Paper Group NANR 130
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure. Learning Contextually Informed Representations for Linear-Time Discourse Parsing. NLPSA at IJCNLP-2017 Task 2: Imagine Scenario: Leveraging Supportive Images for Dimensional Sentiment Analysis. Remarks on epistemically biased questions. BTG-based Machin …
Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure
| Title | Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite Sum Structure |
| Authors | Alberto Bietti, Julien Mairal |
| Abstract | Stochastic optimization algorithms with variance reduction have proven successful for minimizing large finite sums of functions. Unfortunately, these techniques are unable to deal with stochastic perturbations of input data, induced for example by data augmentation. In such cases, the objective is no longer a finite sum, and the main candidate for optimization is the stochastic gradient descent method (SGD). In this paper, we introduce a variance reduction approach for these settings when the objective is composite and strongly convex. The convergence rate outperforms SGD with a typically much smaller constant factor, which depends on the variance of gradient estimates only due to perturbations on a single example. |
| Tasks | Data Augmentation, Stochastic Optimization |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6760-stochastic-optimization-with-variance-reduction-for-infinite-datasets-with-finite-sum-structure |
| http://papers.nips.cc/paper/6760-stochastic-optimization-with-variance-reduction-for-infinite-datasets-with-finite-sum-structure.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-optimization-with-variance-1 |
| Repo | |
| Framework | |
Learning Contextually Informed Representations for Linear-Time Discourse Parsing
| Title | Learning Contextually Informed Representations for Linear-Time Discourse Parsing |
| Authors | Yang Liu, Mirella Lapata |
| Abstract | Recent advances in RST discourse parsing have focused on two modeling paradigms: (a) high order parsers which jointly predict the tree structure of the discourse and the relations it encodes; or (b) linear-time parsers which are efficient but mostly based on local features. In this work, we propose a linear-time parser with a novel way of representing discourse constituents based on neural networks which takes into account global contextual information and is able to capture long-distance dependencies. Experimental results show that our parser obtains state-of-the art performance on benchmark datasets, while being efficient (with time complexity linear in the number of sentences in the document) and requiring minimal feature engineering. |
| Tasks | Feature Engineering, Question Answering, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1133/ |
| https://www.aclweb.org/anthology/D17-1133 | |
| PWC | https://paperswithcode.com/paper/learning-contextually-informed |
| Repo | |
| Framework | |
NLPSA at IJCNLP-2017 Task 2: Imagine Scenario: Leveraging Supportive Images for Dimensional Sentiment Analysis
| Title | NLPSA at IJCNLP-2017 Task 2: Imagine Scenario: Leveraging Supportive Images for Dimensional Sentiment Analysis |
| Authors | Szu-Min Chen, Zi-Yuan Chen, Lun-Wei Ku |
| Abstract | Categorical sentiment classification has drawn much attention in the field of NLP, while less work has been conducted for dimensional sentiment analysis (DSA). Recent works for DSA utilize either word embedding, knowledge base features, or bilingual language resources. In this paper, we propose our model for IJCNLP 2017 Dimensional Sentiment Analysis for Chinese Phrases shared task. Our model incorporates word embedding as well as image features, attempting to simulate human{'}s imaging behavior toward sentiment analysis. Though the performance is not comparable to others in the end, we conduct several experiments with possible reasons discussed, and analyze the drawbacks of our model. |
| Tasks | Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4017/ |
| https://www.aclweb.org/anthology/I17-4017 | |
| PWC | https://paperswithcode.com/paper/nlpsa-at-ijcnlp-2017-task-2-imagine-scenario |
| Repo | |
| Framework | |
Remarks on epistemically biased questions
| Title | Remarks on epistemically biased questions |
| Authors | David Yoshikazu Oshima |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1025/ |
| https://www.aclweb.org/anthology/Y17-1025 | |
| PWC | https://paperswithcode.com/paper/remarks-on-epistemically-biased-questions |
| Repo | |
| Framework | |
BTG-based Machine Translation with Simple Reordering Model using Structured Perceptron
| Title | BTG-based Machine Translation with Simple Reordering Model using Structured Perceptron |
| Authors | Hao Wang, Yves Lepage |
| Abstract | |
| Tasks | Machine Translation, Word Alignment |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1018/ |
