Paper Group NANR 184
Minimizing a Submodular Function from Samples. An Empirical Study on End-to-End Sentence Modelling. NLP for Precision Medicine. Consistent Classification of Translation Revisions: A Case Study of English-Japanese Student Translations. Adaptive Sampling Probabilities for Non-Smooth Optimization. Variable Importance Using Decision Trees. Neural Seque …
Minimizing a Submodular Function from Samples
| Title | Minimizing a Submodular Function from Samples |
| Authors | Eric Balkanski, Yaron Singer |
| Abstract | In this paper we consider the problem of minimizing a submodular function from training data. Submodular functions can be efficiently minimized and are conse- quently heavily applied in machine learning. There are many cases, however, in which we do not know the function we aim to optimize, but rather have access to training data that is used to learn the function. In this paper we consider the question of whether submodular functions can be minimized in such cases. We show that even learnable submodular functions cannot be minimized within any non-trivial approximation when given access to polynomially-many samples. Specifically, we show that there is a class of submodular functions with range in [0, 1] such that, despite being PAC-learnable and minimizable in polynomial-time, no algorithm can obtain an approximation strictly better than 1/2 − o(1) using polynomially-many samples drawn from any distribution. Furthermore, we show that this bound is tight using a trivial algorithm that obtains an approximation of 1/2. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6683-minimizing-a-submodular-function-from-samples |
| http://papers.nips.cc/paper/6683-minimizing-a-submodular-function-from-samples.pdf | |
| PWC | https://paperswithcode.com/paper/minimizing-a-submodular-function-from-samples |
| Repo | |
| Framework | |
An Empirical Study on End-to-End Sentence Modelling
| Title | An Empirical Study on End-to-End Sentence Modelling |
| Authors | Kurt Junshean Espinosa |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3021/ |
| https://www.aclweb.org/anthology/P17-3021 | |
| PWC | https://paperswithcode.com/paper/an-empirical-study-on-end-to-end-sentence |
| Repo | |
| Framework | |
NLP for Precision Medicine
| Title | NLP for Precision Medicine |
| Authors | Hoifung Poon, Chris Quirk, Kristina Toutanova, Wen-tau Yih |
| Abstract | We will introduce precision medicine and showcase the vast opportunities for NLP in this burgeoning field with great societal impact. We will review pressing NLP problems, state-of-the art methods, and important applications, as well as datasets, medical resources, and practical issues. The tutorial will provide an accessible overview of biomedicine, and does not presume knowledge in biology or healthcare. The ultimate goal is to reduce the entry barrier for NLP researchers to contribute to this exciting domain. |
| Tasks | Decision Making, Entity Linking, Relation Extraction, Semantic Parsing |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-5001/ |
| https://www.aclweb.org/anthology/P17-5001 | |
| PWC | https://paperswithcode.com/paper/nlp-for-precision-medicine |
| Repo | |
| Framework | |
Consistent Classification of Translation Revisions: A Case Study of English-Japanese Student Translations
| Title | Consistent Classification of Translation Revisions: A Case Study of English-Japanese Student Translations |
| Authors | Atsushi Fujita, Kikuko Tanabe, Chiho Toyoshima, Mayuka Yamamoto, Kyo Kageura, Anthony Hartley |
| Abstract | Consistency is a crucial requirement in text annotation. It is especially important in educational applications, as lack of consistency directly affects learners{'} motivation and learning performance. This paper presents a quality assessment scheme for English-to-Japanese translations produced by learner translators at university. We constructed a revision typology and a decision tree manually through an application of the OntoNotes method, i.e., an iteration of assessing learners{'} translations and hypothesizing the conditions for consistent decision making, as well as re-organizing the typology. Intrinsic evaluation of the created scheme confirmed its potential contribution to the consistent classification of identified erroneous text spans, achieving visibly higher Cohen{'}s kappa values, up to 0.831, than previous work. This paper also describes an application of our scheme to an English-to-Japanese translation exercise course for undergraduate students at a university in Japan. |
| Tasks | Decision Making |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0807/ |
| https://www.aclweb.org/anthology/W17-0807 | |
