Paper Group NANR 230
Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate. Identification of Adverse Drug Reaction Mentions in Tweets – SMM4H Shared Task 2019. ltl.uni-due at SemEval-2019 Task 5: Simple but Effective Lexico-Semantic Features for Detecting Hate Speech in Twitter. A Personalized Sentiment Model with Textual a …
Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate
| Title | Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate |
| Authors | James Jordon, Jinsung Yoon, Mihaela Van Der Schaar |
| Abstract | Differential Privacy is a popular and well-studied notion of privacy. In the era ofbig data that we are in, privacy concerns are becoming ever more prevalent and thusdifferential privacy is being turned to as one such solution. A popular method forensuring differential privacy of a classifier is known as subsample-and-aggregate,in which the dataset is divided into distinct chunks and a model is learned on eachchunk, after which it is aggregated. This approach allows for easy analysis of themodel on the data and thus differential privacy can be easily applied. In this paper,we extend this approach by dividing the data several times (rather than just once)and learning models on each chunk within each division. The first benefit of thisapproach is the natural improvement of utility by aggregating models trained ona more diverse range of subsets of the data (as demonstrated by the well-knownbagging technique). The second benefit is that, through analysis that we provide inthe paper, we can derive tighter differential privacy guarantees when several queriesare made to this mechanism. In order to derive these guarantees, we introducethe upwards and downwards moments accountants and derive bounds for thesemoments accountants in a data-driven fashion. We demonstrate the improvementsour model makes over standard subsample-and-aggregate in two datasets (HeartFailure (private) and UCI Adult (public)). |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8684-differentially-private-bagging-improved-utility-and-cheaper-privacy-than-subsample-and-aggregate |
| http://papers.nips.cc/paper/8684-differentially-private-bagging-improved-utility-and-cheaper-privacy-than-subsample-and-aggregate.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-bagging-improved |
| Repo | |
| Framework | |
Identification of Adverse Drug Reaction Mentions in Tweets – SMM4H Shared Task 2019
| Title | Identification of Adverse Drug Reaction Mentions in Tweets – SMM4H Shared Task 2019 |
| Authors | Samarth Rawal, Siddharth Rawal, Saadat Anwar, Chitta Baral |
| Abstract | Analyzing social media posts can offer insights into a wide range of topics that are commonly discussed online, providing valuable information for studying various health-related phenomena reported online. The outcome of this work can offer insights into pharmacovigilance research to monitor the adverse effects of medications. This research specifically looks into mentions of adverse drug reactions (ADRs) in Twitter data through the Social Media Mining for Health Applications (SMM4H) Shared Task 2019. Adverse drug reactions are undesired harmful effects which can arise from medication or other methods of treatment. The goal of this research is to build accurate models using natural language processing techniques to detect reports of adverse drug reactions in Twitter data and extract these words or phrases. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3225/ |
| https://www.aclweb.org/anthology/W19-3225 | |
| PWC | https://paperswithcode.com/paper/identification-of-adverse-drug-reaction |
| Repo | |
| Framework | |
ltl.uni-due at SemEval-2019 Task 5: Simple but Effective Lexico-Semantic Features for Detecting Hate Speech in Twitter
| Title | ltl.uni-due at SemEval-2019 Task 5: Simple but Effective Lexico-Semantic Features for Detecting Hate Speech in Twitter |
| Authors | Huangpan Zhang, Michael Wojatzki, Tobias Horsmann, Torsten Zesch |
| Abstract | In this paper, we present our contribution to SemEval 2019 Task 5 Multilingual Detection of Hate, specifically in the Subtask A (English and Spanish). We compare different configurations of shallow and deep learning approaches on the English data and use the system that performs best in both sub-tasks. The resulting SVM-based system with lexicosemantic features (n-grams and embeddings) is ranked 23rd out of 69 on the English data and beats the baseline system. On the Spanish data our system is ranked 25th out of 39. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2078/ |
| https://www.aclweb.org/anthology/S19-2078 | |
| PWC | https://paperswithcode.com/paper/ltluni-due-at-semeval-2019-task-5-simple-but |
| Repo | |
| Framework | |
A Personalized Sentiment Model with Textual and Contextual Information
| Title | A Personalized Sentiment Model with Textual and Contextual Information |
| Authors | Siwen Guo, Sviatlana H{"o}hn, Christoph Schommer |
