January 24, 2020

2086 words 10 mins read

Paper Group NANR 198

Learning Exceptionality and Variation with Lexically Scaled MaxEnt. Hierarchical Nested Named Entity Recognition. Expanding English and Chinese Dictionaries by Wikipedia Titles. Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda. CLER: Cross-task Learning with Expert Re …

Learning Exceptionality and Variation with Lexically Scaled MaxEnt


Title	Learning Exceptionality and Variation with Lexically Scaled MaxEnt
Authors	Coral Hughto, Andrew Lamont, Br Prickett, on, Gaja Jarosz
Abstract
Tasks
Published	2019-01-01
URL	https://www.aclweb.org/anthology/W19-0110/
PDF	https://www.aclweb.org/anthology/W19-0110
PWC	https://paperswithcode.com/paper/learning-exceptionality-and-variation-with
Repo
Framework

Hierarchical Nested Named Entity Recognition


Title	Hierarchical Nested Named Entity Recognition
Authors	Zita Marinho, Afonso Mendes, Mir, Sebasti{~a}o a, David Nogueira
Abstract	In the medical domain and other scientific areas, it is often important to recognize different levels of hierarchy in mentions, such as those related to specific symptoms or diseases associated with different anatomical regions. Unlike previous approaches, we build a transition-based parser that explicitly models an arbitrary number of hierarchical and nested mentions, and propose a loss that encourages correct predictions of higher-level mentions. We further introduce a set of modifier classes which introduces certain concepts that change the meaning of an entity, such as absence, or uncertainty about a given disease. Our proposed model achieves state-of-the-art results in medical entity recognition datasets, using both nested and hierarchical mentions.
Tasks	Named Entity Recognition, Nested Named Entity Recognition
Published	2019-06-01
URL	https://www.aclweb.org/anthology/W19-1904/
PDF	https://www.aclweb.org/anthology/W19-1904
PWC	https://paperswithcode.com/paper/hierarchical-nested-named-entity-recognition
Repo
Framework

Expanding English and Chinese Dictionaries by Wikipedia Titles


Title	Expanding English and Chinese Dictionaries by Wikipedia Titles
Authors	Wei-Ting Chen, Yu-Te Wang, Chuan-Jie Lin
Abstract
Tasks
Published	2019-09-01
URL	https://www.aclweb.org/anthology/W19-7415/
PDF	https://www.aclweb.org/anthology/W19-7415
PWC	https://paperswithcode.com/paper/expanding-english-and-chinese-dictionaries-by
Repo
Framework

Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda


Title	Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda
Authors
Abstract
Tasks
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-5000/
PDF	https://www.aclweb.org/anthology/D19-5000
PWC	https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-natural-2
Repo
Framework

CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding


Title	CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding
Authors	Takumi Takahashi, Motoki Taniguchi, Tomoki Taniguchi, Tomoko Ohkuma
Abstract	This paper describes our model for the reading comprehension task of the MRQA shared task. We propose CLER, which stands for Cross-task Learning with Expert Representation for the generalization of reading and understanding. To generalize its capabilities, the proposed model is composed of three key ideas: multi-task learning, mixture of experts, and ensemble. In-domain datasets are used to train and validate our model, and other out-of-domain datasets are used to validate the generalization of our model{'}s performances. In a submission run result, the proposed model achieved an average F1 score of 66.1 {%} in the out-of-domain setting, which is a 4.3 percentage point improvement over the official BERT baseline model.
Tasks	Multi-Task Learning, Reading Comprehension
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-5824/
PDF	https://www.aclweb.org/anthology/D19-5824
PWC	https://paperswithcode.com/paper/cler-cross-task-learning-with-expert
Repo
Framework

KARNA at COIN Shared Task 1: Bidirectional Encoder Representations from Transformers with relational knowledge for machine comprehension with common sense


