【arxiv论文】 Computation and Language 2020-10-14

发表于 2020-10-14 分类于 arxiv ， CL 90k 2:29

目录

1. Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think! [PDF] 摘要

2. XL-WiC: A Multilingual Benchmark for Evaluating Semantic Contextualization [PDF] 摘要

3. Demographic Representation and Collective Storytelling in the Me Too Twitter Hashtag Activism Movement [PDF] 摘要

4. Pagsusuri ng RNN-based Transfer Learning Technique sa Low-Resource Language [PDF] 摘要

5. RuSemShift: a dataset of historical lexical semantic change in Russian [PDF] 摘要

6. Multilingual Argument Mining: Datasets and Analysis [PDF] 摘要

7. Interpreting Attention Models with Human Visual Attention in Machine Reading Comprehension [PDF] 摘要

8. Aspect-based Document Similarity for Research Papers [PDF] 摘要

9. Fine-grained linguistic evaluation for state-of-the-art Machine Translation [PDF] 摘要

10. The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MT [PDF] 摘要

11. CAPT: Contrastive Pre-Training for LearningDenoised Sequence Representations [PDF] 摘要

12. Modeling the Music Genre Perception across Language-Bound Cultures [PDF] 摘要

13. Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks [PDF] 摘要

14. Extending Implicit Discourse Relation Recognition to the PDTB-3 [PDF] 摘要

15. F1 is Not Enough! Models and Evaluation Towards User-Centered Explainable Question Answering [PDF] 摘要

16. RGCL at SemEval-2020 Task 6: Neural Approaches to Definition Extraction [PDF] 摘要

17. BRUMS at SemEval-2020 Task 12 : Transformer based Multilingual Offensive Language Identification in Social Media [PDF] 摘要

18. BRUMS at SemEval-2020 Task 3: Contextualised Embeddings forPredicting the (Graded) Effect of Context in Word Similarity [PDF] 摘要

19. Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks [PDF] 摘要

20. Annotationsaurus: A Searchable Directory of Annotation Tools [PDF] 摘要

21. KLearn: Background Knowledge Inference from Summarization Data [PDF] 摘要

22. Mitigating Gender Bias in Machine Translation with Target Gender Annotations [PDF] 摘要

23. Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations [PDF] 摘要

24. Multilingual Factual Knowledge Retrieval from Pretrained Language Models [PDF] 摘要

25. The workweek is the best time to start a family -- A Study of GPT-2 Based Claim Generation [PDF] 摘要

26. Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance [PDF] 摘要

27. Incorporating BERT into Parallel Sequence Decoding with Adapters [PDF] 摘要

28. Corruption Is Not All Bad: Incorporating Discourse Structure into Pre-training via Corruption for Essay Scoring [PDF] 摘要

29. BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's Distance [PDF] 摘要

30. Model Selection for Cross-Lingual Transfer using a Learned Scoring Function [PDF] 摘要

31. Asking Crowdworkers to Write Entailment Examples: The Best of Bad Options [PDF] 摘要

32. ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis [PDF] 摘要

33. Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks [PDF] 摘要

34. Are Some Words Worth More than Others? [PDF] 摘要

35. Zero-shot Entity Linking with Efficient Long Range Sequence Modeling [PDF] 摘要

36. BioMegatron: Larger Biomedical Domain Language Model [PDF] 摘要

37. TextHide: Tackling Data Privacy in Language Understanding Tasks [PDF] 摘要

38. Towards Machine Translation for the Kurdish Language [PDF] 摘要

39. Improving Self-supervised Pre-training via a Fully-Explored Masked Language Model [PDF] 摘要

40. Measuring and Reducing Gendered Correlations in Pre-trained Models [PDF] 摘要

41. Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling [PDF] 摘要

42. End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems [PDF] 摘要

43. Gender Coreference and Bias Evaluation at WMT 2020 [PDF] 摘要

44. Look It Up: Bilingual and Monolingual Dictionaries Improve Neural Machine Translation [PDF] 摘要

45. Improving Text Generation with Student-Forcing Optimal Transport [PDF] 摘要

46. Vulgaris: Analysis of a Corpus for Middle-Age Varieties of Italian Language [PDF] 摘要

47. Chatbot Interaction with Artificial Intelligence: Human Data Augmentation with T5 and Language Transformer Ensemble for Text Classification [PDF] 摘要

48. SLEDGE-Z: A Zero-Shot Baseline for COVID-19 Literature Search [PDF] 摘要

49. NEMO: Frequentist Inference Approach to Constrained Linguistic Typology Feature Prediction in SIGTYP 2020 Shared Task [PDF] 摘要

50. The Extraordinary Failure of Complement Coercion Crowdsourcing [PDF] 摘要

51. The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units [PDF] 摘要

52. Perceptimatic: A human speech perception benchmark for unsupervised subword modelling [PDF] 摘要

53. Towards Induction of Structured Phoneme Inventories [PDF] 摘要

54. COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs [PDF] 摘要

55. Fantastic Features and Where to Find Them: Detecting Cognitive Impairment with a Subsequence Classification Guided Approach [PDF] 摘要

