Paper Group NANR 84
Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach. Data-driven learning of symbolic constraints for a log-linear model in a phonological setting. Extraction of Regulatory Events using Kernel-based Classifiers and Distant Supervision. Online Multilingual Topic Models with Multi-Level Hyperpriors. Cross-Lingual S …
Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach
| Title | Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach |
| Authors | Remi Lam, Karen Willcox, David H. Wolpert |
| Abstract | We consider the problem of optimizing an expensive objective function when a finite budget of total evaluations is prescribed. In that context, the optimal solution strategy for Bayesian optimization can be formulated as a dynamic programming instance. This results in a complex problem with uncountable, dimension-increasing state space and an uncountable control space. We show how to approximate the solution of this dynamic programming problem using rollout, and propose rollout heuristics specifically designed for the Bayesian optimization setting. We present numerical experiments showing that the resulting algorithm for optimization with a finite budget outperforms several popular Bayesian optimization algorithms. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6188-bayesian-optimization-with-a-finite-budget-an-approximate-dynamic-programming-approach |
| http://papers.nips.cc/paper/6188-bayesian-optimization-with-a-finite-budget-an-approximate-dynamic-programming-approach.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-optimization-with-a-finite-budget-an |
| Repo | |
| Framework | |
Data-driven learning of symbolic constraints for a log-linear model in a phonological setting
| Title | Data-driven learning of symbolic constraints for a log-linear model in a phonological setting |
| Authors | Gabriel Doyle, Roger Levy |
| Abstract | We propose a non-parametric Bayesian model for learning and weighting symbolically-defined constraints to populate a log-linear model. The model jointly infers a vector of binary constraint values for each candidate output and likely definitions for these constraints, combining observations of the output classes with a (potentially infinite) grammar over potential constraint definitions. We present results on a small morphophonological system, English regular plurals, as a test case. The inferred constraints, based on a grammar of articulatory features, perform as well as theoretically-defined constraints on both observed and novel forms of English regular plurals. The learned constraint values and definitions also closely resemble standard constraints defined within phonological theory. |
| Tasks | Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1209/ |
| https://www.aclweb.org/anthology/C16-1209 | |
| PWC | https://paperswithcode.com/paper/data-driven-learning-of-symbolic-constraints |
| Repo | |
| Framework | |
Extraction of Regulatory Events using Kernel-based Classifiers and Distant Supervision
| Title | Extraction of Regulatory Events using Kernel-based Classifiers and Distant Supervision |
| Authors | Andre Lamurias, Miguel J. Rodrigues, Luka A. Clarke, Francisco M. Couto |
| Abstract | |
| Tasks | Relation Extraction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-3011/ |
| https://www.aclweb.org/anthology/W16-3011 | |
| PWC | https://paperswithcode.com/paper/extraction-of-regulatory-events-using-kernel |
| Repo | |
| Framework | |
Online Multilingual Topic Models with Multi-Level Hyperpriors
| Title | Online Multilingual Topic Models with Multi-Level Hyperpriors |
| Authors | Kriste Krstovski, David Smith, Michael J. Kurtz |
| Abstract | |
| Tasks | Topic Models |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1053/ |
| https://www.aclweb.org/anthology/N16-1053 | |
| PWC | https://paperswithcode.com/paper/online-multilingual-topic-models-with-multi |
| Repo | |
| Framework | |
Cross-Lingual Sentiment Classification with Bilingual Document Representation Learning
| Title | Cross-Lingual Sentiment Classification with Bilingual Document Representation Learning |
| Authors | Xinjie Zhou, Xiaojun Wan, Jianguo Xiao |
| Abstract | |
| Tasks | Machine Translation, Representation Learning, Sentiment Analysis, Stock Market Prediction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1133/ |
| https://www.aclweb.org/anthology/P16-1133 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-sentiment-classification-with |
| Repo | |
| Framework | |
Combining Human Inputters and Language Services to provide Multi-language support system for International Symposiums
| Title | Combining Human Inputters and Language Services to provide Multi-language support system for International Symposiums |
| Authors | Takao Nakaguchi, Masayuki Otani, Toshiyuki Takasaki, Toru Ishida |
| Abstract | In this research, we introduce and implement a method that combines human inputters and machine translators. When the languages of the participants vary widely, the cost of simultaneous translation becomes very high. However, the results of simply applying machine translation to speech text do not have the quality that is needed for real use. Thus, we propose a method that people who understand the language of the speaker cooperate with a machine translation service in support of multilingualization by the co-creation of value. We implement a system with this method and apply it to actual presentations. While the quality of direct machine translations is 1.84 (fluency) and 2.89 (adequacy), the system has corresponding values of 3.76 and 3.85. |
| Tasks | Machine Translation, Speech Recognition, Speech Synthesis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5204/ |
| https://www.aclweb.org/anthology/W16-5204 | |
| PWC | https://paperswithcode.com/paper/combining-human-inputters-and-language |
| Repo | |
| Framework | |
Dependency-based Gated Recursive Neural Network for Chinese Word Segmentation
| Title | Dependency-based Gated Recursive Neural Network for Chinese Word Segmentation |
| Authors | Jingjing Xu, Xu Sun |
| Abstract | |
| Tasks | Chinese Word Segmentation, Feature Engineering |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2092/ |
