Paper Group NANR 28
Estimation of the covariance structure of heavy-tailed distributions. The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction. A Coarse-Fine Network for Keypoint Localization. Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning. Challenging learners in their individu …
Estimation of the covariance structure of heavy-tailed distributions
| Title | Estimation of the covariance structure of heavy-tailed distributions |
| Authors | Xiaohan Wei, Stanislav Minsker |
| Abstract | We propose and analyze a new estimator of the covariance matrix that admits strong theoretical guarantees under weak assumptions on the underlying distribution, such as existence of moments of only low order. While estimation of covariance matrices corresponding to sub-Gaussian distributions is well-understood, much less in known in the case of heavy-tailed data. As K. Balasubramanian and M. Yuan write, data from real-world experiments oftentimes tend to be corrupted with outliers and/or exhibit heavy tails. In such cases, it is not clear that those covariance matrix estimators .. remain optimal'' and ..what are the other possible strategies to deal with heavy tailed distributions warrant further studies.’’ We make a step towards answering this question and prove tight deviation inequalities for the proposed estimator that depend only on the parameters controlling the ``intrinsic dimension’’ associated to the covariance matrix (as opposed to the dimension of the ambient space); in particular, our results are applicable in the case of high-dimensional observations. | |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6878-estimation-of-the-covariance-structure-of-heavy-tailed-distributions |
| http://papers.nips.cc/paper/6878-estimation-of-the-covariance-structure-of-heavy-tailed-distributions.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-of-the-covariance-structure-of |
| Repo | |
| Framework | |
The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction
| Title | The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction |
| Authors | Waleed Ammar, Matthew Peters, Ch Bhagavatula, ra, Russell Power |
| Abstract | This paper describes our submission for the ScienceIE shared task (SemEval- 2017 Task 10) on entity and relation extraction from scientific papers. Our model is based on the end-to-end relation extraction model of Miwa and Bansal (2016) with several enhancements such as semi-supervised learning via neural language models, character-level encoding, gazetteers extracted from existing knowledge bases, and model ensembles. Our official submission ranked first in end-to-end entity and relation extraction (scenario 1), and second in the relation-only extraction (scenario 3). |
| Tasks | Dependency Parsing, Part-Of-Speech Tagging, Relation Extraction, Tokenization |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2097/ |
| https://www.aclweb.org/anthology/S17-2097 | |
| PWC | https://paperswithcode.com/paper/the-ai2-system-at-semeval-2017-task-10 |
| Repo | |
| Framework | |
A Coarse-Fine Network for Keypoint Localization
| Title | A Coarse-Fine Network for Keypoint Localization |
| Authors | Shaoli Huang, Mingming Gong, Dacheng Tao |
| Abstract | We propose a coarse-fine network (CFN) that exploits multi-level supervisions for keypoint localization. Recently, convolutional neural networks (CNNs)-based methods have achieved great success due to the powerful hierarchical features in CNNs. These methods typically use confidence maps generated from ground-truth keypoint locations as supervisory signals. However, while some keypoints can be easily located with high accuracy, many of them are hard to localize due to appearance ambiguity. Thus, using strict supervision often fails to detect keypoints that are difficult to locate accurately. To target this problem, we develop a keypoint localization network composed of several coarse detector branches, each of which is built on top of a feature layer in a CNN, and a fine detector branch built on top of multiple feature layers. We supervise each branch by a specified label map to explicate a certain supervision strictness level. All the branches are unified principally to produce the final accurate keypoint locations. We demonstrate the efficacy, efficiency, and generality of our method on several benchmarks for multiple tasks including bird part localization and human body pose estimation. Especially, our method achieves 72.2% AP on the 2016 COCO Keypoints Challenge dataset, which is an 18% improvement over the winning entry. |
| Tasks | Pose Estimation |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Huang_A_Coarse-Fine_Network_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Huang_A_Coarse-Fine_Network_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-coarse-fine-network-for-keypoint |
| Repo | |
| Framework | |
Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning
| Title | Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning |
| Authors | Caglar Gulcehre, Francis Dutil, Adam Trischler, Yoshua Bengio |