| Abstract | In this paper, we look beyond the traditional population-level sentiment modeling and consider the individuality in a person{'}s expressions by discovering both textual and contextual information. In particular, we construct a hierarchical neural network that leverages valuable information from a person{'}s past expressions, and offer a better understanding of the sentiment from the expresser{'}s perspective. Additionally, we investigate how a person{'}s sentiment changes over time so that recent incidents or opinions may have more effect on the person{'}s current sentiment than the old ones. Psychological studies have also shown that individual variation exists in how easily people change their sentiments. In order to model such traits, we develop a modified attention mechanism with Hawkes process applied on top of a recurrent network for a user-specific design. Implemented with automatically labeled Twitter data, the proposed model has shown positive results employing different input formulations for representing the concerned information. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1093/ |
| https://www.aclweb.org/anthology/K19-1093 | |
| PWC | https://paperswithcode.com/paper/a-personalized-sentiment-model-with-textual |
| Repo | |
| Framework | |
Spelling-Aware Construction of Macaronic Texts for Teaching Foreign-Language Vocabulary
| Title | Spelling-Aware Construction of Macaronic Texts for Teaching Foreign-Language Vocabulary |
| Authors | Adithya Renduchintala, Philipp Koehn, Jason Eisner |
| Abstract | We present a machine foreign-language teacher that modifies text in a student{'}s native language (L1) by replacing some word tokens with glosses in a foreign language (L2), in such a way that the student can acquire L2 vocabulary simply by reading the resulting macaronic text. The machine teacher uses no supervised data from human students. Instead, to guide the machine teacher{'}s choice of which words to replace, we equip a cloze language model with a training procedure that can incrementally learn representations for novel words, and use this model as a proxy for the word guessing and learning ability of real human students. We use Mechanical Turk to evaluate two variants of the student model: (i) one that generates a representation for a novel word using only surrounding context and (ii) an extension that also uses the spelling of the novel word. |
| Tasks | Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1679/ |
| https://www.aclweb.org/anthology/D19-1679 | |
| PWC | https://paperswithcode.com/paper/spelling-aware-construction-of-macaronic |
| Repo | |
| Framework | |
Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model
| Title | Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model |
| Authors | Andrea Zanette, Mykel J. Kochenderfer, Emma Brunskill |
| Abstract | This paper focuses on the problem of computing an $\epsilon$-optimal policy in a discounted Markov Decision Process (MDP) provided that we can access the reward and transition function through a generative model. We propose an algorithm that is initially agnostic to the MDP but that can leverage the specific MDP structure, expressed in terms of variances of the rewards and next-state value function, and gaps in the optimal action-value function to reduce the sample complexity needed to find a good policy, precisely highlighting the contribution of each state-action pair to the final sample complexity. A key feature of our analysis is that it removes all horizon dependencies in the sample complexity of suboptimal actions except for the intrinsic scaling of the value function and a constant additive term. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8800-almost-horizon-free-structure-aware-best-policy-identification-with-a-generative-model |
| http://papers.nips.cc/paper/8800-almost-horizon-free-structure-aware-best-policy-identification-with-a-generative-model.pdf | |
| PWC | https://paperswithcode.com/paper/almost-horizon-free-structure-aware-best |
| Repo | |
| Framework | |
YNU NLP at SemEval-2019 Task 5: Attention and Capsule Ensemble for Identifying Hate Speech
| Title | YNU NLP at SemEval-2019 Task 5: Attention and Capsule Ensemble for Identifying Hate Speech |
| Authors | Bin Wang, Haiyan Ding |
| Abstract | This paper describes the system submitted to SemEval 2019 Task 5: Multilingual detection of hate speech against immigrants and women in Twitter (hatEval). Its main purpose is to conduct hate speech detection on Twitter, which mainly includes two specific different targets, immigrants and women. We participate in both subtask A and subtask B for English. In order to address this task, we develope an ensemble of an attention-LSTM model based on HAN and an BiGRU-capsule model. Both models use fastText pre-trained embeddings, and we use this model in both subtasks. In comparison to other participating teams, our system is ranked 16th in the Sub-task A for English, and 12th in the Sub-task B for English. |
| Tasks | Hate Speech Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2095/ |
| https://www.aclweb.org/anthology/S19-2095 | |
| PWC | https://paperswithcode.com/paper/ynu-nlp-at-semeval-2019-task-5-attention-and |
| Repo | |
| Framework | |
Controlling the Specificity of Clarification Question Generation
| Title | Controlling the Specificity of Clarification Question Generation |
| Authors | Yang Trista Cao, Sudha Rao, Hal Daum{'e} III |