| https://www.aclweb.org/anthology/Y17-1018 | |
| PWC | https://paperswithcode.com/paper/btg-based-machine-translation-with-simple |
| Repo | |
| Framework | |
Ensemble Technique Utilization for Indonesian Dependency Parser
| Title | Ensemble Technique Utilization for Indonesian Dependency Parser |
| Authors | Arief Rahman, Ayu Purwarianti |
| Abstract | |
| Tasks | Dependency Parsing, Semantic Role Labeling, Sentiment Analysis |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1012/ |
| https://www.aclweb.org/anthology/Y17-1012 | |
| PWC | https://paperswithcode.com/paper/ensemble-technique-utilization-for-indonesian |
| Repo | |
| Framework | |
Issues of Mass and Count: Dealing with `Dual-Life’ Nouns
| Title | Issues of Mass and Count: Dealing with `Dual-Life’ Nouns | |
| Authors | Tibor Kiss, Francis Jeffry Pelletier, Halima Husi{'c}, Johanna Poppek |
| Abstract | The topics of mass and count have been studied for many decades in philosophy (e.g., Quine, 1960; Pelletier, 1975), linguistics (e.g., McCawley, 1975; Allen, 1980; Krifka, 1991) and psychology (e.g., Middleton et al, 2004; Barner et al, 2009). More recently, interest from within computational linguistics has studied the issues involved (e.g., Pustejovsky, 1991; Bond, 2005; Schmidtke {&} Kuperman, 2016), to name just a few. As is pointed out in these works, there are many difficult conceptual issues involved in the study of this contrast. In this article we study one of these issues {–} the {``}Dual-Life{''} of being simultaneously +mass and +count {–} by means of an unusual combination of human annotation, online lexical resources, and online corpora. | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1023/ |
| https://www.aclweb.org/anthology/S17-1023 | |
| PWC | https://paperswithcode.com/paper/issues-of-mass-and-count-dealing-with-dual |
| Repo | |
| Framework | |
Semantic Enrichment Across Language: A Case Study of Czech Bibliographic Databases
| Title | Semantic Enrichment Across Language: A Case Study of Czech Bibliographic Databases |
| Authors | Pavel Smrz, Lubomir Otrusina |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7563/ |
| https://www.aclweb.org/anthology/W17-7563 | |
| PWC | https://paperswithcode.com/paper/semantic-enrichment-across-language-a-case |
| Repo | |
| Framework | |
Incorporating Global Visual Features into Attention-based Neural Machine Translation.
| Title | Incorporating Global Visual Features into Attention-based Neural Machine Translation. |
| Authors | Iacer Calixto, Qun Liu |
| Abstract | We introduce multi-modal, attention-based neural machine translation (NMT) models which incorporate visual features into different parts of both the encoder and the decoder. Global image features are extracted using a pre-trained convolutional neural network and are incorporated (i) as words in the source sentence, (ii) to initialise the encoder hidden state, and (iii) as additional data to initialise the decoder hidden state. In our experiments, we evaluate translations into English and German, how different strategies to incorporate global image features compare and which ones perform best. We also study the impact that adding synthetic multi-modal, multilingual data brings and find that the additional data have a positive impact on multi-modal NMT models. We report new state-of-the-art results and our best models also significantly improve on a comparable phrase-based Statistical MT (PBSMT) model trained on the Multi30k data set according to all metrics evaluated. To the best of our knowledge, it is the first time a purely neural model significantly improves over a PBSMT model on all metrics evaluated on this data set. |
| Tasks | Machine Translation, Text Generation, Video Description |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1105/ |
| https://www.aclweb.org/anthology/D17-1105 | |
| PWC | https://paperswithcode.com/paper/incorporating-global-visual-features-into-1 |
| Repo | |
| Framework | |
Scalable Levy Process Priors for Spectral Kernel Learning
| Title | Scalable Levy Process Priors for Spectral Kernel Learning |
| Authors | Phillip A. Jang, Andrew Loeb, Matthew Davidow, Andrew G. Wilson |