| PWC | https://paperswithcode.com/paper/consistent-classification-of-translation-1 |
| Repo | |
| Framework | |
Adaptive Sampling Probabilities for Non-Smooth Optimization
| Title | Adaptive Sampling Probabilities for Non-Smooth Optimization |
| Authors | Hongseok Namkoong, Aman Sinha, Steve Yadlowsky, John C. Duchi |
| Abstract | Standard forms of coordinate and stochastic gradient methods do not adapt to structure in data; their good behavior under random sampling is predicated on uniformity in data. When gradients in certain blocks of features (for coordinate descent) or examples (for SGD) are larger than others, there is a natural structure that can be exploited for quicker convergence. Yet adaptive variants often suffer nontrivial computational overhead. We present a framework that discovers and leverages such structural properties at a low computational cost. We employ a bandit optimization procedure that “learns” probabilities for sampling coordinates or examples in (non-smooth) optimization problems, allowing us to guarantee performance close to that of the optimal stationary sampling distribution. When such structures exist, our algorithms achieve tighter convergence guarantees than their non-adaptive counterparts, and we complement our analysis with experiments on several datasets. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=562 |
| http://proceedings.mlr.press/v70/namkoong17a/namkoong17a.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-sampling-probabilities-for-non |
| Repo | |
| Framework | |
Variable Importance Using Decision Trees
| Title | Variable Importance Using Decision Trees |
| Authors | Jalil Kazemitabar, Arash Amini, Adam Bloniarz, Ameet S. Talwalkar |
| Abstract | Decision trees and random forests are well established models that not only offer good predictive performance, but also provide rich feature importance information. While practitioners often employ variable importance methods that rely on this impurity-based information, these methods remain poorly characterized from a theoretical perspective. We provide novel insights into the performance of these methods by deriving finite sample performance guarantees in a high-dimensional setting under various modeling assumptions. We further demonstrate the effectiveness of these impurity-based methods via an extensive set of simulations. |
| Tasks | Feature Importance |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6646-variable-importance-using-decision-trees |
| http://papers.nips.cc/paper/6646-variable-importance-using-decision-trees.pdf | |
| PWC | https://paperswithcode.com/paper/variable-importance-using-decision-trees |
| Repo | |
| Framework | |
Neural Sequence-Labelling Models for Grammatical Error Correction
| Title | Neural Sequence-Labelling Models for Grammatical Error Correction |
| Authors | Helen Yannakoudakis, Marek Rei, {\O}istein E. Andersen, Zheng Yuan |
| Abstract | We propose an approach to N-best list reranking using neural sequence-labelling models. We train a compositional model for error detection that calculates the probability of each token in a sentence being correct or incorrect, utilising the full sentence as context. Using the error detection model, we then re-rank the N best hypotheses generated by statistical machine translation systems. Our approach achieves state-of-the-art results on error correction for three different datasets, and it has the additional advantage of only using a small set of easily computed features that require no linguistic input. |
| Tasks | Grammatical Error Correction, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1297/ |
| https://www.aclweb.org/anthology/D17-1297 | |
| PWC | https://paperswithcode.com/paper/neural-sequence-labelling-models-for |
| Repo | |
| Framework | |
Linguistically Regularized LSTM for Sentiment Classification
| Title | Linguistically Regularized LSTM for Sentiment Classification |
| Authors | Qiao Qian, Minlie Huang, Jinhao Lei, Xiaoyan Zhu |
| Abstract | This paper deals with sentence-level sentiment classification. Though a variety of neural network models have been proposed recently, however, previous models either depend on expensive phrase-level annotation, most of which has remarkably degraded performance when trained with only sentence-level annotation; or do not fully employ linguistic resources (e.g., sentiment lexicons, negation words, intensity words). In this paper, we propose simple models trained with sentence-level annotation, but also attempt to model the linguistic role of sentiment lexicons, negation words, and intensity words. Results show that our models are able to capture the linguistic role of sentiment words, negation words, and intensity words in sentiment expression. |