| Abstract | Unlike comprehension-style questions, clarification questions look for some missing information in a given context. However, without guidance, neural models for question generation, similar to dialog generation models, lead to generic and bland questions that cannot elicit useful information. We argue that controlling the level of specificity of the generated questions can have useful applications and propose a neural clarification question generation model for the same. We first train a classifier that annotates a clarification question with its level of specificity (generic or specific) to the given context. Our results on the Amazon questions dataset demonstrate that training a clarification question generation model on specificity annotated data can generate questions with varied levels of specificity to the given context. |
| Tasks | Question Generation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3619/ |
| https://www.aclweb.org/anthology/W19-3619 | |
| PWC | https://paperswithcode.com/paper/controlling-the-specificity-of-clarification |
| Repo | |
| Framework | |
SILCO: Show a Few Images, Localize the Common Object
| Title | SILCO: Show a Few Images, Localize the Common Object |
| Authors | Tao Hu, Pascal Mettes, Jia-Hong Huang, Cees G. M. Snoek |
| Abstract | Few-shot learning is a nascent research topic, motivated by the fact that traditional deep learning requires tremendous amounts of data. In this work, we propose a new task along this research direction, we call few-shot common-localization. Given a few weakly-supervised support images, we aim to localize the common object in the query image without any box annotation. This task differs from standard few-shot settings, since we aim to address the localization problem, rather than the global classification problem. To tackle this new problem, we propose a network that aims to get the most out of the support and query images. To that end, we introduce a spatial similarity module that searches the spatial commonality among the given images. We furthermore introduce a feature reweighting module to balance the influence of different support images through graph convolutional networks. To evaluate few-shot common-localization, we repurpose and reorganize the well-known Pascal VOC and MS-COCO datasets, as well as a video dataset from ImageNet VID. Experiments on the new settings for few-shot common-localization shows the importance of searching for spatial similarity and feature reweighting, outperforming baselines from related tasks. |
| Tasks | Few-Shot Learning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Hu_SILCO_Show_a_Few_Images_Localize_the_Common_Object_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Hu_SILCO_Show_a_Few_Images_Localize_the_Common_Object_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/silco-show-a-few-images-localize-the-common |
| Repo | |
| Framework | |
The ERG at MRP 2019: Radically Compositional Semantic Dependencies
| Title | The ERG at MRP 2019: Radically Compositional Semantic Dependencies |
| Authors | Stephan Oepen, Dan Flickinger |
| Abstract | The English Resource Grammar (ERG) is a broad-coverage computational grammar of English that outputs underspecified logical-form representations of meaning in a framework dubbed English Resource Semantics (ERS). Two of the target representations in the the 2019 Shared Task on Cross-Framework Meaning Representation Parsing (MRP 2019) derive graph-based simplifications of ERS, viz. Elementary Dependency Structures (EDS) and DELPH-IN MRS Bi-Lexical Dependencies (DM). As a point of reference outside the official MRP competition, we parsed the evaluation strings using the ERG and converted the resulting meaning representations to EDS and DM. These graphs yield higher evaluation scores than the purely data-driven parsers in the actual shared task, suggesting that the general-purpose linguistic knowledge about English grammar encoded in the ERG can add value when parsing into these meaning representations. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2003/ |
| https://www.aclweb.org/anthology/K19-2003 | |
| PWC | https://paperswithcode.com/paper/the-erg-at-mrp-2019-radically-compositional |
| Repo | |
| Framework | |
ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing
| Title | ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing |
| Authors | Xinyu Wang, Yixian Liu, Zixia Jia, Chengyue Jiang, Kewei Tu |
| Abstract | This paper presents the system used in our submission to the CoNLL 2019 shared task: Cross-Framework Meaning Representation Parsing. Our system is a graph-based parser which combines an extended pointer-generator network that generates nodes and a second-order mean field variational inference module that predicts edges. Our system achieved 1st and 2nd place for the DM and PSD frameworks respectively on the in-framework ranks and achieved 3rd place for the DM framework on the cross-framework ranks. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2005/ |
| https://www.aclweb.org/anthology/K19-2005 | |
| PWC | https://paperswithcode.com/paper/shanghaitech-at-mrp-2019-sequence-to-graph |
| Repo | |
| Framework | |
A Primal-Dual link between GANs and Autoencoders
| Title | A Primal-Dual link between GANs and Autoencoders |
| Authors | Hisham Husain, Richard Nock, Robert C. Williamson |
