October 15, 2019

2155 words 11 mins read

Paper Group NANR 272

Paper Group NANR 272

UMBC at SemEval-2018 Task 8: Understanding Text about Malware. Flytxt_NTNU at SemEval-2018 Task 8: Identifying and Classifying Malware Text Using Conditional Random Fields and Na"\ive Bayes Classifiers. Digital Operatives at SemEval-2018 Task 8: Using dependency features for malware NLP. Towards a Diagnosis of Textual Difficulties for Children wi …

UMBC at SemEval-2018 Task 8: Understanding Text about Malware

Title UMBC at SemEval-2018 Task 8: Understanding Text about Malware
Authors Ankur Padia, Arpita Roy, Taneeya Satyapanich, Francis Ferraro, Shimei Pan, Youngja Park, Anupam Joshi, Tim Finin
Abstract We describe the systems developed by the UMBC team for 2018 SemEval Task 8, SecureNLP (Semantic Extraction from CybersecUrity REports using Natural Language Processing). We participated in three of the sub-tasks: (1) classifying sentences as being relevant or irrelevant to malware, (2) predicting token labels for sentences, and (4) predicting attribute labels from the Malware Attribute Enumeration and Characterization vocabulary for defining malware characteristics. We achieve F1 score of 50.34/18.0 (dev/test), 22.23 (test-data), and 31.98 (test-data) for Task1, Task2 and Task2 respectively. We also make our cybersecurity embeddings publicly available at \url{http://bit.ly/cyber2vec}.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1142/
PDF https://www.aclweb.org/anthology/S18-1142
PWC https://paperswithcode.com/paper/umbc-at-semeval-2018-task-8-understanding
Repo
Framework

Flytxt_NTNU at SemEval-2018 Task 8: Identifying and Classifying Malware Text Using Conditional Random Fields and Na"\ive Bayes Classifiers

Title Flytxt_NTNU at SemEval-2018 Task 8: Identifying and Classifying Malware Text Using Conditional Random Fields and Na"\ive Bayes Classifiers
Authors Utpal Kumar Sikdar, Biswanath Barik, Bj{"o}rn Gamb{"a}ck
Abstract Cybersecurity risks such as malware threaten the personal safety of users, but to identify malware text is a major challenge. The paper proposes a supervised learning approach to identifying malware sentences given a document (subTask1 of SemEval 2018, Task 8), as well as to classifying malware tokens in the sentences (subTask2). The approach achieved good results, ranking second of twelve participants for both subtasks, with F-scores of 57{%} for subTask1 and 28{%} for subTask2.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1144/
PDF https://www.aclweb.org/anthology/S18-1144
PWC https://paperswithcode.com/paper/flytxt_ntnu-at-semeval-2018-task-8
Repo
Framework

Digital Operatives at SemEval-2018 Task 8: Using dependency features for malware NLP

Title Digital Operatives at SemEval-2018 Task 8: Using dependency features for malware NLP
Authors Chris Brew
Abstract The four sub-tasks of SecureNLP build towards a capability for quickly highlighting critical information from malware reports, such as the specific actions taken by a malware sample. Digital Operatives (DO) submitted to sub-tasks 1 and 2, using standard text analysis technology (text classification for sub-task 1, and a CRF for sub-task 2). Performance is broadly competitive with other submitted systems on sub-task 1 and weak on sub-task 2. The annotation guidelines for the intermediate sub-tasks create a linkage to the final task, which is both an annotation challenge and a potentially useful feature of the task. The methods that DO chose do not attempt to make use of this linkage, which may be a missed opportunity. This motivates a post-hoc error analysis. It appears that the annotation task is very hard, and that in some cases both deep conceptual knowledge and substantial surrounding context are needed in order to correctly classify sentences.
Tasks Text Classification
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1145/
PDF https://www.aclweb.org/anthology/S18-1145
PWC https://paperswithcode.com/paper/digital-operatives-at-semeval-2018-task-8
Repo
Framework

