October 16, 2019

2399 words 12 mins read

Paper Group NANR 43

Paper Group NANR 43

Automatic Assessment of Conceptual Text Complexity Using Knowledge Graphs. Joker at SemEval-2018 Task 12: The Argument Reasoning Comprehension with Neural Attention. Best Arm Identification in Linear Bandits with Linear Dimension Dependency. Matching Pixels Using Co-Occurrence Statistics. An Analysis of the Effect of Emotional Speech Synthesis on N …

Automatic Assessment of Conceptual Text Complexity Using Knowledge Graphs

Title Automatic Assessment of Conceptual Text Complexity Using Knowledge Graphs
Authors Sanja {\v{S}}tajner, Ioana Hulpu{\c{s}}
Abstract Complexity of texts is usually assessed only at the lexical and syntactic levels. Although it is known that conceptual complexity plays a significant role in text understanding, no attempts have been made at assessing it automatically. We propose to automatically estimate the conceptual complexity of texts by exploiting a number of graph-based measures on a large knowledge base. By using a high-quality language learners corpus for English, we show that graph-based measures of individual text concepts, as well as the way they relate to each other in the knowledge graph, have a high discriminative power when distinguishing between two versions of the same text. Furthermore, when used as features in a binary classification task aiming to choose the simpler of two versions of the same text, our measures achieve high performance even in a default setup.
Tasks Knowledge Graphs, Text Simplification
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1027/
PDF https://www.aclweb.org/anthology/C18-1027
PWC https://paperswithcode.com/paper/automatic-assessment-of-conceptual-text
Repo
Framework

Joker at SemEval-2018 Task 12: The Argument Reasoning Comprehension with Neural Attention

Title Joker at SemEval-2018 Task 12: The Argument Reasoning Comprehension with Neural Attention
Authors Guobin Sui, Wenhan Chao, Zhunchen Luo
Abstract This paper describes a classification system that participated in the SemEval-2018 Task 12: The Argument Reasoning Comprehension Task. Briefly the task can be described as that a natural language {``}argument{''} is what we have, with reason, claim, and correct and incorrect warrants, and we need to choose the correct warrant. In order to make fully understand of the semantic information of the sentences, we proposed a neural network architecture with attention mechanism to achieve this goal. Besides we try to introduce keywords into the model to improve accuracy. Finally the proposed system achieved 5th place among 22 participating systems |
Tasks Argument Mining, Stance Detection
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1191/
PDF https://www.aclweb.org/anthology/S18-1191
PWC https://paperswithcode.com/paper/joker-at-semeval-2018-task-12-the-argument
Repo
Framework

Best Arm Identification in Linear Bandits with Linear Dimension Dependency

Title Best Arm Identification in Linear Bandits with Linear Dimension Dependency
Authors Chao Tao, Saúl Blanco, Yuan Zhou
Abstract We study the best arm identification problem in linear bandits, where the mean reward of each arm depends linearly on an unknown $d$-dimensional parameter vector $\theta$, and the goal is to identify the arm with the largest expected reward. We first design and analyze a novel randomized $\theta$ estimator based on the solution to the convex relaxation of an optimal $G$-allocation experiment design problem. Using this estimator, we describe an algorithm whose sample complexity depends linearly on the dimension $d$, as well as an algorithm with sample complexity dependent on the reward gaps of the best $d$ arms, matching the lower bound arising from the ordinary top-arm identification problem. We finally compare the empirical performance of our algorithms with other state-of-the-art algorithms in terms of both sample complexity and computational time.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=1983
PDF http://proceedings.mlr.press/v80/tao18a/tao18a.pdf
PWC https://paperswithcode.com/paper/best-arm-identification-in-linear-bandits-1
Repo
Framework