| Abstract | We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention. We develop a model that can plan ahead when it computes alignments between the source and target sequences not only for a single time-step but for the next k time-steps as well by constructing a matrix of proposed future alignments and a commitment vector that governs whether to follow or recompute the plan. This mechanism is inspired by strategic attentive reader and writer (STRAW) model, a recent neural architecture for planning with hierarchical reinforcement learning that can also learn higher level temporal abstractions. Our proposed model is end-to-end trainable with differentiable operations. We show that our model outperforms strong baselines on character-level translation task from WMT{'}15 with fewer parameters and computes alignments that are qualitatively intuitive. |
| Tasks | Hierarchical Reinforcement Learning, Machine Translation, Representation Learning |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2627/ |
| https://www.aclweb.org/anthology/W17-2627 | |
| PWC | https://paperswithcode.com/paper/plan-attend-generate-character-level-neural |
| Repo | |
| Framework | |
Challenging learners in their individual zone of proximal development using pedagogic developmental benchmarks of syntactic complexity
| Title | Challenging learners in their individual zone of proximal development using pedagogic developmental benchmarks of syntactic complexity |
| Authors | Xiaobin Chen, Detmar Meurers |
| Abstract | |
| Tasks | Language Acquisition |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0302/ |
| https://www.aclweb.org/anthology/W17-0302 | |
| PWC | https://paperswithcode.com/paper/challenging-learners-in-their-individual-zone |
| Repo | |
| Framework | |
Group Additive Structure Identification for Kernel Nonparametric Regression
| Title | Group Additive Structure Identification for Kernel Nonparametric Regression |
| Authors | Chao Pan, Michael Zhu |
| Abstract | The additive model is one of the most popularly used models for high dimensional nonparametric regression analysis. However, its main drawback is that it neglects possible interactions between predictor variables. In this paper, we reexamine the group additive model proposed in the literature, and rigorously define the intrinsic group additive structure for the relationship between the response variable $Y$ and the predictor vector $\vect{X}$, and further develop an effective structure-penalized kernel method for simultaneous identification of the intrinsic group additive structure and nonparametric function estimation. The method utilizes a novel complexity measure we derive for group additive structures. We show that the proposed method is consistent in identifying the intrinsic group additive structure. Simulation study and real data applications demonstrate the effectiveness of the proposed method as a general tool for high dimensional nonparametric regression. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7076-group-additive-structure-identification-for-kernel-nonparametric-regression |
| http://papers.nips.cc/paper/7076-group-additive-structure-identification-for-kernel-nonparametric-regression.pdf | |
| PWC | https://paperswithcode.com/paper/group-additive-structure-identification-for |
| Repo | |
| Framework | |
Comparing Approaches for Automatic Question Identification
| Title | Comparing Approaches for Automatic Question Identification |
| Authors | Angel Maredia, Kara Schechtman, Sarah Ita Levitan, Julia Hirschberg |
| Abstract | Collecting spontaneous speech corpora that are open-ended, yet topically constrained, is increasingly popular for research in spoken dialogue systems and speaker state, inter alia. Typically, these corpora are labeled by human annotators, either in the lab or through crowd-sourcing; however, this is cumbersome and time-consuming for large corpora. We present four different approaches to automatically tagging a corpus when general topics of the conversations are known. We develop these approaches on the Columbia X-Cultural Deception corpus and find accuracy that significantly exceeds the baseline. Finally, we conduct a cross-corpus evaluation by testing the best performing approach on the Columbia/SRI/Colorado corpus. |
| Tasks | Semantic Textual Similarity, Spoken Dialogue Systems, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1013/ |
| https://www.aclweb.org/anthology/S17-1013 | |
| PWC | https://paperswithcode.com/paper/comparing-approaches-for-automatic-question |
| Repo | |
| Framework | |
A Decomposition of Forecast Error in Prediction Markets
| Title | A Decomposition of Forecast Error in Prediction Markets |
| Authors | Miro Dudik, Sebastien Lahaie, Ryan M. Rogers, Jennifer Wortman Vaughan |
