October 15, 2019

1992 words 10 mins read

Paper Group NANR 121

Paper Group NANR 121

Discovering Phonesthemes with Sparse Regularization. Proceedings of the 22nd Conference on Computational Natural Language Learning. Proceedings of the 5th Workshop on Argument Mining. Grapheme-level Awareness in Word Embeddings for Morphologically Rich Languages. TakeLab at SemEval-2018 Task 7: Combining Sparse and Dense Features for Relation Class …

Discovering Phonesthemes with Sparse Regularization

Title Discovering Phonesthemes with Sparse Regularization
Authors Nelson F. Liu, Gina-Anne Levow, Noah A. Smith
Abstract We introduce a simple method for extracting non-arbitrary form-meaning representations from a collection of semantic vectors. We treat the problem as one of feature selection for a model trained to predict word vectors from subword features. We apply this model to the problem of automatically discovering phonesthemes, which are submorphemic sound clusters that appear in words with similar meaning. Many of our model-predicted phonesthemes overlap with those proposed in the linguistics literature, and we validate our approach with human judgments.
Tasks Feature Selection
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1206/
PDF https://www.aclweb.org/anthology/W18-1206
PWC https://paperswithcode.com/paper/discovering-phonesthemes-with-sparse
Repo
Framework

Proceedings of the 22nd Conference on Computational Natural Language Learning

Title Proceedings of the 22nd Conference on Computational Natural Language Learning
Authors
Abstract
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-1000/
PDF https://www.aclweb.org/anthology/K18-1000
PWC https://paperswithcode.com/paper/proceedings-of-the-22nd-conference-on
Repo
Framework

Proceedings of the 5th Workshop on Argument Mining

Title Proceedings of the 5th Workshop on Argument Mining
Authors
Abstract
Tasks Argument Mining
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5200/
PDF https://www.aclweb.org/anthology/W18-5200
PWC https://paperswithcode.com/paper/proceedings-of-the-5th-workshop-on-argument
Repo
Framework

Grapheme-level Awareness in Word Embeddings for Morphologically Rich Languages

Title Grapheme-level Awareness in Word Embeddings for Morphologically Rich Languages
Authors Suzi Park, Hyopil Shin
Abstract
Tasks Word Embeddings
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1471/
PDF https://www.aclweb.org/anthology/L18-1471
PWC https://paperswithcode.com/paper/grapheme-level-awareness-in-word-embeddings
Repo
Framework

TakeLab at SemEval-2018 Task 7: Combining Sparse and Dense Features for Relation Classification in Scientific Texts

Title TakeLab at SemEval-2018 Task 7: Combining Sparse and Dense Features for Relation Classification in Scientific Texts
Authors Martin Gluhak, Maria Pia di Buono, Abbas Akkasi, Jan {\v{S}}najder
Abstract We describe two systems for semantic relation classification with which we participated in the SemEval 2018 Task 7, subtask 1 on semantic relation classification: an SVM model and a CNN model. Both models combine dense pretrained word2vec features and hancrafted sparse features. For training the models, we combine the two datasets provided for the subtasks in order to balance the under-represented classes. The SVM model performed better than CNN, achieving a F1-macro score of 69.98{%} on subtask 1.1 and 75.69{%} on subtask 1.2. The system ranked 7th on among 28 submissions on subtask 1.1 and 7th among 20 submissions on subtask 1.2.
Tasks Relation Classification, Relation Extraction
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1135/
PDF https://www.aclweb.org/anthology/S18-1135
PWC https://paperswithcode.com/paper/takelab-at-semeval-2018-task-7-combining
Repo
Framework

NTNU at SemEval-2018 Task 7: Classifier Ensembling for Semantic Relation Identification and Classification in Scientific Papers

Title NTNU at SemEval-2018 Task 7: Classifier Ensembling for Semantic Relation Identification and Classification in Scientific Papers
Authors Biswanath Barik, Utpal Kumar Sikdar, Bj{"o}rn Gamb{"a}ck
Abstract The paper presents NTNU{'}s contribution to SemEval-2018 Task 7 on relation identification and classification. The class weights and parameters of five alternative supervised classifiers were optimized through grid search and cross-validation. The outputs of the classifiers were combined through voting for the final prediction. A wide variety of features were explored, with the most informative identified by feature selection. The best setting achieved F1 scores of 47.4{%} and 66.0{%} in the relation classification subtasks 1.1 and 1.2. For relation identification and classification in subtask 2, it achieved F1 scores of 33.9{%} and 17.0{%},
Tasks Feature Selection, Relation Classification, Relation Extraction
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1138/
PDF https://www.aclweb.org/anthology/S18-1138
PWC https://paperswithcode.com/paper/ntnu-at-semeval-2018-task-7-classifier
Repo
Framework