| https://www.aclweb.org/anthology/P16-2092 | |
| PWC | https://paperswithcode.com/paper/dependency-based-gated-recursive-neural |
| Repo | |
| Framework | |
Genetic Algorithm (GA) Implementation for Feature Selection in Manipuri POS Tagging
| Title | Genetic Algorithm (GA) Implementation for Feature Selection in Manipuri POS Tagging |
| Authors | Kishorjit Nongmeikapam, B, Sivaji yopadhyay |
| Abstract | |
| Tasks | Feature Selection, Part-Of-Speech Tagging |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6333/ |
| https://www.aclweb.org/anthology/W16-6333 | |
| PWC | https://paperswithcode.com/paper/genetic-algorithm-ga-implementation-for |
| Repo | |
| Framework | |
GATE-Time: Extraction of Temporal Expressions and Events
| Title | GATE-Time: Extraction of Temporal Expressions and Events |
| Authors | Leon Derczynski, Jannik Str{"o}tgen, Diana Maynard, Mark A. Greenwood, Manuel Jung |
| Abstract | GATE is a widely used open-source solution for text processing with a large user community. It contains components for several natural language processing tasks. However, temporal information extraction functionality within GATE has been rather limited so far, despite being a prerequisite for many application scenarios in the areas of natural language processing and information retrieval. This paper presents an integrated approach to temporal information processing. We take state-of-the-art tools in temporal expression and event recognition and bring them together to form an openly-available resource within the GATE infrastructure. GATE-Time provides annotation in the form of TimeML events and temporal expressions complying with this mature ISO standard for temporal semantic annotation of documents. Major advantages of GATE-Time are (i) that it relies on HeidelTime for temporal tagging, so that temporal expressions can be extracted and normalized in multiple languages and across different domains, (ii) it includes a modern, fast event recognition and classification tool, and (iii) that it can be combined with different linguistic pre-processing annotations, and is thus not bound to license restricted preprocessing components. |
| Tasks | Information Retrieval, Temporal Information Extraction |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1587/ |
| https://www.aclweb.org/anthology/L16-1587 | |
| PWC | https://paperswithcode.com/paper/gate-time-extraction-of-temporal-expressions |
| Repo | |
| Framework | |
Building Chinese Affective Resources in Valence-Arousal Dimensions
| Title | Building Chinese Affective Resources in Valence-Arousal Dimensions |
| Authors | Liang-Chih Yu, Lung-Hao Lee, Shuai Hao, Jin Wang, Yunchao He, Jun Hu, K. Robert Lai, Xuejie Zhang |
| Abstract | |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis, Stance Detection, Twitter Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1066/ |
| https://www.aclweb.org/anthology/N16-1066 | |
| PWC | https://paperswithcode.com/paper/building-chinese-affective-resources-in |
| Repo | |
| Framework | |
Learning Structured Predictors from Bandit Feedback for Interactive NLP
| Title | Learning Structured Predictors from Bandit Feedback for Interactive NLP |
| Authors | Artem Sokolov, Julia Kreutzer, Christopher Lo, Stefan Riezler |
| Abstract | |
| Tasks | Machine Translation, Stochastic Optimization, Structured Prediction, Text Classification |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1152/ |
| https://www.aclweb.org/anthology/P16-1152 | |
| PWC | https://paperswithcode.com/paper/learning-structured-predictors-from-bandit |
| Repo | |
| Framework | |
Semi-supervised Clustering of Medical Text
| Title | Semi-supervised Clustering of Medical Text |
| Authors | Pracheta Sahoo, Asif Ekbal, Sriparna Saha, Diego Moll{'a}, N, Kaushik an |
| Abstract | Semi-supervised clustering is an attractive alternative for traditional (unsupervised) clustering in targeted applications. By using the information of a small annotated dataset, semi-supervised clustering can produce clusters that are customized to the application domain. In this paper, we present a semi-supervised clustering technique based on a multi-objective evolutionary algorithm (NSGA-II-clus). We apply this technique to the task of clustering medical publications for Evidence Based Medicine (EBM) and observe an improvement of the results against unsupervised and other semi-supervised clustering techniques. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4205/ |
| https://www.aclweb.org/anthology/W16-4205 | |
| PWC | https://paperswithcode.com/paper/semi-supervised-clustering-of-medical-text |
| Repo | |
| Framework | |
Syntactic Parsing of Web Queries with Question Intent
| Title | Syntactic Parsing of Web Queries with Question Intent |
| Authors | Yuval Pinter, Roi Reichart, Idan Szpektor |
| Abstract | |
| Tasks | Community Question Answering, Domain Adaptation, Information Retrieval, Question Answering |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1081/ |
| https://www.aclweb.org/anthology/N16-1081 | |
| PWC | https://paperswithcode.com/paper/syntactic-parsing-of-web-queries-with |
| Repo | |
| Framework | |
USAAR at SemEval-2016 Task 11: Complex Word Identification with Sense Entropy and Sentence Perplexity
| Title | USAAR at SemEval-2016 Task 11: Complex Word Identification with Sense Entropy and Sentence Perplexity |
| Authors | Jos{'e} Manuel Mart{'\i}nez Mart{'\i}nez, Liling Tan |
| Abstract | |
| Tasks | Complex Word Identification, Lexical Simplification, Word Sense Disambiguation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1147/ |
| https://www.aclweb.org/anthology/S16-1147 | |
| PWC | https://paperswithcode.com/paper/usaar-at-semeval-2016-task-11-complex-word |
| Repo | |
| Framework | |
Sensible at SemEval-2016 Task 11: Neural Nonsense Mangled in Ensemble Mess
| Title | Sensible at SemEval-2016 Task 11: Neural Nonsense Mangled in Ensemble Mess |
| Authors | Gillin Nat |
| Abstract | |
| Tasks | Complex Word Identification |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1148/ |
| https://www.aclweb.org/anthology/S16-1148 | |
| PWC | https://paperswithcode.com/paper/sensible-at-semeval-2016-task-11-neural |
| Repo | |
| Framework | |