56. Controlling the Interaction Between Generation and Inference in Semi-Supervised Variational Autoencoders Using Importance Weighting [PDF] 摘要

57. Autotuning Search Space for Loop Transformations [PDF] 摘要

58. Pretrained Transformers for Text Ranking: BERT and Beyond [PDF] 摘要

59. Automatic Extraction of Urban Outdoor Perception from Geolocated Free-Texts [PDF] 摘要

60. Artificial Intelligence, speech and language processing approaches to monitoring Alzheimer's Disease: a systematic review [PDF] 摘要

61. MedICaT: A Dataset of Medical Images, Captions, and Textual References [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-12

发表于 2020-10-12 分类于 arxiv ， CV 74k 2:03

目录

1. Robust Isometric Non-Rigid Structure-from-Motion [PDF] 摘要

2. Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds [PDF] 摘要

3. Hyperspectral Unmixing via Nonnegative Matrix Factorization with Handcrafted and Learnt Priors [PDF] 摘要

4. GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering [PDF] 摘要

5. A Novel ANN Structure for Image Recognition [PDF] 摘要

6. Table Structure Recognition using Top-Down and Bottom-Up Cues [PDF] 摘要

7. Incorporating planning intelligence into deep learning: A planning support tool for street network design [PDF] 摘要

8. Uncertainty-Aware Few-Shot Image Classification [PDF] 摘要

9. Real Time Face Recognition Using Convoluted Neural Networks [PDF] 摘要

10. Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer [PDF] 摘要

11. Controllable Continuous Gaze Redirection [PDF] 摘要

12. Background Learnable Cascade for Zero-Shot Object Detection [PDF] 摘要

13. Contralaterally Enhanced Networks for Thoracic Disease Detection [PDF] 摘要

14. gundapusunil at SemEval-2020 Task 8: Multimodal Memotion Analysis [PDF] 摘要

15. Real-time Mask Detection on Google Edge TPU [PDF] 摘要

16. Long-distance tiny face detection based on enhanced YOLOv3 for unmanned system [PDF] 摘要

17. A deep learning based interactive sketching system for fashion images design [PDF] 摘要

18. Generating Novel Glyph without Human Data by Learning to Communicate [PDF] 摘要

19. Learning 3D Face Reconstruction with a Pose Guidance Network [PDF] 摘要

20. Deep Sequence Learning for Video Anticipation: From Discrete and Deterministic to Continuous and Stochastic [PDF] 摘要

21. Robust Instance Tracking via Uncertainty Flow [PDF] 摘要

22. DeepStreet: A deep learning powered urban street network generation module [PDF] 摘要

23. Deep Learning Superpixel Semantic Segmentation with Transparent Initialization and Sparse Encoder [PDF] 摘要

24. Once Quantized for All: Progressively Searching for Quantized Efficient Models [PDF] 摘要

25. MMGSD: Multi-Modal Gaussian Shape Descriptors for Correspondence Matching in 1D and 2D Deformable Objects [PDF] 摘要

26. Targeted Attention Attack on Deep Learning Models in Road Sign Recognition [PDF] 摘要

27. Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images [PDF] 摘要

28. Addressing the Real-world Class Imbalance Problem in Dermatology [PDF] 摘要

29. Large Scale Indexing of Generic Medical Image Data using Unbiased Shallow Keypoints and Deep CNN Features [PDF] 摘要

30. Refinement of Predicted Missing Parts Enhance Point Cloud Completion [PDF] 摘要

31. Fast Fourier Transformation for Optimizing Convolutional Neural Networks in Object Recognition [PDF] 摘要

32. Ensemble Hyperspectral Band Selection for Detecting Nitrogen Status in Grape Leaves [PDF] 摘要

33. Efficient Real-Time Radial Distortion Correction for UAVs [PDF] 摘要

34. Unsupervised 3D Brain Anomaly Detection [PDF] 摘要

35. PathoNet: Deep learning assisted evaluation of Ki-67 and tumor infiltrating lymphocytes (TILs) as prognostic factors in breast cancer; A large dataset and baseline [PDF] 摘要

36. LaND: Learning to Navigate from Disengagements [PDF] 摘要

37. Smooth Variational Graph Embeddings for Efficient Neural Architecture Search [PDF] 摘要

38. Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [PDF] 摘要

39. Baseline and Triangulation Geometry in a Standard Plenoptic Camera [PDF] 摘要

40. Attaining Real-Time Super-Resolution for Microscopic Images Using GAN [PDF] 摘要

41. Conditional GAN for Prediction of Glaucoma Progression with Macular Optical Coherence Tomography [PDF] 摘要

42. Sickle-cell disease diagnosis support selecting the most appropriate machinelearning method: Towards a general and interpretable approach for cellmorphology analysis from microscopy images [PDF] 摘要

