques are applied to measure the influence of women in terms of protagonism, positive values, negative values, compliance or non-compliance with the Bechdel test, and results are evaluated. It is based on two previous binding publications: Marzal et al. The crisis of the real. Representations of the 2008 financial crisis in contemporary audiovisual (2018) and Mart\'in-de-Santos, Financial administration through cinema. Analytical and critical study of the most interesting films for university education (20219. Realistic film versions are contrasted with actual events today.

arXiv:2112.03003

What goes on inside rumour and non-rumour tweets and their reactions: A Psycholinguistic Analyses

In recent years, the problem of rumours on online social media (OSM) has attracted lots of attention. Researchers have started investigating from two main directions. First is the descriptive analysis of rumours and secondly, proposing techniques to detect (or classify) rumours. In the descriptive line of works, where researchers have tried to analyse rumours using NLP approaches, there isnt much emphasis on psycho-linguistics analyses of social media text. These kinds of analyses on rumour case studies are vital for drawing meaningful conclusions to mitigate misinformation. For our analysis, we explored the PHEME9 rumour dataset (consisting of 9 events), including source tweets (both rumour and non-rumour categories) and response tweets. We compared the rumour and nonrumour source tweets and then their corresponding reply (response) tweets to understand how they differ linguistically for every incident. Furthermore, we also evaluated if these features can be used for classifying rumour vs. non-rumour tweets through machine learning models. To this end, we employed various classical and ensemble-based approaches. To filter out the highly discriminative psycholinguistic features, we explored the SHAP AI Explainability tool. To summarise, this research contributes by performing an in-depth psycholinguistic analysis of rumours related to various kinds of events.

arXiv:2112.02513

Intention Recognition for Multiple Agents

Intention recognition is an important step to facilitate collaboration among multiple agents. Existing work mainly focuses on intention recognition in a single-agent setting and uses a descriptive model, e.g. Bayesian networks, in the recognition process. In this article, we develop a new approach of identifying intentions for multiple agents through a clustering algorithm. We first define an intention model for multiple agents of interest. We use a prescriptive approach to model agents' behaviours where their intentions are hidden in the implementation of their plans. We introduce landmarks into the behavioural model therefore enhancing informative features to identify common intentions for multiple agents. Subsequently, we further refine the model by focusing only action sequences in their plan and provide a light model for identifying and comparing their intentions. The new models provide a simple approach of grouping agents' common intentions upon partial plans observed in agents' interactions. Then, we transform the intention recognition into an un-supervised learning problem and adapt a clustering algorithm to group intentions of multiple agents through comparing their behavioural models. We conduct the clustering process by measuring similarity of probability distributions over potential landmarks in intention models so as to discover agents' common intentions. Finally, we examine the new intention recognition approaches in two problem domains. We demonstrate importance of recognising common intentions of multiple agents in achieving their goals and provide experimental results to show performance of the new approaches.

arXiv:2112.01591공식 코드 · Papers with Code

PLSUM: Generating PT-BR Wikipedia by Summarizing Multiple Websites

Wikipedia is an important free source of intelligible knowledge. Despite that, Brazilian Portuguese Wikipedia still lacks descriptions for many subjects. In an effort to expand the Brazilian Wikipedia, we contribute PLSum, a framework for generating wiki-like abstractive summaries from multiple descriptive websites. The framework has an extractive stage followed by an abstractive one. In particular, for the abstractive stage, we fine-tune and compare two recent variations of the Transformer neural network, PTT5, and Longformer. To fine-tune and evaluate the model, we created a dataset with thousands of examples, linking reference websites to Wikipedia. Our results show that it is possible to generate meaningful abstractive summaries from Brazilian Portuguese web content.

arXiv:2112.01231

Internationalizing AI: Evolution and Impact of Distance Factors

International collaboration has become imperative in the field of AI. However, few studies exist concerning how distance factors have affected the international collaboration in AI research. In this study, we investigate this problem by using 1,294,644 AI related collaborative papers harvested from the Microsoft Academic Graph (MAG) dataset. A framework including 13 indicators to quantify the distance factors between countries from 5 perspectives (i.e., geographic distance, economic distance, cultural distance, academic distance, and industrial distance) is proposed. The relationships were conducted by the methods of descriptive analysis and regression analysis. The results show that international collaboration in the field of AI today is not prevalent (only 15.7%). All the separations in international collaborations have increased over years, except for the cultural distance in masculinity/felinity dimension and the industrial distance. The geographic distance, economic distance and academic distances have shown significantly negative relationships with the degree of international collaborations in the field of AI. The industrial distance has a significant positive relationship with the degree of international collaboration in the field of AI. Also, the results demonstrate that the participation of the United States and China have promoted the international collaboration in the field of AI. This study provides a comprehensive understanding of internationalizing AI research in geographic, economic, cultural, academic, and industrial aspects.

arXiv:2112.01037

Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attention

Multi-label few-shot image classification (ML-FSIC) is the task of assigning descriptive labels to previously unseen images, based on a small number of training examples. A key feature of the multi-label setting is that images often have multiple labels, which typically refer to different regions of the image. When estimating prototypes, in a metric-based setting, it is thus important to determine which regions are relevant for which labels, but the limited amount of training data makes this highly challenging. As a solution, in this paper we propose to use word embeddings as a form of prior knowledge about the meaning of the labels. In particular, visual prototypes are obtained by aggregating the local feature maps of the support images, using an attention mechanism that relies on the label embeddings. As an important advantage, our model can infer prototypes for unseen labels without the need for fine-tuning any model parameters, which demonstrates its strong generalization abilities. Experiments on COCO and PASCAL VOC furthermore show that our model substantially improves the current state-of-the-art.

arXiv:2112.00848

First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle

The Abstraction and Reasoning Corpus (ARC) was recently introduced by Fran\c{c}ois Chollet as a tool to measure broad intelligence in both humans and machines. It is very challenging, and the best approach in a Kaggle competition could only solve 20% of the tasks, relying on brute-force search for chains of hand-crafted transformations. In this paper, we present the first steps exploring an approach based on descriptive grid models and the Minimum Description Length (MDL) principle. The grid models describe the contents of a grid, and support both parsing grids and generating grids. The MDL principle is used to guide the search for good models, i.e. models that compress the grids the most. We report on our progress over a year, improving on the general approach and the models. Out of the 400 training tasks, our performance increased from 5 to 29 solved tasks, only using 30s computation time per task. Our approach not only predicts the output grids, but also outputs an intelligible model and explanations for how the model was incrementally built.