| Abstract | We analyze sources of error in prediction market forecasts in order to bound the difference between a security’s price and the ground truth it estimates. We consider cost-function-based prediction markets in which an automated market maker adjusts security prices according to the history of trade. We decompose the forecasting error into three components: sampling error, arising because traders only possess noisy estimates of ground truth; market-maker bias, resulting from the use of a particular market maker (i.e., cost function) to facilitate trade; and convergence error, arising because, at any point in time, market prices may still be in flux. Our goal is to make explicit the tradeoffs between these error components, influenced by design decisions such as the functional form of the cost function and the amount of liquidity in the market. We consider a specific model in which traders have exponential utility and exponential-family beliefs representing noisy estimates of ground truth. In this setting, sampling error vanishes as the number of traders grows, but there is a tradeoff between the other two components. We provide both upper and lower bounds on market-maker bias and convergence error, and demonstrate via numerical simulations that these bounds are tight. Our results yield new insights into the question of how to set the market’s liquidity parameter and into the forecasting benefits of enforcing coherent prices across securities. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7024-a-decomposition-of-forecast-error-in-prediction-markets |
| http://papers.nips.cc/paper/7024-a-decomposition-of-forecast-error-in-prediction-markets.pdf | |
| PWC | https://paperswithcode.com/paper/a-decomposition-of-forecast-error-in |
| Repo | |
| Framework | |
Robust Estimation of Neural Signals in Calcium Imaging
| Title | Robust Estimation of Neural Signals in Calcium Imaging |
| Authors | Hakan Inan, Murat A. Erdogdu, Mark Schnitzer |
| Abstract | Calcium imaging is a prominent technology in neuroscience research which allows for simultaneous recording of large numbers of neurons in awake animals. Automated extraction of neurons and their temporal activity from imaging datasets is an important step in the path to producing neuroscience results. However, nearly all imaging datasets contain gross contaminating sources which could originate from the technology used, or the underlying biological tissue. Although past work has considered the effects of contamination under limited circumstances, there has not been a general framework treating contamination and its effects on the statistical estimation of calcium signals. In this work, we proceed in a new direction and propose to extract cells and their activity using robust statistical estimation. Using the theory of M-estimation, we derive a minimax optimal robust loss, and also find a simple and practical optimization routine for this loss with provably fast convergence. We use our proposed robust loss in a matrix factorization framework to extract the neurons and their temporal activity in calcium imaging datasets. We demonstrate the superiority of our robust estimation approach over existing methods on both simulated and real datasets. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6883-robust-estimation-of-neural-signals-in-calcium-imaging |
| http://papers.nips.cc/paper/6883-robust-estimation-of-neural-signals-in-calcium-imaging.pdf | |
| PWC | https://paperswithcode.com/paper/robust-estimation-of-neural-signals-in |
| Repo | |
| Framework | |
Embracing Non-Traditional Linguistic Resources for Low-resource Language Name Tagging
| Title | Embracing Non-Traditional Linguistic Resources for Low-resource Language Name Tagging |
| Authors | Boliang Zhang, Di Lu, Xiaoman Pan, Ying Lin, Halidanmu Abudukelimu, Heng Ji, Kevin Knight |
| Abstract | Current supervised name tagging approaches are inadequate for most low-resource languages due to the lack of annotated data and actionable linguistic knowledge. All supervised learning methods (including deep neural networks (DNN)) are sensitive to noise and thus they are not quite portable without massive clean annotations. We found that the F-scores of DNN-based name taggers drop rapidly (20{%}-30{%}) when we replace clean manual annotations with noisy annotations in the training data. We propose a new solution to incorporate many non-traditional language universal resources that are readily available but rarely explored in the Natural Language Processing (NLP) community, such as the World Atlas of Linguistic Structure, CIA names, PanLex and survival guides. We acquire and encode various types of non-traditional linguistic resources into a DNN name tagger. Experiments on three low-resource languages show that feeding linguistic knowledge can make DNN significantly more robust to noise, achieving 8{%}-22{%} absolute F-score gains on name tagging without using any human annotation |
| Tasks | Relation Classification, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1037/ |
| https://www.aclweb.org/anthology/I17-1037 | |
| PWC | https://paperswithcode.com/paper/embracing-non-traditional-linguistic |
| Repo | |
| Framework | |
A method for in-depth comparative evaluation: How (dis)similar are outputs of pos taggers, dependency parsers and coreference resolvers really?