43. Linear Mode Connectivity in Multitask and Continual Learning [PDF] 摘要

44. Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting [PDF] 摘要

45. Rethinking the Extraction and Interaction of Multi-Scale Features for Vessel Segmentation [PDF] 摘要

46. WHO 2016 subtyping and automated segmentation of glioma using multi-task deep learning [PDF] 摘要

47. Weaponizing Unicodes with Deep Learning -- Identifying Homoglyphs with Weakly Labeled Data [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-12

发表于 2020-10-12 分类于 arxiv ， CL 77k 2:09

目录

1. Uncertainty over Uncertainty: Investigating the Assumptions, Annotations, and Text Measurements of Economic Policy Uncertainty [PDF] 摘要

2. Recursive Top-Down Production for Sentence Generation with Latent Trees [PDF] 摘要

3. Learning Context-Free Languages with Nondeterministic Stack RNNs [PDF] 摘要

4. Scaling Systematic Literature Reviews with Machine Learning Pipelines [PDF] 摘要

5. Case Study: Deontological Ethics in NLP [PDF] 摘要

6. LSTMs Compose (and Learn) Bottom-Up [PDF] 摘要

7. High-order Semantic Role Labeling [PDF] 摘要

8. Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction [PDF] 摘要

9. Recurrent babbling: evaluating the acquisition of grammar from limited input data [PDF] 摘要

10. Examining the Ordering of Rhetorical Strategies in Persuasive Requests [PDF] 摘要

11. Mark-Evaluate: Assessing Language Generation using Population Estimation Methods [PDF] 摘要

12. Denoising Multi-Source Weak Supervision for Neural Text Classification [PDF] 摘要

13. HENIN: Learning Heterogeneous Neural Interaction Networks for Explainable Cyberbullying Detection on Social Media [PDF] 摘要

14. Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis [PDF] 摘要

15. Measuring What Counts: The case of Rumour Stance Classification [PDF] 摘要

16. What Have We Achieved on Text Summarization? [PDF] 摘要

17. Online Back-Parsing for AMR-to-Text Generation [PDF] 摘要

18. Self-Paced Learning for Neural Machine Translation [PDF] 摘要

19. Top-Rank-Focused Adaptive Vote Collection for the Evaluation of Domain-Specific Semantic Models [PDF] 摘要

20. Word Level Language Identification in English Telugu Code Mixed Data [PDF] 摘要

21. MLQE-PE: A Multilingual Quality Estimation and Post-Editing Dataset [PDF] 摘要

22. Multichannel Generative Language Model: Learning All Possible Factorizations Within and Across Channels [PDF] 摘要

23. Uncertainty-Aware Semantic Augmentation for Neural Machine Translation [PDF] 摘要

24. gundapusunil at SemEval-2020 Task 9: Syntactic Semantic LSTM Architecture for SENTIment Analysis of Code-MIXed Data [PDF] 摘要

25. A Survey of Knowledge-Enhanced Text Generation [PDF] 摘要

26. Graphing Contributions in Natural Language Processing Research: Intra-Annotator Agreement on a Trial Dataset [PDF] 摘要

27. Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation [PDF] 摘要

28. Token-level Adaptive Training for Neural Machine Translation [PDF] 摘要

29. Q-learning with Language Model for Edit-based Unsupervised Summarization [PDF] 摘要

30. iobes: A Library for Span-Level Processing [PDF] 摘要

31. Pragmatically Informative Color Generation by Grounding Contextual Modifiers [PDF] 摘要

32. Constrained Decoding for Computationally Efficient Named Entity Recognition Taggers [PDF] 摘要

33. Style Attuned Pre-training and Parameter Efficient Fine-tuning for Spoken Language Understanding [PDF] 摘要

34. Plug-and-Play Conversational Models [PDF] 摘要

35. NutCracker at WNUT-2020 Task 2: Robustly Identifying Informative COVID-19 Tweets using Ensembling and Adversarial Training [PDF] 摘要

36. Langsmith: An Interactive Academic Text Revision System [PDF] 摘要

37. Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning [PDF] 摘要

38. How Can Self-Attention Networks Recognize Dyck-n Languages? [PDF] 摘要

39. Masked ELMo: An evolution of ELMo towards fully contextual RNN language models [PDF] 摘要

40. Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task [PDF] 摘要

41. Analysis of Disfluency in Children's Speech [PDF] 摘要

42. comp-syn: Perceptually Grounded Word Embeddings with Color [PDF] 摘要

43. On the Role of Style in Parsing Speech with Neural Models [PDF] 摘要

44. Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems [PDF] 摘要

45. Fake Reviews Detection through Analysis of Linguistic Features [PDF] 摘要

46. Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks [PDF] 摘要

47. Dual Inference for Improving Language Understanding and Generation [PDF] 摘要

48. Query-Key Normalization for Transformers [PDF] 摘要

49. PoinT-5: Pointer Network and T-5 based Financial NarrativeSummarisation [PDF] 摘要

50. Causal Feature Selection with Dimension Reduction for Interpretable Text Classification [PDF] 摘要

51. The NU Voice Conversion System for the Voice Conversion Challenge 2020: On the Effectiveness of Sequence-to-sequence Models and Autoregressive Neural Vocoders [PDF] 摘要