| Abstract | Since the introduction of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE), the literature on generative modelling has witnessed an overwhelming resurgence. The impressive, yet elusive empirical performance of GANs has lead to the rise of many GAN-VAE hybrids, with the hopes of GAN level performance and additional benefits of VAE, such as an encoder for feature reduction, which is not offered by GANs. Recently, the Wasserstein Autoencoder (WAE) was proposed, achieving performance similar to that of GANs, yet it is still unclear whether the two are fundamentally different or can be further improved into a unified model. In this work, we study the $f$-GAN and WAE models and make two main discoveries. First, we find that the $f$-GAN and WAE objectives partake in a primal-dual relationship and are equivalent under some assumptions, which then allows us to explicate the success of WAE. Second, the equivalence result allows us to, for the first time, prove generalization bounds for Autoencoder models, which is a pertinent problem when it comes to theoretical analyses of generative models. Furthermore, we show that the WAE objective is related to other statistical quantities such as the $f$-divergence and in particular, upper bounded by the Wasserstein distance, which then allows us to tap into existing efficient (regularized) optimal transport solvers. Our findings thus present the first primal-dual relationship between GANs and Autoencoder models, comment on generalization abilities and make a step towards unifying these models. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8333-a-primal-dual-link-between-gans-and-autoencoders |
| http://papers.nips.cc/paper/8333-a-primal-dual-link-between-gans-and-autoencoders.pdf | |
| PWC | https://paperswithcode.com/paper/a-primal-dual-link-between-gans-and |
| Repo | |
| Framework | |
Learning to Ask for Conversational Machine Learning
| Title | Learning to Ask for Conversational Machine Learning |
| Authors | Shashank Srivastava, Igor Labutov, Tom Mitchell |
| Abstract | Natural language has recently been explored as a new medium of supervision for training machine learning models. Here, we explore learning classification tasks using language in a conversational setting {–} where the automated learner does not simply receive language input from a teacher, but can proactively engage the teacher by asking questions. We present a reinforcement learning framework, where the learner{'}s actions correspond to question types and the reward for asking a question is based on how the teacher{'}s response changes performance of the resulting machine learning model on the learning task. In this framework, learning good question-asking strategies corresponds to asking sequences of questions that maximize the cumulative (discounted) reward, and hence quickly lead to effective classifiers. Empirical analysis across three domains shows that learned question-asking strategies expedite classifier training by asking appropriate questions at different points in the learning process. The approach allows learning classifiers from a blend of strategies, including learning from observations, explanations and clarifications. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1426/ |
| https://www.aclweb.org/anthology/D19-1426 | |
| PWC | https://paperswithcode.com/paper/learning-to-ask-for-conversational-machine |
| Repo | |
| Framework | |
Low-Rank Approximations of Second-Order Document Representations
| Title | Low-Rank Approximations of Second-Order Document Representations |
| Authors | Jarkko Lagus, Janne Sinkkonen, Arto Klami |
| Abstract | Document embeddings, created with methods ranging from simple heuristics to statistical and deep models, are widely applicable. Bag-of-vectors models for documents include the mean and quadratic approaches (Torki, 2018). We present evidence that quadratic statistics alone, without the mean information, can offer superior accuracy, fast document comparison, and compact document representations. In matching news articles to their comment threads, low-rank representations of only 3-4 times the size of the mean vector give most accurate matching, and in standard sentence comparison tasks, results are state of the art despite faster computation. Similarity measures are discussed, and the Frobenius product implicit in the proposed method is contrasted to Wasserstein or Bures metric from the transportation theory. We also shortly demonstrate matching of unordered word lists to documents, to measure topicality or sentiment of documents. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1059/ |
| https://www.aclweb.org/anthology/K19-1059 | |
| PWC | https://paperswithcode.com/paper/low-rank-approximations-of-second-order |
| Repo | |
| Framework | |
GenSMT at SemEval-2019 Task 3: Contextual Emotion Detection in tweets using multi task generic approach
| Title | GenSMT at SemEval-2019 Task 3: Contextual Emotion Detection in tweets using multi task generic approach |
| Authors | Dumitru Bogdan |
| Abstract | In this paper, we describe our participation in SemEval-2019 Task 3: EmoContext - A Shared Task on Contextual Emotion Detection in Text. We propose a three layer model with a generic, multi-purpose approach that without any task specific optimizations achieve competitive results (f1 score of 0.7096) in the EmoContext task. We describe our development strategy in detail along with an exposition of our results. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2037/ |
| https://www.aclweb.org/anthology/S19-2037 | |
| PWC | https://paperswithcode.com/paper/gensmt-at-semeval-2019-task-3-contextual |
| Repo | |
| Framework | |