Title	KARNA at COIN Shared Task 1: Bidirectional Encoder Representations from Transformers with relational knowledge for machine comprehension with common sense
Authors	Yash Jain, Chinmay Singh
Abstract	This paper describes our model for COmmonsense INference in Natural Language Processing (COIN) shared task 1: Commonsense Inference in Everyday Narrations. This paper explores the use of Bidirectional Encoder Representations from Transformers(BERT) along with external relational knowledge from ConceptNet to tackle the problem of commonsense inference. The input passage, question, and answer are augmented with relational knowledge from ConceptNet. Using this technique we are able to achieve an accuracy of 73.3 {%} on the official test data.
Tasks	Common Sense Reasoning, Reading Comprehension
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-6008/
PDF	https://www.aclweb.org/anthology/D19-6008
PWC	https://paperswithcode.com/paper/karna-at-coin-shared-task-1-bidirectional
Repo
Framework

IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension


Title	IIT-KGP at COIN 2019: Using pre-trained Language Models for modeling Machine Comprehension
Authors	Prakhar Sharma, Sumegh Roychowdhury
Abstract	In this paper, we describe our system for COIN 2019 Shared Task 1: Commonsense Inference in Everyday Narrations. We show the power of leveraging state-of-the-art pre-trained language models such as BERT(Bidirectional Encoder Representations from Transformers) and XLNet over other Commonsense Knowledge Base Resources such as ConceptNet and NELL for modeling machine comprehension. We used an ensemble of BERT-Large and XLNet-Large. Experimental results show that our model give substantial improvements over the baseline and other systems incorporating knowledge bases. We bagged 2nd position on the final test set leaderboard with an accuracy of 90.5{%}
Tasks	Reading Comprehension
Published	2019-11-01
URL	https://www.aclweb.org/anthology/D19-6009/
PDF	https://www.aclweb.org/anthology/D19-6009
PWC	https://paperswithcode.com/paper/iit-kgp-at-coin-2019-using-pre-trained
Repo
Framework

Cross-Modality Personalization for Retrieval


Title	Cross-Modality Personalization for Retrieval
Authors	Nils Murrugarra-Llerena, Adriana Kovashka
Abstract	Existing captioning and gaze prediction approaches do not consider the multiple facets of personality that affect how a viewer extracts meaning from an image. While there are methods that consider personalized captioning, they do not consider personalized perception across modalities, i.e. how a person’s way of looking at an image (gaze) affects the way they describe it (captioning). In this work, we propose a model for modeling cross-modality personalized retrieval. In addition to modeling gaze and captions, we also explicitly model the personality of the users providing these samples. We incorporate constraints that encourage gaze and caption samples on the same image to be close in a learned space; we refer to this as content modeling. We also model style: we encourage samples provided by the same user to be close in a separate embedding space, regardless of the image on which they were provided. To leverage the complementary information that content and style constraints provide, we combine the embeddings from both networks. We show that our combined embeddings achieve better performance than existing approaches for cross-modal retrieval.
Tasks	Cross-Modal Retrieval, Gaze Prediction
Published	2019-06-01
URL	http://openaccess.thecvf.com/content_CVPR_2019/html/Murrugarra-Llerena_Cross-Modality_Personalization_for_Retrieval_CVPR_2019_paper.html
PDF	http://openaccess.thecvf.com/content_CVPR_2019/papers/Murrugarra-Llerena_Cross-Modality_Personalization_for_Retrieval_CVPR_2019_paper.pdf
PWC	https://paperswithcode.com/paper/cross-modality-personalization-for-retrieval
Repo
Framework

AI Werewolf Agent with Reasoning Using Role Patterns and Heuristics


Title	AI Werewolf Agent with Reasoning Using Role Patterns and Heuristics
Authors	Issei Tsunoda, Yoshinobu Kano
Abstract
Tasks
Published	2019-10-01
URL	https://www.aclweb.org/anthology/W19-8303/
PDF	https://www.aclweb.org/anthology/W19-8303
PWC	https://paperswithcode.com/paper/ai-werewolf-agent-with-reasoning-using-role
Repo
Framework

