October 19, 2019

2865 words 14 mins read

Paper Group ANR 223

Paper Group ANR 223

Weakly Supervised Attention Learning for Textual Phrases Grounding. Structured Multi-Label Biomedical Text Tagging via Attentive Neural Tree Decoding. The Anatomy of a Cryptocurrency Pump-and-Dump Scheme. Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks. Deep Differential Recurrent Neural Networks. …

Weakly Supervised Attention Learning for Textual Phrases Grounding

Title Weakly Supervised Attention Learning for Textual Phrases Grounding
Authors Zhiyuan Fang, Shu Kong, Tianshu Yu, Yezhou Yang
Abstract Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the supervised learning mechanism which requires ground-truth at pixel level during training. However, fine-grained level ground-truth annotation is quite time-consuming and severely narrows the scope for more general applications. In this extended abstract, we explore methods to localize flexibly image regions from the top-down signal (in a form of one-hot label or natural languages) with a weakly supervised attention learning mechanism. In our model, two types of modules are utilized: a backbone module for visual feature capturing, and an attentive module generating maps based on regularized bilinear pooling. We construct the model in an end-to-end fashion which is trained by encouraging the spatial attentive map to shift and focus on the region that consists of the best matched visual features with the top-down signal. We demonstrate the preliminary yet promising results on a testbed that is synthesized with multi-label MNIST data.
Tasks
Published 2018-05-01
URL http://arxiv.org/abs/1805.00545v1
PDF http://arxiv.org/pdf/1805.00545v1.pdf
PWC https://paperswithcode.com/paper/weakly-supervised-attention-learning-for
Repo
Framework

Structured Multi-Label Biomedical Text Tagging via Attentive Neural Tree Decoding

Title Structured Multi-Label Biomedical Text Tagging via Attentive Neural Tree Decoding
Authors Gaurav Singh, James Thomas, Iain J. Marshall, John Shawe-Taylor, Byron C. Wallace
Abstract We propose a model for tagging unstructured texts with an arbitrary number of terms drawn from a tree-structured vocabulary (i.e., an ontology). We treat this as a special case of sequence-to-sequence learning in which the decoder begins at the root node of an ontological tree and recursively elects to expand child nodes as a function of the input text, the current node, and the latent decoder state. In our experiments the proposed method outperforms state-of-the-art approaches on the important task of automatically assigning MeSH terms to biomedical abstracts.
Tasks
Published 2018-10-02
URL http://arxiv.org/abs/1810.01468v1
PDF http://arxiv.org/pdf/1810.01468v1.pdf
PWC https://paperswithcode.com/paper/structured-multi-label-biomedical-text
Repo
Framework

The Anatomy of a Cryptocurrency Pump-and-Dump Scheme

Title The Anatomy of a Cryptocurrency Pump-and-Dump Scheme
Authors Jiahua Xu, Benjamin Livshits
Abstract While pump-and-dump schemes have attracted the attention of cryptocurrency observers and regulators alike, this paper represents the first detailed empirical query of pump-and-dump activities in cryptocurrency markets. We present a case study of a recent pump-and-dump event, investigate 412 pump-and-dump activities organized in Telegram channels from June 17, 2018 to February 26, 2019, and discover patterns in crypto-markets associated with pump-and-dump schemes. We then build a model that predicts the pump likelihood of all coins listed in a crypto-exchange prior to a pump. The model exhibits high precision as well as robustness, and can be used to create a simple, yet very effective trading strategy, which we empirically demonstrate can generate a return as high as 60% on small retail investments within a span of two and half months. The study provides a proof of concept for strategic crypto-trading and sheds light on the application of machine learning for crime detection.
Tasks
Published 2018-11-25
URL https://arxiv.org/abs/1811.10109v2
PDF https://arxiv.org/pdf/1811.10109v2.pdf
PWC https://paperswithcode.com/paper/the-anatomy-of-a-cryptocurrency-pump-and-dump
Repo
Framework

Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks

Title Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks
Authors Tengyuan Liang, James Stokes
Abstract Motivated by the pursuit of a systematic computational and algorithmic understanding of Generative Adversarial Networks (GANs), we present a simple yet unified non-asymptotic local convergence theory for smooth two-player games, which subsumes several discrete-time gradient-based saddle point dynamics. The analysis reveals the surprising nature of the off-diagonal interaction term as both a blessing and a curse. On the one hand, this interaction term explains the origin of the slow-down effect in the convergence of Simultaneous Gradient Ascent (SGA) to stable Nash equilibria. On the other hand, for the unstable equilibria, exponential convergence can be proved thanks to the interaction term, for four modified dynamics proposed to stabilize GAN training: Optimistic Mirror Descent (OMD), Consensus Optimization (CO), Implicit Updates (IU) and Predictive Method (PM). The analysis uncovers the intimate connections among these stabilizing techniques, and provides detailed characterization on the choice of learning rate. As a by-product, we present a new analysis for OMD proposed in Daskalakis, Ilyas, Syrgkanis, and Zeng [2017] with improved rates.
Tasks
Published 2018-02-16
URL http://arxiv.org/abs/1802.06132v2
PDF http://arxiv.org/pdf/1802.06132v2.pdf
PWC https://paperswithcode.com/paper/interaction-matters-a-note-on-non-asymptotic
Repo
Framework