| Tasks | Sentiment Analysis |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1154/ |
| https://www.aclweb.org/anthology/P17-1154 | |
| PWC | https://paperswithcode.com/paper/linguistically-regularized-lstm-for-sentiment |
| Repo | |
| Framework | |
Neural Architectures for Multilingual Semantic Parsing
| Title | Neural Architectures for Multilingual Semantic Parsing |
| Authors | Raymond Hendy Susanto, Wei Lu |
| Abstract | In this paper, we address semantic parsing in a multilingual context. We train one multilingual model that is capable of parsing natural language sentences from multiple different languages into their corresponding formal semantic representations. We extend an existing sequence-to-tree model to a multi-task learning framework which shares the decoder for generating semantic representations. We report evaluation results on the multilingual GeoQuery corpus and introduce a new multilingual version of the ATIS corpus. |
| Tasks | Machine Translation, Multi-Task Learning, Semantic Parsing |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2007/ |
| https://www.aclweb.org/anthology/P17-2007 | |
| PWC | https://paperswithcode.com/paper/neural-architectures-for-multilingual |
| Repo | |
| Framework | |
Tutorial: Making Better Use of the Crowd
| Title | Tutorial: Making Better Use of the Crowd |
| Authors | Jennifer Wortman Vaughan |
| Abstract | Over the last decade, crowdsourcing has been used to harness the power of human computation to solve tasks that are notoriously difficult to solve with computers alone, such as determining whether or not an image contains a tree, rating the relevance of a website, or verifying the phone number of a business. The natural language processing community was early to embrace crowdsourcing as a tool for quickly and inexpensively obtaining annotated data to train NLP systems. Once this data is collected, it can be handed off to algorithms that learn to perform basic NLP tasks such as translation or parsing. Usually this handoff is where interaction with the crowd ends. The crowd provides the data, but the ultimate goal is to eventually take humans out of the loop. Are there better ways to make use of the crowd?In this tutorial, I will begin with a showcase of innovative uses of crowdsourcing that go beyond data collection and annotation. I will discuss applications to natural language processing and machine learning, hybrid intelligence or {``}human in the loop{''} AI systems that leverage the complementary strengths of humans and machines in order to achieve more than either could achieve alone, and large scale studies of human behavior online. I will then spend the majority of the tutorial diving into recent research aimed at understanding who crowdworkers are, how they behave, and what this should teach us about best practices for interacting with the crowd. | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-5006/ |
| https://www.aclweb.org/anthology/P17-5006 | |
| PWC | https://paperswithcode.com/paper/tutorial-making-better-use-of-the-crowd |
| Repo | |
| Framework | |
Lightly-Supervised Modeling of Argument Persuasiveness
| Title | Lightly-Supervised Modeling of Argument Persuasiveness |
| Authors | Isaac Persing, Vincent Ng |
| Abstract | We propose the first lightly-supervised approach to scoring an argument{'}s persuasiveness. Key to our approach is the novel hypothesis that lightly-supervised persuasiveness scoring is possible by explicitly modeling the major errors that negatively impact persuasiveness. In an evaluation on a new annotated corpus of online debate arguments, our approach rivals its fully-supervised counterparts in performance by four scoring metrics when using only 10{%} of the available training instances. |
| Tasks | Argument Mining |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1060/ |
| https://www.aclweb.org/anthology/I17-1060 | |
| PWC | https://paperswithcode.com/paper/lightly-supervised-modeling-of-argument |
| Repo | |
| Framework | |
Texture image retrieval using DTCWT-SVD and local binary pattern features
| Title | Texture image retrieval using DTCWT-SVD and local binary pattern features |
| Authors | Dayou, Jiang; Jongweon, Kim |
| Abstract | The combination texture feature extraction approach for texture image retrieval is proposed in this paper. Two kinds of low-level texture features were combined in the approach. One of them was extracted from singular value decomposition (SVD) based dual-tree complex wavelet transform (DTCWT) coefficients, and the other one was extracted from multi-scale local binary patterns (LBPs). The fusion features of SVD based multi-directional wavelet features and multi-scale LBP features have short dimensions of the feature vector. The comparing experiments are conducted on Brodatz and Vistex datasets. According to the experimental results, the proposed method has a relatively better performance in aspect of retrieval accuracy and time complexity upon the existing methods. |