WUT at SemEval-2019 Task 9: Domain-Adversarial Neural Networks for Domain Adaptation in Suggestion Mining


Title	WUT at SemEval-2019 Task 9: Domain-Adversarial Neural Networks for Domain Adaptation in Suggestion Mining
Authors	Mateusz Klimaszewski, Piotr Andruszkiewicz
Abstract	We present a system for cross-domain suggestion mining, prepared for the SemEval-2019 Task 9: Suggestion Mining from Online Reviews and Forums (Subtask B). Our submitted solution for this text classification problem explores the idea of treating different suggestions{'} sources as one of the settings of Transfer Learning - Domain Adaptation. Our experiments show that without any labeled target domain examples during training time, we are capable of proposing a system, reaching up to 0.778 in terms of F1 score on test dataset, based on Target Preserving Domain Adversarial Neural Networks.
Tasks	Domain Adaptation, Text Classification, Transfer Learning
Published	2019-06-01
URL	https://www.aclweb.org/anthology/S19-2221/
PDF	https://www.aclweb.org/anthology/S19-2221
PWC	https://paperswithcode.com/paper/wut-at-semeval-2019-task-9-domain-adversarial
Repo
Framework

Identifying Grammar Rules for Language Education with Dependency Parsing in German


Title	Identifying Grammar Rules for Language Education with Dependency Parsing in German
Authors	Eleni Metheniti, Pomi Park, Kristina Kolesova, G{"u}nter Neumann
Abstract
Tasks	Dependency Parsing
Published	2019-08-01
URL	https://www.aclweb.org/anthology/W19-7712/
PDF	https://www.aclweb.org/anthology/W19-7712
PWC	https://paperswithcode.com/paper/identifying-grammar-rules-for-language
Repo
Framework

Attention-Based Autism Spectrum Disorder Screening With Privileged Modality


Title	Attention-Based Autism Spectrum Disorder Screening With Privileged Modality
Authors	Shi Chen, Qi Zhao
Abstract	This paper presents a novel framework for automatic and quantitative screening of autism spectrum disorder (ASD). It is motivated to address two issues in the current clinical settings: 1) short of clinical resources with the prevalence of ASD (1.7% in the United States), and 2) subjectivity of ASD screening. This work differentiates itself with three unique features: first, it proposes an ASD screening with privileged modality framework that integrates information from two behavioral modalities during training and improves the performance on each single modality at testing. The proposed framework does not require overlap in subjects between the modalities. Second, it develops the first computational model to classify people with ASD using a photo-taking task where subjects freely explore their environment in a more ecological setting. Photo-taking reveals attentional preference of subjects, differentiating people with ASD from healthy people, and is also easy to implement in real-world clinical settings without requiring advanced diagnostic instruments. Third, this study for the first time takes advantage of the temporal information in eye movements while viewing images, encoding more detailed behavioral differences between ASD people and healthy controls. Experiments show that our ASD screening models can achieve superior performance, outperforming the previous state-of-the-art methods by a considerable margin. Moreover, our framework using diverse modalities demonstrates performance improvement on both the photo-taking and image-viewing tasks, providing a general paradigm that takes in multiple sources of behavioral data for a more accurate ASD screening. The framework is also applicable to various scenarios where one-to-one pairwise relationship is difficult to obtain across different modalities.
Tasks
Published	2019-10-01
URL	http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Attention-Based_Autism_Spectrum_Disorder_Screening_With_Privileged_Modality_ICCV_2019_paper.html
PDF	http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Attention-Based_Autism_Spectrum_Disorder_Screening_With_Privileged_Modality_ICCV_2019_paper.pdf
PWC	https://paperswithcode.com/paper/attention-based-autism-spectrum-disorder
Repo
Framework