52. Baseline System of Voice Conversion Challenge 2020 with Cyclic Variational Autoencoder and Parallel WaveGAN [PDF] 摘要

53. Hate is the New Infodemic: A Topic-aware Modeling of Hate Speech Diffusion on Twitter [PDF] 摘要

54. Event Representation with Sequential, Semi-Supervised Discrete Variables [PDF] 摘要

55. Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling [PDF] 摘要

56. Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-09

发表于 2020-10-09 分类于 arxiv ， CV 69k 1:55

目录

1. Deformable DETR: Deformable Transformers for End-to-End Object Detection [PDF] 摘要

2. A Survey On Anti-Spoofing Methods For Face Recognition with RGB Cameras of Generic Consumer Devices [PDF] 摘要

3. Deep SVBRDF Estimation on Real Materials [PDF] 摘要

4. 3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings [PDF] 摘要

5. Are Adaptive Face Recognition Systems still Necessary? Experiments on the APE Dataset [PDF] 摘要

6. Semi-Supervised Learning of Multi-Object 3D Scene Representations [PDF] 摘要

7. Single-Image Camera Response Function Using Prediction Consistency and Gradual Refinement [PDF] 摘要

8. Watch, read and lookup: learning to spot signs from multiple supervisors [PDF] 摘要

9. Unconstrained Text Detection in Manga [PDF] 摘要

10. UESegNet: Context Aware Unconstrained ROI Segmentation Networks for Ear Biometric [PDF] 摘要

11. A Human Ear Reconstruction Autoencoder [PDF] 摘要

12. IRX-1D: A Simple Deep Learning Architecture for Remote Sensing Classifications [PDF] 摘要

13. BGM: Building a Dynamic Guidance Map without Visual Images for Trajectory Prediction [PDF] 摘要

14. Clinically Verified Hybrid Deep Learning System for Retinal Ganglion Cells Aware Grading of Glaucomatous Progression [PDF] 摘要

15. Dense Relational Image Captioning via Multi-task Triple-Stream Networks [PDF] 摘要

16. A Comparative Study on Effects of Original and Pseudo Labels for Weakly Supervised Learning for Car Localization Problem [PDF] 摘要

17. Age and Gender Prediction From Face Images Using Attentional Convolutional Network [PDF] 摘要

18. DBLFace: Domain-Based Labels for NIR-VIS Heterogeneous Face Recognition [PDF] 摘要

19. Generative Autoregressive Ensembles for Satellite Imagery Manipulation Detection [PDF] 摘要

20. VisualNews : A Large Multi-source News Image Dataset [PDF] 摘要

21. Decamouflage: A Framework to Detect Image-Scaling Attacks on Convolutional Neural Networks [PDF] 摘要

22. Deep Tiered Image Segmentation forDetecting Internal Ice Layers in Radar Imagery [PDF] 摘要

23. Revisiting Batch Normalization for Improving Corruption Robustness [PDF] 摘要

24. Infant-ID: Fingerprints for Global Good [PDF] 摘要

25. Shape, Illumination, and Reflectance from Shading [PDF] 摘要

26. Regularized Compression of MRI Data: Modular Optimization of Joint Reconstruction and Coding [PDF] 摘要

27. A Unified Approach to Interpreting and Boosting Adversarial Transferability [PDF] 摘要

28. Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study [PDF] 摘要

29. Texture-based Presentation Attack Detection for Automatic Speaker Verification [PDF] 摘要

30. Frequency and Spatial domain based Saliency for Pigmented Skin Lesion Segmentation [PDF] 摘要

31. Spatially-Variant CNN-based Point Spread Function Estimation for Blind Deconvolution and Depth Estimation [PDF] 摘要

32. Tractography filtering using autoencoders [PDF] 摘要

33. Free annotated data for deep learning in microscopy? A hitchhiker's guide [PDF] 摘要

34. A Brief Review of Domain Adaptation [PDF] 摘要

35. Synthesising clinically realistic Chest X-rays using Generative Adversarial Networks [PDF] 摘要

36. High Definition image classification in Geoscience using Machine Learning [PDF] 摘要

37. Improve Adversarial Robustness via Weight Penalization on Classification Layer [PDF] 摘要

38. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning [PDF] 摘要

39. Bone Feature Segmentation in Ultrasound Spine Image with Robustness to Speckle and Regular Occlusion Noise [PDF] 摘要

40. 3D Convolutional Sequence to Sequence Model for Vertebral Compression Fractures Identification in CT [PDF] 摘要