| Tasks | Image Retrieval, Texture Image Retrieval |
| Published | 2017-12-01 |
| URL | http://jips-k.org/q.jips?cp=pp&pn=523 |
| http://jips-k.org/q.jips?cp=pp&pn=523 | |
| PWC | https://paperswithcode.com/paper/texture-image-retrieval-using-dtcwt-svd-and |
| Repo | |
| Framework | |
Alignment at Work: Using Language to Distinguish the Internalization and Self-Regulation Components of Cultural Fit in Organizations
| Title | Alignment at Work: Using Language to Distinguish the Internalization and Self-Regulation Components of Cultural Fit in Organizations |
| Authors | Gabriel Doyle, Amir Goldberg, Sameer Srivastava, Michael Frank |
| Abstract | Cultural fit is widely believed to affect the success of individuals and the groups to which they belong. Yet it remains an elusive, poorly measured construct. Recent research draws on computational linguistics to measure cultural fit but overlooks asymmetries in cultural adaptation. By contrast, we develop a directed, dynamic measure of cultural fit based on linguistic alignment, which estimates the influence of one person{'}s word use on another{'}s and distinguishes between two enculturation mechanisms: internalization and self-regulation. We use this measure to trace employees{'} enculturation trajectories over a large, multi-year corpus of corporate emails and find that patterns of alignment in the first six months of employment are predictive of individuals{'} downstream outcomes, especially involuntary exit. Further predictive analyses suggest referential alignment plays an overlooked role in linguistic alignment. |
| Tasks | Language Modelling |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1056/ |
| https://www.aclweb.org/anthology/P17-1056 | |
| PWC | https://paperswithcode.com/paper/alignment-at-work-using-language-to |
| Repo | |
| Framework | |
Spindle Net: Person Re-Identification With Human Body Region Guided Feature Decomposition and Fusion
| Title | Spindle Net: Person Re-Identification With Human Body Region Guided Feature Decomposition and Fusion |
| Authors | Haiyu Zhao, Maoqing Tian, Shuyang Sun, Jing Shao, Junjie Yan, Shuai Yi, Xiaogang Wang, Xiaoou Tang |
| Abstract | Person re-identification (ReID) is an important task in video surveillance and has various applications. It is non-trivial due to complex background clutters, varying illumination conditions, and uncontrollable camera settings. Moreover, the person body misalignment caused by detectors or pose variations is sometimes too severe for feature matching across images. In this study, we propose a novel Convolutional Neural Network (CNN), called Spindle Net, based on human body region guided multi-stage feature decomposition and tree-structured competitive feature fusion. It is the first time human body structure information is considered in a CNN framework to facilitate feature learning. The proposed Spindle Net brings unique advantages: 1) it separately captures semantic features from different body regions thus the macro- and micro-body features can be well aligned across images, 2) the learned region features from different semantic regions are merged with a competitive scheme and discriminative features can be well preserved. State of the art performance can be achieved on multiple datasets by large margins. We further demonstrate the robustness and effectiveness of the proposed Spindle Net on our proposed dataset SenseReID without fine-tuning. |
| Tasks | Person Re-Identification |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Zhao_Spindle_Net_Person_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhao_Spindle_Net_Person_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spindle-net-person-re-identification-with |
| Repo | |
| Framework | |
Learning with learner corpora: Using the TLE for native language identification
| Title | Learning with learner corpora: Using the TLE for native language identification |
| Authors | Allison Adams, Sara Stymne |
| Abstract | |
| Tasks | Language Acquisition, Language Identification, Native Language Identification, Text Classification |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0301/ |
| https://www.aclweb.org/anthology/W17-0301 | |
| PWC | https://paperswithcode.com/paper/learning-with-learner-corpora-using-the-tle |
| Repo | |
| Framework | |