Topic Intrusion for Automatic Topic Model Evaluation

Title Topic Intrusion for Automatic Topic Model Evaluation
Authors Shraey Bhatia, Jey Han Lau, Timothy Baldwin
Abstract Topic coherence is increasingly being used to evaluate topic models and filter topics for end-user applications. Topic coherence measures how well topic words relate to each other, but offers little insight on the utility of the topics in describing the documents. In this paper, we explore the topic intrusion task {—} the task of guessing an outlier topic given a document and a few topics {—} and propose a method to automate it. We improve upon the state-of-the-art substantially, demonstrating its viability as an alternative method for topic model evaluation.
Tasks Information Retrieval, Topic Models
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1098/
PDF https://www.aclweb.org/anthology/D18-1098
PWC https://paperswithcode.com/paper/topic-intrusion-for-automatic-topic-model
Repo
Framework

Rule- and Learning-based Methods for Bridging Resolution in the ARRAU Corpus

Title Rule- and Learning-based Methods for Bridging Resolution in the ARRAU Corpus
Authors Ina Roesiger
Abstract We present two systems for bridging resolution, which we submitted to the CRAC shared task on bridging anaphora resolution in the ARRAU corpus (track 2): a rule-based approach following Hou et al. 2014 and a learning-based approach. The re-implementation of Hou et al. 2014 achieves very poor performance when being applied to ARRAU. We found that the reasons for this lie in the different bridging annotations: whereas the rule-based system suggests many referential bridging pairs, ARRAU contains mostly lexical bridging. We describe the differences between these two types of bridging and adapt the rule-based approach to be able to handle lexical bridging. The modified rule-based approach achieves reasonable performance on all (sub)-tasks and outperforms a simple learning-based approach.
Tasks Bridging Anaphora Resolution
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0703/
PDF https://www.aclweb.org/anthology/W18-0703
PWC https://paperswithcode.com/paper/rule-and-learning-based-methods-for-bridging
Repo
Framework

Bandit Learning in Concave N-Person Games

Title Bandit Learning in Concave N-Person Games
Authors Mario Bravo, David Leslie, Panayotis Mertikopoulos
Abstract This paper examines the long-run behavior of learning with bandit feedback in non-cooperative concave games. The bandit framework accounts for extremely low-information environments where the agents may not even know they are playing a game; as such, the agents’ most sensible choice in this setting would be to employ a no-regret learning algorithm. In general, this does not mean that the players’ behavior stabilizes in the long run: no-regret learning may lead to cycles, even with perfect gradient information. However, if a standard monotonicity condition is satisfied, our analysis shows that no-regret learning based on mirror descent with bandit feedback converges to Nash equilibrium with probability 1. We also derive an upper bound for the convergence rate of the process that nearly matches the best attainable rate for single-agent bandit stochastic optimization.
Tasks Stochastic Optimization
Published 2018-12-01
URL http://papers.nips.cc/paper/7809-bandit-learning-in-concave-n-person-games
PDF http://papers.nips.cc/paper/7809-bandit-learning-in-concave-n-person-games.pdf
PWC https://paperswithcode.com/paper/bandit-learning-in-concave-n-person-games-1
Repo
Framework

PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos

Title PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos
Authors Dingwen Zhang, Guangyu Guo, Dong Huang, Junwei Han
Abstract Motion of the human body is the critical cue for understanding and characterizing human behavior in videos. Most existing approaches explore the motion cue using optical flows. However, optical flow usually contains motion on both the interested human bodies and the undesired background. This “noisy” motion representation makes it very challenging for pose estimation and action recognition in real scenarios. To address this issue, this paper presents a novel deep motion representation, called PoseFlow, which reveals human motion in videos while suppressing background and motion blur, and being robust to occlusion. For learning PoseFlow with mild computational cost, we propose a functionally structured spatial-temporal deep network, PoseFlow Net (PFN), to jointly solve the skeleton localization and matching problems of PoseFlow. Comprehensive experiments show that PFN outperforms the state-of-the-art deep flow estimation models in generating PoseFlow. Moreover, PoseFlow demonstrates its potential on improving two challenging tasks in human video analysis: pose estimation and action recognition.
Tasks Optical Flow Estimation, Pose Estimation, Pose Tracking, Temporal Action Localization
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_PoseFlow_A_Deep_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_PoseFlow_A_Deep_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/poseflow-a-deep-motion-representation-for
Repo
Framework

Corpora with Part-of-Speech Annotations for Three Regional Languages of France: Alsatian, Occitan and Picard

Title Corpora with Part-of-Speech Annotations for Three Regional Languages of France: Alsatian, Occitan and Picard
Authors Delphine Bernhard, Anne-Laure Ligozat, Fanny Martin, Myriam Bras, Pierre Magistry, Marianne Vergez-Couret, Lucie Steibl{'e}, Pascale Erhart, Nabil Hathout, Dominique Huck, Christophe Rey, Philippe Reyn{'e}s, Sophie Rosset, Jean Sibille, Thomas Lavergne
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1619/
PDF https://www.aclweb.org/anthology/L18-1619
PWC https://paperswithcode.com/paper/corpora-with-part-of-speech-annotations-for
Repo
Framework