41. A Critique of Self-Expressive Deep Subspace Clustering [PDF] 摘要

42. Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations [PDF] 摘要

43. pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-09

发表于 2020-10-09 分类于 arxiv ， CL 75k 2:06

目录

1. DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool [PDF] 摘要

2. Towards Topic-Guided Conversational Recommender System [PDF] 摘要

3. Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language? [PDF] 摘要

4. BERTering RAMS: What and How Much does BERT Already Know About Event Arguments? -- A Study on the RAMS Dataset [PDF] 摘要

5. Precise Task Formalization Matters in Winograd Schema Evaluations [PDF] 摘要

6. GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems [PDF] 摘要

7. Generating Instructions at Different Levels of Abstraction [PDF] 摘要

8. Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: ÚFAL Submission to the SIGTYP 2020 Shared Task [PDF] 摘要

9. Injecting Word Information with Multi-Level Word Adapter for Chinese Spoken Language Understanding [PDF] 摘要

10. Population Based Training for Data Augmentation and Regularization in Speech Recognition [PDF] 摘要

11. Large Product Key Memory for Pretrained Language Models [PDF] 摘要

12. A Co-Interactive Transformer for Joint Slot Filling and Intent Detection [PDF] 摘要

13. What Can We Do to Improve Peer Review in NLP? [PDF] 摘要

14. Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders [PDF] 摘要

15. Extracting a Knowledge Base of Mechanisms from COVID-19 Papers [PDF] 摘要

16. On the importance of pre-training data volume for compact language models [PDF] 摘要

17. TextSETTR: Label-Free Text Style Extraction and Tunable Targeted Restyling [PDF] 摘要

18. An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference [PDF] 摘要

19. Detect All Abuse! Toward Universal Abusive Language Detection Models [PDF] 摘要

20. Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention [PDF] 摘要

21. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning [PDF] 摘要

22. Improving Attention Mechanism with Query-Value Interaction [PDF] 摘要

23. Assessing Phrasal Representation and Composition in Transformers [PDF] 摘要

24. Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference [PDF] 摘要

25. Generalizable and Explainable Dialogue Generation via Explicit Action Learning [PDF] 摘要

26. Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition [PDF] 摘要

27. Multi-hop Inference for Question-driven Summarization [PDF] 摘要

28. Shallow-to-Deep Training for Neural Machine Translation [PDF] 摘要

29. Leveraging Discourse Rewards for Document-Level Neural Machine Translation [PDF] 摘要

30. Learning to Fuse Sentences with Transformers for Summarization [PDF] 摘要

31. PARADE: A New Dataset for Paraphrase Identification Requiring Computer Science Domain Knowledge [PDF] 摘要

32. A Cascade Approach to Neural Abstractive Summarization with Content Selection and Fusion [PDF] 摘要

33. Don't Parse, Insert: Multilingual Semantic Parsing with Insertion Based Decoding [PDF] 摘要

34. Learning to Recombine and Resample Data for Compositional Generalization [PDF] 摘要

35. Optimizing Transformers with Approximate Computing for Faster, Smaller and more Accurate NLP Models [PDF] 摘要

36. Adaptive Self-training for Few-shot Neural Sequence Labeling [PDF] 摘要

37. Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank [PDF] 摘要

38. Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data [PDF] 摘要

39. Cross-Thought for Sentence Encoder Pre-training [PDF] 摘要

40. A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks [PDF] 摘要

41. Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations [PDF] 摘要

42. Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations [PDF] 摘要

43. MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics [PDF] 摘要

44. MuSeM: Detecting Incongruent News Headlines using Mutual Attentive Semantic Matching [PDF] 摘要

45. Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets [PDF] 摘要

46. SRLGRN: Semantic Role Labeling Graph Reasoning Network [PDF] 摘要

47. Characterizing the Value of Information in Medical Notes [PDF] 摘要

48. Dense Relational Image Captioning via Multi-task Triple-Stream Networks [PDF] 摘要

49. Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines [PDF] 摘要

50. Latent linguistic embedding for cross-lingual text-to-speech and voice conversion [PDF] 摘要

51. Domain Adversarial Neural Networks for Dysarthric Speech Recognition [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-08

发表于 2020-10-08 分类于 arxiv ， CV 85k 2:22

目录

1. High-Capacity Expert Binary Networks [PDF] 摘要

2. On the Evaluation of Generative Adversarial Networks By Discriminative Models [PDF] 摘要

3. BoMuDA: Boundless Multi-Source Domain Adaptive Segmentation in Unconstrained Environments [PDF] 摘要

4. Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels [PDF] 摘要

5. Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning [PDF] 摘要

6. Super-Human Performance in Online Low-latency Recognition of Conversational Speech [PDF] 摘要

7. Universal Weighting Metric Learning for Cross-Modal Matching [PDF] 摘要

8. A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations [PDF] 摘要

9. Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation [PDF] 摘要

10. Multi-label classification of promotions in digital leaflets using textual and visual information [PDF] 摘要

11. Contour Primitive of Interest Extraction Network Based on One-shot Learning for Object-Agnostic Vision Measurement [PDF] 摘要