Deep Differential Recurrent Neural Networks

Title Deep Differential Recurrent Neural Networks
Authors Naifan Zhuang, The Duc Kieu, Guo-Jun Qi, Kien A. Hua
Abstract Due to the special gating schemes of Long Short-Term Memory (LSTM), LSTMs have shown greater potential to process complex sequential information than the traditional Recurrent Neural Network (RNN). The conventional LSTM, however, fails to take into consideration the impact of salient spatio-temporal dynamics present in the sequential input data. This problem was first addressed by the differential Recurrent Neural Network (dRNN), which uses a differential gating scheme known as Derivative of States (DoS). DoS uses higher orders of internal state derivatives to analyze the change in information gain caused by the salient motions between the successive frames. The weighted combination of several orders of DoS is then used to modulate the gates in dRNN. While each individual order of DoS is good at modeling a certain level of salient spatio-temporal sequences, the sum of all the orders of DoS could distort the detected motion patterns. To address this problem, we propose to control the LSTM gates via individual orders of DoS and stack multiple levels of LSTM cells in an increasing order of state derivatives. The proposed model progressively builds up the ability of the LSTM gates to detect salient dynamical patterns in deeper stacked layers modeling higher orders of DoS, and thus the proposed LSTM model is termed deep differential Recurrent Neural Network (d2RNN). The effectiveness of the proposed model is demonstrated on two publicly available human activity datasets: NUS-HGA and Violent-Flows. The proposed model outperforms both LSTM and non-LSTM based state-of-the-art algorithms.
Tasks
Published 2018-04-11
URL http://arxiv.org/abs/1804.04192v1
PDF http://arxiv.org/pdf/1804.04192v1.pdf
PWC https://paperswithcode.com/paper/deep-differential-recurrent-neural-networks
Repo
Framework

Towards Knowledge Discovery from the Vatican Secret Archives. In Codice Ratio – Episode 1: Machine Transcription of the Manuscripts

Title Towards Knowledge Discovery from the Vatican Secret Archives. In Codice Ratio – Episode 1: Machine Transcription of the Manuscripts
Authors Donatella Firmani, Marco Maiorino, Paolo Merialdo, Elena Nieddu
Abstract In Codice Ratio is a research project to study tools and techniques for analyzing the contents of historical documents conserved in the Vatican Secret Archives (VSA). In this paper, we present our efforts to develop a system to support the transcription of medieval manuscripts. The goal is to provide paleographers with a tool to reduce their efforts in transcribing large volumes, as those stored in the VSA, producing good transcriptions for significant portions of the manuscripts. We propose an original approach based on character segmentation. Our solution is able to deal with the dirty segmentation that inevitably occurs in handwritten documents. We use a convolutional neural network to recognize characters and language models to compose word transcriptions. Our approach requires minimal training efforts, making the transcription process more scalable as the production of training sets requires a few pages and can be easily crowdsourced. We have conducted experiments on manuscripts from the Vatican Registers, an unreleased corpus containing the correspondence of the popes. With training data produced by 120 high school students, our system has been able to produce good transcriptions that can be used by paleographers as a solid basis to speedup the transcription process at a large scale.
Tasks
Published 2018-03-08
URL http://arxiv.org/abs/1803.03200v3
PDF http://arxiv.org/pdf/1803.03200v3.pdf
PWC https://paperswithcode.com/paper/towards-knowledge-discovery-from-the-vatican
Repo
Framework

Text Assisted Insight Ranking Using Context-Aware Memory Network

Title Text Assisted Insight Ranking Using Context-Aware Memory Network
Authors Qi Zeng, Liangchen Luo, Wenhao Huang, Yang Tang
Abstract Extracting valuable facts or informative summaries from multi-dimensional tables, i.e. insight mining, is an important task in data analysis and business intelligence. However, ranking the importance of insights remains a challenging and unexplored task. The main challenge is that explicitly scoring an insight or giving it a rank requires a thorough understanding of the tables and costs a lot of manual efforts, which leads to the lack of available training data for the insight ranking problem. In this paper, we propose an insight ranking model that consists of two parts: A neural ranking model explores the data characteristics, such as the header semantics and the data statistical features, and a memory network model introduces table structure and context information into the ranking process. We also build a dataset with text assistance. Experimental results show that our approach largely improves the ranking precision as reported in multi evaluation metrics.
Tasks
Published 2018-11-13
URL http://arxiv.org/abs/1811.05563v1
PDF http://arxiv.org/pdf/1811.05563v1.pdf
PWC https://paperswithcode.com/paper/text-assisted-insight-ranking-using-context
Repo
Framework