Matching Pixels Using Co-Occurrence Statistics

Title Matching Pixels Using Co-Occurrence Statistics
Authors Rotal Kat, Roy Jevnisek, Shai Avidan
Abstract We propose a new error measure for matching pixels that is based on co-occurrence statistics. The measure relies on a co-occurrence matrix that counts the number of times pairs of pixel values co-occur within a window. The error incurred by matching a pair of pixels is inverse proportional to the probability that their values co-occur together, and not their color difference. This measure also works with features other than color, e.g. deep features. We show that this improves the state-of-the-art performance of template matching on standard benchmarks. We then propose an embedding scheme that maps the input image to an embedded image such that the Euclidean distance between pixel values in the embedded space resembles the co-occurrence statistics in the original space. This lets us run existing vision algorithms on the embedded images and enjoy the power of co-occurrence statistics for free. We demonstrate this on two algorithms, the Lucas-Kanade image registration and the Kernelized Correlation Filter (KCF) tracker. Experiments show that performance of each algorithm improves by about 10%.
Tasks Image Registration
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Kat_Matching_Pixels_Using_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Kat_Matching_Pixels_Using_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/matching-pixels-using-co-occurrence
Repo
Framework

An Analysis of the Effect of Emotional Speech Synthesis on Non-Task-Oriented Dialogue System

Title An Analysis of the Effect of Emotional Speech Synthesis on Non-Task-Oriented Dialogue System
Authors Yuya Chiba, Takashi Nose, Taketo Kase, Mai Yamanaka, Akinori Ito
Abstract This paper explores the effect of emotional speech synthesis on a spoken dialogue system when the dialogue is non-task-oriented. Although the use of emotional speech responses have been shown to be effective in a limited domain, e.g., scenario-based and counseling dialogue, the effect is still not clear in the non-task-oriented dialogue such as voice chatting. For this purpose, we constructed a simple dialogue system with example- and rule-based dialogue management. In the system, two types of emotion labeling with emotion estimation are adopted, i.e., system-driven and user-cooperative emotion labeling. We conducted a dialogue experiment where subjects evaluate the subjective quality of the system and the dialogue from the multiple aspects such as richness of the dialogue and impression of the agent. We then analyze and discuss the results and show the advantage of using appropriate emotions for the expressive speech responses in the non-task-oriented system.
Tasks Dialogue Management, Speech Synthesis, Spoken Dialogue Systems, Task-Oriented Dialogue Systems
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5044/
PDF https://www.aclweb.org/anthology/W18-5044
PWC https://paperswithcode.com/paper/an-analysis-of-the-effect-of-emotional-speech
Repo
Framework

Neural Networks with Block Diagonal Inner Product Layers

Title Neural Networks with Block Diagonal Inner Product Layers
Authors Amy Nesky, Quentin Stout
Abstract Artificial neural networks have opened up a world of possibilities in data science and artificial intelligence, but neural networks are cumbersome tools that grow with the complexity of the learning problem. We make contributions to this issue by considering a modified version of the fully connected layer we call a block diagonal inner product layer. These modified layers have weight matrices that are block diagonal, turning a single fully connected layer into a set of densely connected neuron groups. This idea is a natural extension of group, or depthwise separable, convolutional layers applied to the fully connected layers. Block diagonal inner product layers can be achieved by either initializing a purely block diagonal weight matrix or by iteratively pruning off diagonal block entries. This method condenses network storage and speeds up the run time without significant adverse effect on the testing accuracy, thus offering a new approach to improve network computation efficiency.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=HyI5ro0pW
PDF https://openreview.net/pdf?id=HyI5ro0pW
PWC https://paperswithcode.com/paper/neural-networks-with-block-diagonal-inner
Repo
Framework

THU_NGN at SemEval-2018 Task 10: Capturing Discriminative Attributes with MLP-CNN model