12. YOdar: Uncertainty-based Sensor Fusion for Vehicle Detection with Camera and Radar Sensors [PDF] 摘要

13. Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud [PDF] 摘要

14. CD-UAP: Class Discriminative Universal Adversarial Perturbation [PDF] 摘要

15. Attention Model Enhanced Network for Classification of Breast Cancer Image [PDF] 摘要

16. Learning Binary Semantic Embedding for Histology Image Classification and Retrieval [PDF] 摘要

17. Variational Transfer Learning for Fine-grained Few-shot Visual Recognition [PDF] 摘要

18. Learning Clusterable Visual Features for Zero-Shot Recognition [PDF] 摘要

19. RealSmileNet: A Deep End-To-End Network for Spontaneous and Posed Smile Recognition [PDF] 摘要

20. Vision-Based Object Recognition in Indoor Environments Using Topologically Persistent Features [PDF] 摘要

21. VICTR: Visual Information Captured Text Representation for Text-to-Image Multimodal Tasks [PDF] 摘要

22. A Study on Trees's Knots Prediction from their Bark Outer-Shape [PDF] 摘要

23. DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval [PDF] 摘要

24. SLCRF: Subspace Learning with Conditional Random Field for Hyperspectral Image Classification [PDF] 摘要

25. Channel Recurrent Attention Networks for Video Pedestrian Retrieval [PDF] 摘要

26. Adversarial Patch Attacks on Monocular Depth Estimation Networks [PDF] 摘要

27. Domain Adaptive Transfer Learning on Visual Attention Aware Data Augmentation for Fine-grained Visual Categorization [PDF] 摘要

28. Weakly-Supervised Feature Learning via Text and Image Matching [PDF] 摘要

29. Rotate to Attend: Convolutional Triplet Attention Module [PDF] 摘要

30. A deep learning pipeline for identification of motor units in musculoskeletal ultrasound [PDF] 摘要

31. Predicting Hourly Demand in Station-free Bike-sharing Systems with Video-level Data [PDF] 摘要

32. Place Recognition in Forests with Urquhart Tessellations [PDF] 摘要

33. Real-Time Resource Allocation for Tracking Systems [PDF] 摘要

34. IS-CAM: Integrated Score-CAM for axiomatic-based explanations [PDF] 摘要

35. Global Self-Attention Networks for Image Recognition [PDF] 摘要

36. Online Action Detection in Streaming Videos with Time Buffers [PDF] 摘要

37. Motion Prediction Using Temporal Inception Module [PDF] 摘要

38. Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning [PDF] 摘要

39. Learning to Represent Image and Text with Denotation Graph [PDF] 摘要

40. Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win [PDF] 摘要

41. Discriminative Cross-Modal Data Augmentation for Medical Imaging Applications [PDF] 摘要

42. Deep Neural Network: An Efficient and Optimized Machine Learning Paradigm for Reducing Genome Sequencing Error [PDF] 摘要

43. Memory-efficient GAN-based Domain Translation of High Resolution 3D Medical Images [PDF] 摘要

44. Descriptive analysis of computational methods for automating mammograms with practical applications [PDF] 摘要

45. Secure 3D medical Imaging [PDF] 摘要

46. Batch Normalization Increases Adversarial Vulnerability: Disentangling Usefulness and Robustness of Model Features [PDF] 摘要

47. Double Targeted Universal Adversarial Perturbations [PDF] 摘要

48. Low-Rank Robust Online Distance/Similarity Learning based on the Rescaled Hinge Loss [PDF] 摘要

49. A Novel Face-tracking Mouth Controller and its Application to Interacting with Bioacoustic Models [PDF] 摘要

50. Deep Learning-Based Grading of Ductal Carcinoma In Situ in Breast Histopathology Images [PDF] 摘要

51. Sonification of Facial Actions for Musical Expression [PDF] 摘要

52. Designing, Playing, and Performing with a Vision-based Mouth Interface [PDF] 摘要

53. M3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening from CT Imaging [PDF] 摘要

54. WDN: A Wide and Deep Network to Divide-and-Conquer Image Super-resolution [PDF] 摘要

55. Conditional Generative Modeling via Learning the Latent Space [PDF] 摘要

56. A Fast and Effective Method of Macula Automatic Detection for Retina Images [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-08

发表于 2020-10-08 分类于 arxiv ， CL 93k 2:34

目录

1. Understanding Clinical Trial Reports:Extracting Medical Entities and Their Relations [PDF] 摘要

2. Probabilistic Case-based Reasoning for Open-World Knowledge Graph Completion [PDF] 摘要

3. Low-Resource Domain Adaptation for Compositional Task-Oriented Semantic Parsing [PDF] 摘要

4. Galileo at SemEval-2020 Task 12: Multi-lingual Learning for Offensive Language Identification using Pre-trained Language Models [PDF] 摘要