Towards a Diagnosis of Textual Difficulties for Children with Dyslexia

Title Towards a Diagnosis of Textual Difficulties for Children with Dyslexia
Authors Solen Quiniou, B{'e}atrice Daille
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1056/
PDF https://www.aclweb.org/anthology/L18-1056
PWC https://paperswithcode.com/paper/towards-a-diagnosis-of-textual-difficulties
Repo
Framework

Kalman Normalization: Normalizing Internal Representations Across Network Layers

Title Kalman Normalization: Normalizing Internal Representations Across Network Layers
Authors Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang, Liang Lin
Abstract As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hidden layer. However, the effectiveness of BN would diminish with the scenario of micro-batch (e.g. less than 4 samples in a mini-batch), since the estimated statistics in a mini-batch are not reliable with insufficient samples. This limits BN’s room in training larger models on segmentation, detection, and video-related problems, which require small batches constrained by memory consumption. In this paper, we present a novel normalization method, called Kalman Normalization (KN), for improving and accelerating the training of DNNs, particularly under the context of micro-batches. Specifically, unlike the existing solutions treating each hidden layer as an isolated system, KN treats all the layers in a network as a whole system, and estimates the statistics of a certain layer by considering the distributions of all its preceding layers, mimicking the merits of Kalman Filtering. On ResNet50 trained in ImageNet, KN has 3.4% lower error than its BN counterpart when using a batch size of 4; Even when using typical batch sizes, KN still maintains an advantage over BN while other BN variants suffer a performance degradation. Moreover, KN can be naturally generalized to many existing normalization variants to obtain gains, e.g. equipping Group Normalization with Group Kalman Normalization (GKN). KN can outperform BN and its variants for large scale object detection and segmentation task in COCO 2017.
Tasks Object Detection
Published 2018-12-01
URL http://papers.nips.cc/paper/7288-kalman-normalization-normalizing-internal-representations-across-network-layers
PDF http://papers.nips.cc/paper/7288-kalman-normalization-normalizing-internal-representations-across-network-layers.pdf
PWC https://paperswithcode.com/paper/kalman-normalization-normalizing-internal
Repo
Framework

EXPR at SemEval-2018 Task 9: A Combined Approach for Hypernym Discovery

Title EXPR at SemEval-2018 Task 9: A Combined Approach for Hypernym Discovery
Authors Ahmad Issa Alaa Aldine, Mounira Harzallah, Giuseppe Berio, Nicolas B{'e}chet, Ahmad Faour
Abstract In this paper, we present our proposed system (EXPR) to participate in the hypernym discovery task of SemEval 2018. The task addresses the challenge of discovering hypernym relations from a text corpus. Our proposal is a combined approach of path-based technique and distributional technique. We use dependency parser on a corpus to extract candidate hypernyms and represent their dependency paths as a feature vector. The feature vector is concatenated with a feature vector obtained using Wikipedia pre-trained term embedding model. The concatenated feature vector fits a supervised machine learning method to learn a classifier model. This model is able to classify new candidate hypernyms as hypernym or not. Our system performs well to discover new hypernyms not defined in gold hypernyms.
Tasks Hypernym Discovery, Information Retrieval, Machine Translation, Question Answering
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1150/
PDF https://www.aclweb.org/anthology/S18-1150
PWC https://paperswithcode.com/paper/expr-at-semeval-2018-task-9-a-combined
Repo
Framework

Generating Description for Sequential Images with Local-Object Attention Conditioned on Global Semantic Context

Title Generating Description for Sequential Images with Local-Object Attention Conditioned on Global Semantic Context
Authors Jing Su, Chenghua Lin, Mian Zhou, Qingyun Dai, Haoyu Lv
Abstract
Tasks Image Captioning, Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6702/
PDF https://www.aclweb.org/anthology/W18-6702
PWC https://paperswithcode.com/paper/generating-description-for-sequential-images
Repo
Framework

