Paper Group ANR 582
Conversational Networks for Automatic Online Moderation. Understanding the Information needs of Social Scientists in Germany. Negative Training for Neural Dialogue Response Generation. Kernel absolute summability is only sufficient for RKHS stability. A Dynamic Strategy Coach for Effective Negotiation. MetaFun: Meta-Learning with Iterative Function …
Conversational Networks for Automatic Online Moderation
| Title | Conversational Networks for Automatic Online Moderation |
| Authors | Etienne Papegnies, Vincent Labatut, Richard Dufour, Georges Linares |
| Abstract | Moderation of user-generated content in an online community is a challenge that has great socio-economical ramifications. However, the costs incurred by delegating this work to human agents are high. For this reason, an automatic system able to detect abuse in user-generated content is of great interest. There are a number of ways to tackle this problem, but the most commonly seen in practice are word filtering or regular expression matching. The main limitations are their vulnerability to intentional obfuscation on the part of the users, and their context-insensitive nature. Moreover, they are language-dependent and may require appropriate corpora for training. In this paper, we propose a system for automatic abuse detection that completely disregards message content. We first extract a conversational network from raw chat logs and characterize it through topological measures. We then use these as features to train a classifier on our abuse detection task. We thoroughly assess our system on a dataset of user comments originating from a French Massively Multiplayer Online Game. We identify the most appropriate network extraction parameters and discuss the discriminative power of our features, relatively to their topological and temporal nature. Our method reaches an F-measure of 83.89 when using the full feature set, improving on existing approaches. With a selection of the most discriminative features, we dramatically cut computing time while retaining most of the performance (82.65). |
| Tasks | Abuse Detection |
| Published | 2019-01-31 |
| URL | http://arxiv.org/abs/1901.11281v1 |
| http://arxiv.org/pdf/1901.11281v1.pdf | |
| PWC | https://paperswithcode.com/paper/conversational-networks-for-automatic-online |
| Repo | |
| Framework | |
Understanding the Information needs of Social Scientists in Germany
| Title | Understanding the Information needs of Social Scientists in Germany |
| Authors | Dagmar Kern, Daniel Hienert |
| Abstract | The information needs of social science researchers are manifold and almost studied in every decade since the 1950s. With this paper, we contribute to this series and present the results of three studies. We asked 367 social science researchers in Germany for their information needs and identified needs in different categories: literature, research data, measurement instruments, support for data analysis, support for data collection, variables in research data, software support, networking/cooperation, and illustrative material. Thereby, the search for literature and research data is still the main information need with more than three-quarter of our participants expressing needs in these categories. With comprehensive lists of altogether 154 concrete information needs, even those that are only expressed by one participant, we contribute to the holistic understanding of the information needs of social science researchers of today. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08876v1 |
| https://arxiv.org/pdf/1909.08876v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-the-information-needs-of-social |
| Repo | |
| Framework | |
Negative Training for Neural Dialogue Response Generation
| Title | Negative Training for Neural Dialogue Response Generation |
| Authors | Tianxing He, James Glass |
| Abstract | Although deep learning models have brought tremendous advancements to the field of open-domain dialogue response generation, recent research results have revealed that the trained models have undesirable generation behaviors, such as malicious responses and generic (boring) responses. In this work, we propose a framework named “Negative Training” to minimize such behaviors. Given a trained model, the framework will first find generated samples that exhibit the undesirable behavior, and then use them to feed negative training signals for fine-tuning the model. Our experiments show that negative training can significantly reduce the hit rate of malicious responses (e.g. from 12.6% to 0%), or discourage frequent responses and improve response diversity (e.g. improve response entropy by over 63%). |
| Tasks | |
| Published | 2019-03-06 |
| URL | https://arxiv.org/abs/1903.02134v2 |
| https://arxiv.org/pdf/1903.02134v2.pdf | |
| PWC | https://paperswithcode.com/paper/negative-training-for-neural-dialogue |
| Repo | |
| Framework | |
Kernel absolute summability is only sufficient for RKHS stability
| Title | Kernel absolute summability is only sufficient for RKHS stability |
| Authors | Mauro Bisiacco, Gianluigi Pillonetto |
| Abstract | Regularized approaches have been successfully applied to linear system identification in recent years. Many of them model unknown impulse responses exploiting the so called Reproducing Kernel Hilbert spaces (RKHSs) that enjoy the notable property of being in one-to-one correspondence with the class of positive semidefinite kernels. The necessary and sufficient condition for a RKHS to be stable, i.e. to contain only BIBO stable linear dynamic systems, has been known in the literature at least since 2006. However, an open question still persists and concerns the equivalence of such condition with the absolute summability of the kernel. This paper provides a definite answer to this matter by proving that such correspondence does not hold. A counterexample is introduced that illustrates the existence of stable RKHSs that are induced by non-absolutely summable kernels. |