Title THU_NGN at SemEval-2018 Task 10: Capturing Discriminative Attributes with MLP-CNN model
Authors Chuhan Wu, Fangzhao Wu, Sixing Wu, Zhigang Yuan, Yongfeng Huang
Abstract Existing semantic models are capable of identifying the semantic similarity of words. However, it{'}s hard for these models to discriminate between a word and another similar word. Thus, the aim of SemEval-2018 Task 10 is to predict whether a word is a discriminative attribute between two concepts. In this task, we apply a multilayer perceptron (MLP)-convolutional neural network (CNN) model to identify whether an attribute is discriminative. The CNNs are used to extract low-level features from the inputs. The MLP takes both the flatten CNN maps and inputs to predict the labels. The evaluation F-score of our system on the test set is 0.629 (ranked 15th), which indicates that our system still needs to be improved. However, the behaviours of our system in our experiments provide useful information, which can help to improve the collective understanding of this novel task.
Tasks Semantic Similarity, Semantic Textual Similarity, Text Classification, Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1157/
PDF https://www.aclweb.org/anthology/S18-1157
PWC https://paperswithcode.com/paper/thu_ngn-at-semeval-2018-task-10-capturing
Repo
Framework

Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue

Title Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue
Authors
Abstract
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5000/
PDF https://www.aclweb.org/anthology/W18-5000
PWC https://paperswithcode.com/paper/proceedings-of-the-19th-annual-sigdial
Repo
Framework

Madly Ambiguous: A Game for Learning about Structural Ambiguity and Why It’s Hard for Computers

Title Madly Ambiguous: A Game for Learning about Structural Ambiguity and Why It’s Hard for Computers
Authors Ajda Gokcen, Ethan Hill, Michael White
Abstract Madly Ambiguous is an open source, online game aimed at teaching audiences of all ages about structural ambiguity and why it{'}s hard for computers. After a brief introduction to structural ambiguity, users are challenged to complete a sentence in a way that tricks the computer into guessing an incorrect interpretation. Behind the scenes are two different NLP-based methods for classifying the user{'}s input, one representative of classic rule-based approaches to disambiguation and the other representative of recent neural network approaches. Qualitative feedback from the system{'}s use in online, classroom, and science museum settings indicates that it is engaging and successful in conveying the intended take home messages. A demo of Madly Ambiguous can be played at \url{http://madlyambiguous.osu.edu}.
Tasks Prepositional Phrase Attachment, Text Generation
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-5011/
PDF https://www.aclweb.org/anthology/N18-5011
PWC https://paperswithcode.com/paper/madly-ambiguous-a-game-for-learning-about
Repo
Framework

Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation

Title Globally Optimal Inlier Set Maximization for Atlanta Frame Estimation
Authors Kyungdon Joo, Tae-Hyun Oh, In So Kweon, Jean-Charles Bazin
Abstract In this work, we describe man-made structures via an appropriate structure assumption, called Atlanta world, which contains a vertical direction (typically the gravity direction) and a set of horizontal directions orthogonal to the vertical direction. Contrary to the commonly used Manhattan world assumption, the horizontal directions in Atlanta world are not necessarily orthogonal to each other. While Atlanta world permits to encompass a wider range of scenes, this makes the solution space larger and the problem more challenging. Given a set of inputs, such as lines in a calibrated image or surface normals, we propose the first globally optimal method of inlier set maximization for Atlanta direction estimation. We define a novel search space for Atlanta world, as well as its parameterization, and solve this challenging problem by a branch-and-bound framework. Experimental results with synthetic and real-world datasets have successfully confirmed the validity of our approach.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Joo_Globally_Optimal_Inlier_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Joo_Globally_Optimal_Inlier_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/globally-optimal-inlier-set-maximization-for
Repo
Framework

The OSU Realizer for SRST `18: Neural Sequence-to-Sequence Inflection and Incremental Locality-Based Linearization

Title The OSU Realizer for SRST `18: Neural Sequence-to-Sequence Inflection and Incremental Locality-Based Linearization |
Authors David King, Michael White
Abstract Surface realization is a nontrivial task as it involves taking structured data and producing grammatically and semantically correct utterances. Many competing grammar-based and statistical models for realization still struggle with relatively simple sentences. For our submission to the 2018 Surface Realization Shared Task, we tackle the shallow task by first generating inflected wordforms with a neural sequence-to-sequence model before incrementally linearizing them. For linearization, we use a global linear model trained using early update that makes use of features that take into account the dependency structure and dependency locality. Using this pipeline sufficed to produce surprisingly strong results in the shared task. In future work, we intend to pursue joint approaches to linearization and morphological inflection and incorporating a neural language model into the linearization choices.
Tasks Language Modelling, Morphological Inflection
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3605/
PDF https://www.aclweb.org/anthology/W18-3605
PWC https://paperswithcode.com/paper/the-osu-realizer-for-srst-18-neural-sequence
Repo
Framework