Deep Density Clustering of Unconstrained Faces

Title Deep Density Clustering of Unconstrained Faces
Authors Wei-An Lin, Jun-Cheng Chen, Carlos D. Castillo, Rama Chellappa
Abstract In this paper, we consider the problem of grouping a collection of unconstrained face images in which the number of subjects is not known. We propose an unsupervised clustering algorithm called Deep Density Clustering (DDC) which is based on measuring density affinities between local neighborhoods in the feature space. By learning the minimal covering sphere for each neighborhood, information about the underlying structure is encapsulated. The encapsulation is also capable of locating high-density region of the neighborhood, which aids in measuring the neighborhood similarity. We theoretically show that the encapsulation asymptotically converges to a Parzen window density estimator. Our experiments show that DDC is a superior candidate for clustering unconstrained faces when the number of subjects is unknown. Unlike conventional linkage and density-based methods that are sensitive to the selection operating points, DDC attains more consistent and improved performance. Furthermore, the density-aware property reduces the difficulty in finding appropriate operating points.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Lin_Deep_Density_Clustering_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Lin_Deep_Density_Clustering_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/deep-density-clustering-of-unconstrained
Repo
Framework

Automatic Identification of Maghreb Dialects Using a Dictionary-Based Approach

Title Automatic Identification of Maghreb Dialects Using a Dictionary-Based Approach
Authors Houda Sa{^a}dane, Hosni Seffih, Christian Fluhr, Khalid Choukri, Nasredine Semmar
Abstract
Tasks Information Retrieval, Language Identification, Machine Translation, Transliteration
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1575/
PDF https://www.aclweb.org/anthology/L18-1575
PWC https://paperswithcode.com/paper/automatic-identification-of-maghreb-dialects
Repo
Framework

Discovering Parallel Language Resources for Training MT Engines

Title Discovering Parallel Language Resources for Training MT Engines
Authors Vassilis Papavassiliou, Prokopis Prokopidis, Stelios Piperidis
Abstract
Tasks Language Identification, Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1599/
PDF https://www.aclweb.org/anthology/L18-1599
PWC https://paperswithcode.com/paper/discovering-parallel-language-resources-for
Repo
Framework

Meaning_space at SemEval-2018 Task 10: Combining explicitly encoded knowledge with information extracted from word embeddings

Title Meaning_space at SemEval-2018 Task 10: Combining explicitly encoded knowledge with information extracted from word embeddings
Authors Pia Sommerauer, Antske Fokkens, Piek Vossen
Abstract This paper presents the two systems submitted by the meaning space team in Task 10 of the SemEval competition 2018 entitled Capturing discriminative attributes. The systems consist of combinations of approaches exploiting explicitly encoded knowledge about concepts in WordNet and information encoded in distributional semantic vectors. Rather than aiming for high performance, we explore which kind of semantic knowledge is best captured by different methods. The results indicate that WordNet glosses on different levels of the hierarchy capture many attributes relevant for this task. In combination with exploiting word embedding similarities, this source of information yielded our best results. Our best performing system ranked 5th out of 13 final ranks. Our analysis yields insights into the different kinds of attributes represented by different sources of knowledge.
Tasks Semantic Textual Similarity, Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1154/
PDF https://www.aclweb.org/anthology/S18-1154
PWC https://paperswithcode.com/paper/meaning_space-at-semeval-2018-task-10
Repo
Framework

CitiusNLP at SemEval-2018 Task 10: The Use of Transparent Distributional Models and Salient Contexts to Discriminate Word Attributes