5. Exploring the Role of Argument Structure in Online Debate Persuasion [PDF] 摘要

6. What Can We Learn from Collective Human Opinions on Natural Language Inference Data? [PDF] 摘要

7. Inductive Entity Representations from Text via Link Prediction [PDF] 摘要

8. TeaForN: Teacher-Forcing with N-grams [PDF] 摘要

9. Improving Sentiment Analysis over non-English Tweets using Multilingual Transformers and Automatic Translation for Data-Augmentation [PDF] 摘要

10. ELMo and BERT in semantic change detection for Russian [PDF] 摘要

11. Learning a Cost-Effective Annotation Policy for Question Answering [PDF] 摘要

12. "I'd rather just go to bed": Understanding Indirect Answers [PDF] 摘要

13. Analogies minus analogy test: measuring regularities in word embeddings [PDF] 摘要

14. WER we are and WER we think we are [PDF] 摘要

15. Cross-lingual Extended Named Entity Classification of Wikipedia Articles [PDF] 摘要

16. Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation [PDF] 摘要

17. Why do you think that? Exploring Faithful Sentence-Level Rationales Without Supervision [PDF] 摘要

18. Toward Stance-based Personas for Opinionated Dialogues [PDF] 摘要

19. Improving QA Generalization by Concurrent Modeling of Multiple Biases [PDF] 摘要

20. COMETA: A Corpus for Medical Entity Linking in the Social Media [PDF] 摘要

21. ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization [PDF] 摘要

22. Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering [PDF] 摘要

23. Narrative Text Generation with a Latent Discrete Plan [PDF] 摘要

24. Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction [PDF] 摘要

25. Exploring and Evaluating Attributes, Values, and Structures for Entity Alignment [PDF] 摘要

26. Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields [PDF] 摘要

27. Unsupervised Evaluation for Question Answering with Transformers [PDF] 摘要

28. Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions [PDF] 摘要

29. Rank and run-time aware compression of NLP Applications [PDF] 摘要

30. Theedhum Nandrum@Dravidian-CodeMix-FIRE2020: ASentiment Polarity Classifier for YouTube Commentswith Code-switching between Tamil, Malayalam andEnglish [PDF] 摘要

31. Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages [PDF] 摘要

32. Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer [PDF] 摘要

33. Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases [PDF] 摘要

34. A Self-Refinement Strategy for Noise Reduction in Grammatical Error Correction [PDF] 摘要

35. Fortifying Toxic Speech Detectors Against Veiled Toxicity [PDF] 摘要

36. OpenIE6: Iterative Grid Labeling and Coordination Analysis for Open Information Extraction [PDF] 摘要

37. Unsupervised Parsing via Constituency Tests [PDF] 摘要

38. Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information [PDF] 摘要

39. Improving Context Modeling in Neural Topic Segmentation [PDF] 摘要

40. A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions [PDF] 摘要

41. VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling [PDF] 摘要

42. DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling [PDF] 摘要

43. Knowledge-aware Method for Confusing Charge Prediction [PDF] 摘要

44. WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization [PDF] 摘要

45. Is the Best Better? Bayesian Statistical Model Comparison for Natural Language Processing [PDF] 摘要

46. Beyond [CLS] through Ranking by Generation [PDF] 摘要

47. RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text [PDF] 摘要

48. Anubhuti -- An annotated dataset for emotional analysis of Bengali short stories [PDF] 摘要

49. A Survey on Recognizing Textual Entailment as an NLP Evaluation [PDF] 摘要

50. Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers [PDF] 摘要

51. Resource-Enhanced Neural Model for Event Argument Extraction [PDF] 摘要

52. On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment [PDF] 摘要

53. Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming [PDF] 摘要

54. GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extraction [PDF] 摘要

55. Fact Extraction and VERification -- The FEVER case: An Overview [PDF] 摘要

56. Compositional Demographic Word Embeddings [PDF] 摘要

57. Plug and Play Autoencoders for Conditional Text Generation [PDF] 摘要

58. Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces [PDF] 摘要

59. Supervised Seeded Iterated Learning for Interactive Language Learning [PDF] 摘要

60. A Self-supervised Approach for Semantic Indexing in the Context of COVID-19 Pandemic [PDF] 摘要

61. TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion [PDF] 摘要

62. Slice-Aware Neural Ranking [PDF] 摘要

63. Program Enhanced Fact Verification with Verbalization and Graph Attention Network [PDF] 摘要

64. Weakly-Supervised Feature Learning via Text and Image Matching [PDF] 摘要

65. Digital Voicing of Silent Speech [PDF] 摘要

66. Learning to Represent Image and Text with Denotation Graph [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-07

发表于 2020-10-07 更新于 2020-10-08 分类于 arxiv ， CV 92k 2:34

目录

1. SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction [PDF] 摘要

2. CORE: Color Regression for Multiple Colors Fashion Garments [PDF] 摘要

3. Support-set bottlenecks for video-text representation learning [PDF] 摘要

4. Microscopic fine-grained instance classification through deep attention [PDF] 摘要

5. Representation learning from videos in-the-wild: An object-centric approach [PDF] 摘要

6. Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters [PDF] 摘要

7. High Speed Event Camera TRacking [PDF] 摘要

8. Characterization of surface motion patterns in highly deformable soft tissue organs from dynamic Magnetic Resonance Imaging [PDF] 摘要