Embedding Uncertain Knowledge Graphs

Title Embedding Uncertain Knowledge Graphs
Authors Xuelu Chen, Muhao Chen, Weijia Shi, Yizhou Sun, Carlo Zaniolo
Abstract Embedding models for deterministic Knowledge Graphs (KG) have been extensively studied, with the purpose of capturing latent semantic relations between entities and incorporating the structured knowledge into machine learning. However, there are many KGs that model uncertain knowledge, which typically model the inherent uncertainty of relations facts with a confidence score, and embedding such uncertain knowledge represents an unresolved challenge. The capturing of uncertain knowledge will benefit many knowledge-driven applications such as question answering and semantic search by providing more natural characterization of the knowledge. In this paper, we propose a novel uncertain KG embedding model UKGE, which aims to preserve both structural and uncertainty information of relation facts in the embedding space. Unlike previous models that characterize relation facts with binary classification techniques, UKGE learns embeddings according to the confidence scores of uncertain relation facts. To further enhance the precision of UKGE, we also introduce probabilistic soft logic to infer confidence scores for unseen relation facts during training. We propose and evaluate two variants of UKGE based on different learning objectives. Experiments are conducted on three real-world uncertain KGs via three tasks, i.e. confidence prediction, relation fact ranking, and relation fact classification. UKGE shows effectiveness in capturing uncertain knowledge by achieving promising results on these tasks, and consistently outperforms baselines on these tasks.
Tasks Knowledge Graphs, Question Answering
Published 2018-11-26
URL http://arxiv.org/abs/1811.10667v2
PDF http://arxiv.org/pdf/1811.10667v2.pdf
PWC https://paperswithcode.com/paper/embedding-uncertain-knowledge-graphs
Repo
Framework

Zero-Shot Anticipation for Instructional Activities

Title Zero-Shot Anticipation for Instructional Activities
Authors Fadime Sener, Angela Yao
Abstract How can we teach a robot to predict what will happen next for an activity it has never seen before? We address this problem of zero-shot anticipation by presenting a hierarchical model that generalizes instructional knowledge from large-scale text-corpora and transfers the knowledge to the visual domain. Given a portion of an instructional video, our model predicts coherent and plausible actions multiple steps into the future, all in rich natural language. To demonstrate the anticipation capabilities of our model, we introduce the Tasty Videos dataset, a collection of 2511 recipes for zero-shot learning, recognition and anticipation.
Tasks Zero-Shot Learning
Published 2018-12-06
URL https://arxiv.org/abs/1812.02501v3
PDF https://arxiv.org/pdf/1812.02501v3.pdf
PWC https://paperswithcode.com/paper/zero-shot-anticipation-for-instructional
Repo
Framework

Structure and Motion from Multiframes

Title Structure and Motion from Multiframes
Authors Mieczysław A. Kłopotek
Abstract The paper gives an overview of the problems and methods of recovery of structure and motion parameters of rigid bodies from multiframes.
Tasks
Published 2018-11-30
URL http://arxiv.org/abs/1811.12797v1
PDF http://arxiv.org/pdf/1811.12797v1.pdf
PWC https://paperswithcode.com/paper/structure-and-motion-from-multiframes
Repo
Framework

How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation

Title How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation
Authors Menaka Narayanan, Emily Chen, Jeffrey He, Been Kim, Sam Gershman, Finale Doshi-Velez
Abstract Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains poorly understood. This work advances our understanding of what makes explanations interpretable in the specific context of verification. Suppose we have a machine learning system that predicts X, and we provide rationale for this prediction X. Given an input, an explanation, and an output, is the output consistent with the input and the supposed rationale? Via a series of user-studies, we identify what kinds of increases in complexity have the greatest effect on the time it takes for humans to verify the rationale, and which seem relatively insensitive.
Tasks
Published 2018-02-02
URL http://arxiv.org/abs/1802.00682v1
PDF http://arxiv.org/pdf/1802.00682v1.pdf
PWC https://paperswithcode.com/paper/how-do-humans-understand-explanations-from
Repo
Framework

Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking

Title Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking
Authors Shikhar Murty*, Patrick Verga*, Luke Vilnis, Irena Radovanovic, Andrew McCallum
Abstract Extraction from raw text to a knowledge base of entities and fine-grained types is often cast as prediction into a flat set of entity and type labels, neglecting the rich hierarchies over types and entities contained in curated ontologies. Previous attempts to incorporate hierarchical structure have yielded little benefit and are restricted to shallow ontologies. This paper presents new methods using real and complex bilinear mappings for integrating hierarchical information, yielding substantial improvement over flat predictions in entity linking and fine-grained entity typing, and achieving new state-of-the-art results for end-to-end models on the benchmark FIGER dataset. We also present two new human-annotated datasets containing wide and deep hierarchies which we will release to the community to encourage further research in this direction: MedMentions, a collection of PubMed abstracts in which 246k mentions have been mapped to the massive UMLS ontology; and TypeNet, which aligns Freebase types with the WordNet hierarchy to obtain nearly 2k entity types. In experiments on all three datasets we show substantial gains from hierarchy-aware training.
Tasks Entity Linking, Entity Typing
Published 2018-07-13
URL http://arxiv.org/abs/1807.05127v1
PDF http://arxiv.org/pdf/1807.05127v1.pdf
PWC https://paperswithcode.com/paper/hierarchical-losses-and-new-resources-for
Repo
Framework

SEE: Syntax-aware Entity Embedding for Neural Relation Extraction

Title SEE: Syntax-aware Entity Embedding for Neural Relation Extraction
Authors Zhengqiu He, Wenliang Chen, Zhenghua Li, Meishan Zhang, Wei Zhang, Min Zhang
Abstract Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction have shown great progress on this task via modeling the sentences in low-dimensional spaces, but seldom considered syntax information to model the entities. In this paper, we propose to learn syntax-aware entity embedding for neural relation extraction. First, we encode the context of entities on a dependency tree as sentence-level entity embedding based on tree-GRU. Then, we utilize both intra-sentence and inter-sentence attentions to obtain sentence set-level entity embedding over all sentences containing the focus entity pair. Finally, we combine both sentence embedding and entity embedding for relation classification. We conduct experiments on a widely used real-world dataset and the experimental results show that our model can make full use of all informative instances and achieve state-of-the-art performance of relation extraction.
Tasks Relation Classification, Relation Extraction, Sentence Embedding
Published 2018-01-11
URL http://arxiv.org/abs/1801.03603v1
PDF http://arxiv.org/pdf/1801.03603v1.pdf
PWC https://paperswithcode.com/paper/see-syntax-aware-entity-embedding-for-neural
Repo
Framework

Neural Cross-Lingual Named Entity Recognition with Minimal Resources

Title Neural Cross-Lingual Named Entity Recognition with Minimal Resources
Authors Jiateng Xie, Zhilin Yang, Graham Neubig, Noah A. Smith, Jaime Carbonell
Abstract For languages with no annotated resources, unsupervised transfer of natural language processing models such as named-entity recognition (NER) from resource-rich languages would be an appealing capability. However, differences in words and word order across languages make it a challenging problem. To improve mapping of lexical items across languages, we propose a method that finds translations based on bilingual word embeddings. To improve robustness to word order differences, we propose to use self-attention, which allows for a degree of flexibility with respect to word order. We demonstrate that these methods achieve state-of-the-art or competitive NER performance on commonly tested languages under a cross-lingual setting, with much lower resource requirements than past approaches. We also evaluate the challenges of applying these methods to Uyghur, a low-resource language.
Tasks Named Entity Recognition, Word Embeddings
Published 2018-08-29
URL http://arxiv.org/abs/1808.09861v2
PDF http://arxiv.org/pdf/1808.09861v2.pdf
PWC https://paperswithcode.com/paper/neural-cross-lingual-named-entity-recognition
Repo
Framework

Arabic Named Entity Recognition using Word Representations

Title Arabic Named Entity Recognition using Word Representations
Authors Ismail El Bazi, Nabil Laachfoubi
Abstract Recent work has shown the effectiveness of the word representations features in significantly improving supervised NER for the English language. In this study we investigate whether word representations can also boost supervised NER in Arabic. We use word representations as additional features in a Conditional Random Field (CRF) model and we systematically compare three popular neural word embedding algorithms (SKIP-gram, CBOW and GloVe) and six different approaches for integrating word representations into NER system. Experimental results show that Brown Clustering achieves the best performance among the six approaches. Concerning the word embedding features, the clustering embedding features outperform other embedding features and the distributional prototypes produce the second best result. Moreover, the combination of Brown clusters and word embedding features provides additional improvement of nearly 10% in F1-score over the baseline.
Tasks Named Entity Recognition
Published 2018-04-16
URL http://arxiv.org/abs/1804.05630v1
PDF http://arxiv.org/pdf/1804.05630v1.pdf
PWC https://paperswithcode.com/paper/arabic-named-entity-recognition-using-word
Repo
Framework
comments powered by Disqus