| Title | A method for in-depth comparative evaluation: How (dis)similar are outputs of pos taggers, dependency parsers and coreference resolvers really? |
| Authors | Don Tuggener |
| Abstract | This paper proposes a generic method for the comparative evaluation of system outputs. The approach is able to quantify the pairwise differences between two outputs and to unravel in detail what the differences consist of. We apply our approach to three tasks in Computational Linguistics, i.e. POS tagging, dependency parsing, and coreference resolution. We find that system outputs are more distinct than the (often) small differences in evaluation scores seem to suggest. |
| Tasks | Coreference Resolution, Dependency Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1018/ |
| https://www.aclweb.org/anthology/E17-1018 | |
| PWC | https://paperswithcode.com/paper/a-method-for-in-depth-comparative-evaluation |
| Repo | |
| Framework | |
Catching the Common Cause: Extraction and Annotation of Causal Relations and their Participants
| Title | Catching the Common Cause: Extraction and Annotation of Causal Relations and their Participants |
| Authors | Ines Rehbein, Josef Ruppenhofer |
| Abstract | In this paper, we present a simple, yet effective method for the automatic identification and extraction of causal relations from text, based on a large English-German parallel corpus. The goal of this effort is to create a lexical resource for German causal relations. The resource will consist of a lexicon that describes constructions that trigger causality as well as the participants of the causal event, and will be augmented by a corpus with annotated instances for each entry, that can be used as training data to develop a system for automatic classification of causal relations. Focusing on verbs, our method harvested a set of 100 different lexical triggers of causality, including support verb constructions. At the moment, our corpus includes over 1,000 annotated instances. The lexicon and the annotated data will be made available to the research community. |
| Tasks | Language Modelling |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0813/ |
| https://www.aclweb.org/anthology/W17-0813 | |
| PWC | https://paperswithcode.com/paper/catching-the-common-cause-extraction-and |
| Repo | |
| Framework | |
Neural Semantic Parsing with Type Constraints for Semi-Structured Tables
| Title | Neural Semantic Parsing with Type Constraints for Semi-Structured Tables |
| Authors | Jayant Krishnamurthy, Pradeep Dasigi, Matt Gardner |
| Abstract | We present a new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables. Our parser is an encoder-decoder neural network with two key technical innovations: (1) a grammar for the decoder that only generates well-typed logical forms; and (2) an entity embedding and linking module that identifies entity mentions while generalizing across tables. We also introduce a novel method for training our neural model with question-answer supervision. On the WikiTableQuestions data set, our parser achieves a state-of-the-art accuracy of 43.3{%} for a single model and 45.9{%} for a 5-model ensemble, improving on the best prior score of 38.7{%} set by a 15-model ensemble. These results suggest that type constraints and entity linking are valuable components to incorporate in neural semantic parsers. |
| Tasks | Entity Linking, Question Answering, Semantic Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1160/ |
| https://www.aclweb.org/anthology/D17-1160 | |
| PWC | https://paperswithcode.com/paper/neural-semantic-parsing-with-type-constraints |
| Repo | |
| Framework | |
Neuramanteau: A Neural Network Ensemble Model for Lexical Blends
| Title | Neuramanteau: A Neural Network Ensemble Model for Lexical Blends |
| Authors | Kollol Das, Shaona Ghosh |
| Abstract | The problem of blend formation in generative linguistics is interesting in the context of neologism, their quick adoption in modern life and the creative generative process guiding their formation. Blend quality depends on multitude of factors with high degrees of uncertainty. In this work, we investigate if the modern neural network models can sufficiently capture and recognize the creative blend composition process. We propose recurrent neural network sequence-to-sequence models, that are evaluated on multiple blend datasets available in the literature. We propose an ensemble neural and hybrid model that outperforms most of the baselines and heuristic models upon evaluation on test data. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1058/ |
| https://www.aclweb.org/anthology/I17-1058 | |
| PWC | https://paperswithcode.com/paper/neuramanteau-a-neural-network-ensemble-model |
| Repo | |
| Framework | |
Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification
| Title | Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification |
| Authors | Jianfei Yu, Jing Jiang |
| Abstract | In this paper, we study domain adaptation with a state-of-the-art hierarchical neural network for document-level sentiment classification. We first design a new auxiliary task based on sentiment scores of domain-independent words. We then propose two neural network architectures to respectively induce document embeddings and sentence embeddings that work well for different domains. When these document and sentence embeddings are used for sentiment classification, we find that with both pseudo and external sentiment lexicons, our proposed methods can perform similarly to or better than several highly competitive domain adaptation methods on a benchmark dataset of product reviews. |
| Tasks | Denoising, Domain Adaptation, Opinion Mining, Sentence Embeddings, Sentiment Analysis |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1066/ |
| https://www.aclweb.org/anthology/I17-1066 | |
| PWC | https://paperswithcode.com/paper/leveraging-auxiliary-tasks-for-document-level |
| Repo | |
| Framework | |