9. Assisted Probe Positioning for Ultrasound Guided Radiotherapy Using Image Sequence Classification [PDF] 摘要

10. Vec2Instance: Parameterization for Deep Instance Segmentation [PDF] 摘要

11. Parallax Motion Effect Generation Through Instance Segmentation And Depth Estimation [PDF] 摘要

12. A Method for Tumor Treating Fields Fast Estimation [PDF] 摘要

13. How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning [PDF] 摘要

14. Unfolding the Alternating Optimization for Blind Super Resolution [PDF] 摘要

15. Comprehensive Online Network Pruning via Learnable Scaling Factors [PDF] 摘要

16. Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering [PDF] 摘要

17. Arbitrary Style Transfer using Graph Instance Normalization [PDF] 摘要

18. Training Deep Neural Networks for Wireless Sensor Networks Using Loosely and Weakly Labeled Images [PDF] 摘要

19. Mapping of Sparse 3D Data using Alternating Projection [PDF] 摘要

20. Optimization over Random and Gradient Probabilistic Pixel Sampling for Fast, Robust Multi-Resolution Image Registration [PDF] 摘要

21. RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs [PDF] 摘要

22. Self-supervised Exposure Trajectory Recovery for Dynamic Blur Estimation [PDF] 摘要

23. Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track [PDF] 摘要

24. Visualizing Color-wise Saliency of Black-Box Image Classification Models [PDF] 摘要

25. Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays [PDF] 摘要

26. Collaboratively boosting data-driven deep learning and knowledge-guided ontological reasoning for semantic segmentation of remote sensing imagery [PDF] 摘要

27. Shot in the Dark: Few-Shot Learning with No Base-Class Labels [PDF] 摘要

28. Video Anomaly Detection Using Pre-Trained Deep Convolutional Neural Nets and Context Mining [PDF] 摘要

29. Adaptive Automotive Radar data Acquisition [PDF] 摘要

30. VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach [PDF] 摘要

31. Deep Generative Modelling of Human Reach-and-Place Action [PDF] 摘要

32. Multi-level Feature Learning on Embedding Layer of Convolutional Autoencoders and Deep Inverse Feature Learning for Image Clustering [PDF] 摘要

33. A Benchmark and Baseline for Language-Driven Image Editing [PDF] 摘要

34. Common CNN-based Face Embedding Spaces are (Almost) Equivalent [PDF] 摘要

35. Tensor Fields for Data Extraction from Chart Images: Bar Charts and Scatter Plots [PDF] 摘要

36. SMILE: Semantically-guided Multi-attribute Image and Layout Editing [PDF] 摘要

37. Smoother Network Tuning and Interpolation for Continuous-level Image Processing [PDF] 摘要

38. CO2: Consistent Contrast for Unsupervised Visual Representation Learning [PDF] 摘要

39. NCP-VAE: Variational Autoencoders with Noise Contrastive Priors [PDF] 摘要

40. Iterative Methods for Computing Eigenvectors of Nonlinear Operators [PDF] 摘要

41. LETI: Latency Estimation Tool and Investigation of Neural Networks inference on Mobile GPU [PDF] 摘要

42. COVIDomaly: A Deep Convolutional Autoencoder Approach for Detecting Early Cases of COVID-19 [PDF] 摘要

43. Image Translation for Medical Image Generation -- Ischemic Stroke Lesions [PDF] 摘要

44. Assessing Automated Machine Learning service to detect COVID-19 from X-Ray and CT images: A Real-time Smartphone Application case study [PDF] 摘要

45. Histopathological Stain Transfer using Style Transfer Network with Adversarial Loss [PDF] 摘要

46. PCAL: A Privacy-preserving Intelligent Credit Risk Modeling Framework Based on Adversarial Learning [PDF] 摘要

47. Adversarial Boot Camp: label free certified robustness in one epoch [PDF] 摘要

48. Denoising Diffusion Implicit Models [PDF] 摘要

49. Downscaling Attacks: What You See is Not What You Get [PDF] 摘要

50. The Effectiveness of Memory Replay in Large Scale Continual Learning [PDF] 摘要

51. ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution [PDF] 摘要

52. Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction [PDF] 摘要

53. Winning Lottery Tickets in Deep Generative Models [PDF] 摘要

54. Early Detection of Myocardial Infarction in Low-Quality Echocardiography [PDF] 摘要

55. Multi-Resolution 3D Convolutional Neural Networks for Automatic Coronary Centerline Extraction in Cardiac CT Angiography Scans [PDF] 摘要

阅读全文 »