Multiple Source Domain Adaptation with Adversarial Learning

Title Multiple Source Domain Adaptation with Adversarial Learning
Authors Han Zhao, Shanghang Zhang, Guanhang Wu, Jo~{a}o P. Costeira, Jos'{e} M. F. Moura, Geoffrey J. Gordon
Abstract While domain adaptation has been actively researched in recent years, most theoretical results and algorithms focus on the single-source-single-target adaptation setting. Naive application of such algorithms on multiple source domain adaptation problem may lead to suboptimal solutions. We propose a new generalization bound for domain adaptation when there are multiple source domains with labeled instances and one target domain with unlabeled instances. Compared with existing bounds, the new bound does not require expert knowledge about the target distribution, nor the optimal combination rule for multisource domains. Interestingly, our theory also leads to an efficient learning strategy using adversarial neural networks: we show how to interpret it as learning feature representations that are invariant to the multiple domain shifts while still being discriminative for the learning task. To this end, we propose two models, both of which we call multisource domain adversarial networks (MDANs): the first model optimizes directly our bound, while the second model is a smoothed approximation of the first one, leading to a more data-efficient and task-adaptive model. The optimization tasks of both models are minimax saddle point problems that can be optimized by adversarial training. To demonstrate the effectiveness of MDANs, we conduct extensive experiments showing superior adaptation performance on three real-world datasets: sentiment analysis, digit classification, and vehicle counting.
Tasks Domain Adaptation, Sentiment Analysis
Published 2018-01-01
URL https://openreview.net/forum?id=ryDNZZZAW
PDF https://openreview.net/pdf?id=ryDNZZZAW
PWC https://paperswithcode.com/paper/multiple-source-domain-adaptation-with-1
Repo
Framework

Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting

Title Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting
Authors Dirk Hovy, Christoph Purschke
Abstract Dialects are one of the main drivers of language variation, a major challenge for natural language processing tools. In most languages, dialects exist along a continuum, and are commonly discretized by combining the extent of several preselected linguistic variables. However, the selection of these variables is theory-driven and itself insensitive to change. We use Doc2Vec on a corpus of 16.8M anonymous online posts in the German-speaking area to learn continuous document representations of cities. These representations capture continuous regional linguistic distinctions, and can serve as input to downstream NLP tasks sensitive to regional variation. By incorporating geographic information via retrofitting and agglomerative clustering with structure, we recover dialect areas at various levels of granularity. Evaluating these clusters against an existing dialect map, we achieve a match of up to 0.77 V-score (harmonic mean of cluster completeness and homogeneity). Our results show that representation learning with retrofitting offers a robust general method to automatically expose dialectal differences and regional variation at a finer granularity than was previously possible.
Tasks Dimensionality Reduction, Machine Translation, Representation Learning
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1469/
PDF https://www.aclweb.org/anthology/D18-1469
PWC https://paperswithcode.com/paper/capturing-regional-variation-with-distributed
Repo
Framework

Toward Data-Driven Tutorial Question Answering with Deep Learning Conversational Models

Title Toward Data-Driven Tutorial Question Answering with Deep Learning Conversational Models
Authors Mayank Kulkarni, Kristy Boyer
Abstract There has been an increase in popularity of data-driven question answering systems given their recent success. This pa-per explores the possibility of building a tutorial question answering system for Java programming from data sampled from a community-based question answering forum. This paper reports on the creation of a dataset that could support building such a tutorial question answering system and discusses the methodology to create the 106,386 question strong dataset. We investigate how retrieval-based and generative models perform on the given dataset. The work also investigates the usefulness of using hybrid approaches such as combining retrieval-based and generative models. The results indicate that building data-driven tutorial systems using community-based question answering forums holds significant promise.
Tasks Information Retrieval, Question Answering, Semantic Parsing, Transfer Learning
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0532/
PDF https://www.aclweb.org/anthology/W18-0532
PWC https://paperswithcode.com/paper/toward-data-driven-tutorial-question
Repo
Framework

E-magyar – A Digital Language Processing System

Title E-magyar – A Digital Language Processing System
Authors Tam{'a}s V{'a}radi, Eszter Simon, B{'a}lint Sass, Iv{'a}n Mittelholcz, Attila Nov{'a}k, Bal{'a}zs Indig, Rich{'a}rd Farkas, Veronika Vincze
Abstract
Tasks Named Entity Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1208/
PDF https://www.aclweb.org/anthology/L18-1208
PWC https://paperswithcode.com/paper/e-magyar-a-digital-language-processing-system
Repo
Framework
comments powered by Disqus