Team UMBC-FEVER : Claim verification using Semantic Lexical Resources

Title Team UMBC-FEVER : Claim verification using Semantic Lexical Resources
Authors Ankur Padia, Francis Ferraro, Tim Finin
Abstract We describe our system used in the 2018 FEVER shared task. The system employed a frame-based information retrieval approach to select Wikipedia sentences providing evidence and used a two-layer multilayer perceptron to classify a claim as correct or not. Our submission achieved a score of 0.3966 on the Evidence F1 metric with accuracy of 44.79{%}, and FEVER score of 0.2628 F1 points.
Tasks Information Retrieval
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5527/
PDF https://www.aclweb.org/anthology/W18-5527
PWC https://paperswithcode.com/paper/team-umbc-fever-claim-verification-using
Repo
Framework

Automatic Essay Scoring Incorporating Rating Schema via Reinforcement Learning

Title Automatic Essay Scoring Incorporating Rating Schema via Reinforcement Learning
Authors Yucheng Wang, Zhongyu Wei, Yaqian Zhou, Xuanjing Huang
Abstract Automatic essay scoring (AES) is the task of assigning grades to essays without human interference. Existing systems for AES are typically trained to predict the score of each single essay at a time without considering the rating schema. In order to address this issue, we propose a reinforcement learning framework for essay scoring that incorporates quadratic weighted kappa as guidance to optimize the scoring system. Experiment results on benchmark datasets show the effectiveness of our framework.
Tasks Machine Translation, Relation Classification, Text Generation
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1090/
PDF https://www.aclweb.org/anthology/D18-1090
PWC https://paperswithcode.com/paper/automatic-essay-scoring-incorporating-rating
Repo
Framework

Exponentiated Strongly Rayleigh Distributions

Title Exponentiated Strongly Rayleigh Distributions
Authors Zelda E. Mariet, Suvrit Sra, Stefanie Jegelka
Abstract Strongly Rayleigh (SR) measures are discrete probability distributions over the subsets of a ground set. They enjoy strong negative dependence properties, as a result of which they assign higher probability to subsets of diverse elements. We introduce in this paper Exponentiated Strongly Rayleigh (ESR) measures, which sharpen (or smoothen) the negative dependence property of SR measures via a single parameter (the exponent) that can intuitively understood as an inverse temperature. We develop efficient MCMC procedures for approximate sampling from ESRs, and obtain explicit mixing time bounds for two concrete instances: exponentiated versions of Determinantal Point Processes and Dual Volume Sampling. We illustrate some of the potential of ESRs, by applying them to a few machine learning tasks; empirical results confirm that beyond their theoretical appeal, ESR-based models hold significant promise for these tasks.
Tasks Point Processes
Published 2018-12-01
URL http://papers.nips.cc/paper/7698-exponentiated-strongly-rayleigh-distributions
PDF http://papers.nips.cc/paper/7698-exponentiated-strongly-rayleigh-distributions.pdf
PWC https://paperswithcode.com/paper/exponentiated-strongly-rayleigh-distributions
Repo
Framework

Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models

Title Grotoco@SLAM: Second Language Acquisition Modeling with Simple Features, Learners and Task-wise Models
Authors Sigrid Klerke, H{'e}ctor Mart{'\i}nez Alonso, Barbara Plank
Abstract We present our submission to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM). We focus on evaluating a range of features for the task, including user-derived measures, while examining how far we can get with a simple linear classifier. Our analysis reveals that errors differ per exercise format, which motivates our final and best-performing system: a task-wise (per exercise-format) model.
Tasks Language Acquisition
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0523/
PDF https://www.aclweb.org/anthology/W18-0523
PWC https://paperswithcode.com/paper/grotocoslam-second-language-acquisition
Repo
Framework
comments powered by Disqus