Title CitiusNLP at SemEval-2018 Task 10: The Use of Transparent Distributional Models and Salient Contexts to Discriminate Word Attributes
Authors Pablo Gamallo
Abstract This article describes the unsupervised strategy submitted by the CitiusNLP team to the SemEval 2018 Task 10, a task which consists of predict whether a word is a discriminative attribute between two other words. Our strategy relies on the correspondence between discriminative attributes and relevant contexts of a word. More precisely, the method uses transparent distributional models to extract salient contexts of words which are identified as discriminative attributes. The system performance reaches about 70{%} accuracy when it is applied on the development dataset, but its accuracy goes down (63{%}) on the official test dataset.
Tasks Dimensionality Reduction
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1156/
PDF https://www.aclweb.org/anthology/S18-1156
PWC https://paperswithcode.com/paper/citiusnlp-at-semeval-2018-task-10-the-use-of
Repo
Framework

ELiRF-UPV at SemEval-2018 Task 10: Capturing Discriminative Attributes with Knowledge Graphs and Wikipedia

Title ELiRF-UPV at SemEval-2018 Task 10: Capturing Discriminative Attributes with Knowledge Graphs and Wikipedia
Authors Jos{'e}-{'A}ngel Gonz{'a}lez, Llu{'\i}s-F. Hurtado, Encarna Segarra, Ferran Pla
Abstract This paper describes the participation of ELiRF-UPV team at task 10, Capturing Discriminative Attributes, of SemEval-2018. Our best approach consists of using ConceptNet, Wikipedia and NumberBatch embeddings in order to stablish relationships between concepts and attributes. Furthermore, this system achieves competitive results in the official evaluation.
Tasks Knowledge Graphs
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1159/
PDF https://www.aclweb.org/anthology/S18-1159
PWC https://paperswithcode.com/paper/elirf-upv-at-semeval-2018-task-10-capturing
Repo
Framework

NerveNet: Learning Structured Policy with Graph Neural Networks

Title NerveNet: Learning Structured Policy with Graph Neural Networks
Authors Tingwu Wang, Renjie Liao, Jimmy Ba, Sanja Fidler
Abstract We address the problem of learning structured policies for continuous control. In traditional reinforcement learning, policies of agents are learned by MLPs which take the concatenation of all observations from the environment as input for predicting actions. In this work, we propose NerveNet to explicitly model the structure of an agent, which naturally takes the form of a graph. Specifically, serving as the agent’s policy network, NerveNet first propagates information over the structure of the agent and then predict actions for different parts of the agent. In the experiments, we first show that our NerveNet is comparable to state-of-the-art methods on standard MuJoCo environments. We further propose our customized reinforcement learning environments for benchmarking two types of structure transfer learning tasks, i.e., size and disability transfer. We demonstrate that policies learned by NerveNet are significantly better than policies learned by other models and are able to transfer even in a zero-shot setting.
Tasks Continuous Control, Transfer Learning
Published 2018-01-01
URL https://openreview.net/forum?id=S1sqHMZCb
PDF https://openreview.net/pdf?id=S1sqHMZCb
PWC https://paperswithcode.com/paper/nervenet-learning-structured-policy-with
Repo
Framework

Realtime query completion via deep language models

Title Realtime query completion via deep language models
Authors Po-Wei Wang, J. Zico Kolter, Vijai Mohan, Inderjit S. Dhillon
Abstract Search engine users nowadays heavily depend on query completion and correction to shape their queries. Typically, the completion is done by database lookup which does not understand the context and cannot generalize to prefixes not in the database. In the paper, we propose to use unsupervised deep language models to complete and correct the queries given an arbitrary prefix. We show how to address two main challenges that renders this method practical for large-scale deployment: 1) we propose a method for integrating error correction into the language model completion via a edit-distance potential and a variant of beam search that can exploit these potential functions; and 2) we show how to efficiently perform CPU-based computation to complete the queries, with error correction, in real time (generating top 10 completions within 16 ms). Experiments show that the method substantially increases hit rate over standard approaches, and is capable of handling tail queries.
Tasks Language Modelling
Published 2018-01-01
URL https://openreview.net/forum?id=By3VrbbAb
PDF https://openreview.net/pdf?id=By3VrbbAb
PWC https://paperswithcode.com/paper/realtime-query-completion-via-deep-language
Repo
Framework
comments powered by Disqus