| Abstract | Gaussian processes are rich distributions over functions, with generalization properties determined by a kernel function. When used for long-range extrapolation, predictions are particularly sensitive to the choice of kernel parameters. It is therefore critical to account for kernel uncertainty in our predictive distributions. We propose a distribution over kernels formed by modelling a spectral mixture density with a Levy process. The resulting distribution has support for all stationary covariances—including the popular RBF, periodic, and Matern kernels—combined with inductive biases which enable automatic and data efficient learning, long-range extrapolation, and state of the art predictive performance. The proposed model also presents an approach to spectral regularization, as the Levy process introduces a sparsity-inducing prior over mixture components, allowing automatic selection over model order and pruning of extraneous components. We exploit the algebraic structure of the proposed process for O(n) training and O(1) predictions. We perform extrapolations having reasonable uncertainty estimates on several benchmarks, show that the proposed model can recover flexible ground truth covariances and that it is robust to errors in initialization. |
| Tasks | Gaussian Processes |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6983-scalable-levy-process-priors-for-spectral-kernel-learning |
| http://papers.nips.cc/paper/6983-scalable-levy-process-priors-for-spectral-kernel-learning.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-levy-process-priors-for-spectral-1 |
| Repo | |
| Framework | |
LSDSem 2017 Shared Task: The Story Cloze Test
| Title | LSDSem 2017 Shared Task: The Story Cloze Test |
| Authors | Nasrin Mostafazadeh, Michael Roth, Annie Louis, Nathanael Chambers, James Allen |
| Abstract | The LSDSem{'}17 shared task is the Story Cloze Test, a new evaluation for story understanding and script learning. This test provides a system with a four-sentence story and two possible endings, and the system must choose the correct ending to the story. Successful narrative understanding (getting closer to human performance of 100{%}) requires systems to link various levels of semantics to commonsense knowledge. A total of eight systems participated in the shared task, with a variety of approaches including. |
| Tasks | Reading Comprehension |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0906/ |
| https://www.aclweb.org/anthology/W17-0906 | |
| PWC | https://paperswithcode.com/paper/lsdsem-2017-shared-task-the-story-cloze-test |
| Repo | |
| Framework | |
Amharic-English Speech Translation in Tourism Domain
| Title | Amharic-English Speech Translation in Tourism Domain |
| Authors | Michael Melese, Laurent Besacier, Million Meshesha |
| Abstract | This paper describes speech translation from Amharic-to-English, particularly Automatic Speech Recognition (ASR) with post-editing feature and Amharic-English Statistical Machine Translation (SMT). ASR experiment is conducted using morpheme language model (LM) and phoneme acoustic model(AM). Likewise,SMT conducted using word and morpheme as unit. Morpheme based translation shows a 6.29 BLEU score at a 76.4{%} of recognition accuracy while word based translation shows a 12.83 BLEU score using 77.4{%} word recognition accuracy. Further, after post-edit on Amharic ASR using corpus based n-gram, the word recognition accuracy increased by 1.42{%}. Since post-edit approach reduces error propagation, the word based translation accuracy improved by 0.25 (1.95{%}) BLEU score. We are now working towards further improving propagated errors through different algorithms at each unit of speech translation cascading component. |
| Tasks | Language Modelling, Machine Translation, Speech Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4608/ |
| https://www.aclweb.org/anthology/W17-4608 | |
| PWC | https://paperswithcode.com/paper/amharic-english-speech-translation-in-tourism |
| Repo | |
| Framework | |
Sentence Complexity Estimation for Chinese-speaking Learners of Japanese
| Title | Sentence Complexity Estimation for Chinese-speaking Learners of Japanese |
| Authors | Jun Liu, Yuji Matsumoto |
| Abstract | |
| Tasks | Reading Comprehension |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1040/ |
| https://www.aclweb.org/anthology/Y17-1040 | |
| PWC | https://paperswithcode.com/paper/sentence-complexity-estimation-for-chinese |
| Repo | |
| Framework | |
Sense-Aware Statistical Machine Translation using Adaptive Context-Dependent Clustering
| Title | Sense-Aware Statistical Machine Translation using Adaptive Context-Dependent Clustering |
| Authors | Xiao Pu, Nikolaos Pappas, Andrei Popescu-Belis |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4701/ |
| https://www.aclweb.org/anthology/W17-4701 | |
| PWC | https://paperswithcode.com/paper/sense-aware-statistical-machine-translation |
| Repo | |
| Framework | |
Multi-dimensional Meanings of Subjective Adverbs - Case Study of Mandarin Chinese Adverb Pianpian
| Title | Multi-dimensional Meanings of Subjective Adverbs - Case Study of Mandarin Chinese Adverb Pianpian |
| Authors | Mi Zhou, Yao Yao, Chu-Ren Huang |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1042/ |
| https://www.aclweb.org/anthology/Y17-1042 | |
| PWC | https://paperswithcode.com/paper/multi-dimensional-meanings-of-subjective |
| Repo | |
| Framework | |