Learning to encode spatial relations from natural language


Title	Learning to encode spatial relations from natural language
Authors	Tiago Ramalho, Tomas Kocisky‎, Frederic Besse, S. M. Ali Eslami, Gabor Melis, Fabio Viola, Phil Blunsom, Karl Moritz Hermann
Abstract	Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the real world. In particular, spatial relations are encoded in a way that is inconsistent with human spatial reasoning and lacking invariance to viewpoint changes. We present a system capable of capturing the semantics of spatial relations such as behind, left of, etc from natural language. Our key contributions are a novel multi-modal objective based on generating images of scenes from their textual descriptions, and a new dataset on which to train it. We demonstrate that internal representations are robust to meaning preserving transformations of descriptions (paraphrase invariance), while viewpoint invariance is an emergent property of the system.
Tasks
Published	2019-05-01
URL	https://openreview.net/forum?id=BJG__i0qF7
PDF	https://openreview.net/pdf?id=BJG__i0qF7
PWC	https://paperswithcode.com/paper/learning-to-encode-spatial-relations-from
Repo
Framework

Data Representation and Learning With Graph Diffusion-Embedding Networks


Title	Data Representation and Learning With Graph Diffusion-Embedding Networks
Authors	Bo Jiang, Doudou Lin, Jin Tang, Bin Luo
Abstract	Recently, graph convolutional neural networks have been widely studied for graph-structured data representation and learning. In this paper, we present Graph Diffusion-Embedding networks (GDENs), a new model for graph-structured data representation and learning. GDENs are motivated by our development of graph based feature diffusion. GDENs integrate both feature diffusion and graph node (low-dimensional) embedding simultaneously into a unified network by employing a novel diffusion-embedding architecture. GDENs have two main advantages. First, the equilibrium representation of the diffusion-embedding operation in GDENs can be obtained via a simple closed-form solution, which thus guarantees the compactivity and efficiency of GDENs. Second, the proposed GDENs can be naturally extended to address the data with multiple graph structures. Experiments on various semi-supervised learning tasks on several benchmark datasets demonstrate that the proposed GDENs significantly outperform traditional graph convolutional networks.
Tasks
Published	2019-06-01
URL	http://openaccess.thecvf.com/content_CVPR_2019/html/Jiang_Data_Representation_and_Learning_With_Graph_Diffusion-Embedding_Networks_CVPR_2019_paper.html
PDF	http://openaccess.thecvf.com/content_CVPR_2019/papers/Jiang_Data_Representation_and_Learning_With_Graph_Diffusion-Embedding_Networks_CVPR_2019_paper.pdf
PWC	https://paperswithcode.com/paper/data-representation-and-learning-with-graph
Repo
Framework

Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach


Title	Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach
Authors	Minhao Cheng, Thong Le, Pin-Yu Chen, Huan Zhang, JinFeng Yi, Cho-Jui Hsieh
Abstract	We study the problem of attacking machine learning models in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to probe the corresponding hard-label decisions. This is a very challenging problem since the direct extension of state-of-the-art white-box attacks (e.g., C&W or PGD) to the hard-label black-box setting will require minimizing a non-continuous step function, which is combinatorial and cannot be solved by a gradient-based optimizer. The only two current approaches are based on random walk on the boundary (Brendel et al., 2017) and random trials to evaluate the loss function (Ilyas et al., 2018), which require lots of queries and lacks convergence guarantees. We propose a novel way to formulate the hard-label black-box attack as a real-valued optimization problem which is usually continuous and can be solved by any zeroth order optimization algorithm. For example, using the Randomized Gradient-Free method (Nesterov & Spokoiny, 2017), we are able to bound the number of iterations needed for our algorithm to achieve stationary points under mild assumptions. We demonstrate that our proposed method outperforms the previous stochastic approaches to attacking convolutional neural networks on MNIST, CIFAR, and ImageNet datasets. More interestingly, we show that the proposed algorithm can also be used to attack other discrete and non-continuous machine learning models, such as Gradient Boosting Decision Trees (GBDT).
Tasks
Published	2019-05-01
URL	https://openreview.net/forum?id=rJlk6iRqKX
PDF	https://openreview.net/pdf?id=rJlk6iRqKX
PWC	https://paperswithcode.com/paper/query-efficient-hard-label-black-box-attack
Repo
Framework