| Tasks | |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.02341v1 |
| https://arxiv.org/pdf/1909.02341v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-absolute-summability-is-only |
| Repo | |
| Framework | |
A Dynamic Strategy Coach for Effective Negotiation
| Title | A Dynamic Strategy Coach for Effective Negotiation |
| Authors | Yiheng Zhou, He He, Alan W Black, Yulia Tsvetkov |
| Abstract | Negotiation is a complex activity involving strategic reasoning, persuasion, and psychology. An average person is often far from an expert in negotiation. Our goal is to assist humans to become better negotiators through a machine-in-the-loop approach that combines machine’s advantage at data-driven decision-making and human’s language generation ability. We consider a bargaining scenario where a seller and a buyer negotiate the price of an item for sale through a text-based dialog. Our negotiation coach monitors messages between them and recommends tactics in real time to the seller to get a better deal (e.g., “reject the proposal and propose a price”, “talk about your personal experience with the product”). The best strategy and tactics largely depend on the context (e.g., the current price, the buyer’s attitude). Therefore, we first identify a set of negotiation tactics, then learn to predict the best strategy and tactics in a given dialog context from a set of human-human bargaining dialogs. Evaluation on human-human dialogs shows that our coach increases the profits of the seller by almost 60%. |
| Tasks | Decision Making, Text Generation |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13426v1 |
| https://arxiv.org/pdf/1909.13426v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dynamic-strategy-coach-for-effective |
| Repo | |
| Framework | |
MetaFun: Meta-Learning with Iterative Functional Updates
| Title | MetaFun: Meta-Learning with Iterative Functional Updates |
| Authors | Jin Xu, Jean-Francois Ton, Hyunjik Kim, Adam R. Kosiorek, Yee Whye Teh |
| Abstract | We develop a functional encoder-decoder approach to supervised meta-learning, where labeled data is encoded into an infinite-dimensional functional representation rather than a finite-dimensional one. Furthermore, rather than directly producing the representation, we learn a neural update rule resembling functional gradient descent which iteratively improves the representation. The final representation is used to condition the decoder to make predictions on unlabeled data. Our approach is the first to demonstrates the success of encoder-decoder style meta-learning methods like conditional neural processes on large-scale few-shot classification benchmarks such as miniImageNet and tieredImageNet, where it achieves state-of-the-art performance. |
| Tasks | Few-Shot Image Classification, Meta-Learning |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02738v3 |
| https://arxiv.org/pdf/1912.02738v3.pdf | |
| PWC | https://paperswithcode.com/paper/metafun-meta-learning-with-iterative |
| Repo | |
| Framework | |
Investigating the Effect of Segmentation Methods on Neural Model based Sentiment Analysis on Informal Short Texts in Turkish
| Title | Investigating the Effect of Segmentation Methods on Neural Model based Sentiment Analysis on Informal Short Texts in Turkish |
| Authors | Fatih Kurt, Dilek Kisa, Pinar Karagoz |
| Abstract | This work investigates segmentation approaches for sentiment analysis on informal short texts in Turkish. The two building blocks of the proposed work are segmentation and deep neural network model. Segmentation focuses on preprocessing of text with different methods. These methods are grouped in four: morphological, sub-word, tokenization, and hybrid approaches. We analyzed several variants for each of these four methods. The second stage focuses on evaluation of the neural model for sentiment analysis. The performance of each segmentation method is evaluated under Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) model proposed in the literature for sentiment classification. |
| Tasks | Sentiment Analysis, Tokenization |
| Published | 2019-02-18 |
| URL | http://arxiv.org/abs/1902.06635v1 |
| http://arxiv.org/pdf/1902.06635v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-the-effect-of-segmentation |
| Repo | |
| Framework | |
Multi-modality super-resolution loss for GAN-based super-resolution of clinical CT images using micro CT image database
| Title | Multi-modality super-resolution loss for GAN-based super-resolution of clinical CT images using micro CT image database |
| Authors | Tong Zheng, Hirohisa Oda, Takayasu Moriya, Shota Nakamura, Masahiro Oda, Masaki Mori, Horitsugu Takabatake, Hiroshi Natori, Kensaku Mori |
| Abstract | This paper newly introduces multi-modality loss function for GAN-based super-resolution that can maintain image structure and intensity on unpaired training dataset of clinical CT and micro CT volumes. Precise non-invasive diagnosis of lung cancer mainly utilizes 3D multidetector computed-tomography (CT) data. On the other hand, we can take micro CT images of resected lung specimen in 50 micro meter or higher resolution. However, micro CT scanning cannot be applied to living human imaging. For obtaining highly detailed information such as cancer invasion area from pre-operative clinical CT volumes of lung cancer patients, super-resolution (SR) of clinical CT volumes to $\mu$CT level might be one of substitutive solutions. While most SR methods require paired low- and high-resolution images for training, it is infeasible to obtain precisely paired clinical CT and micro CT volumes. We aim to propose unpaired SR approaches for clincial CT using micro CT images based on unpaired image translation methods such as CycleGAN or UNIT. Since clinical CT and micro CT are very different in structure and intensity, direct application of GAN-based unpaired image translation methods in super-resolution tends to generate arbitrary images. Aiming to solve this problem, we propose new loss function called multi-modality loss function to maintain the similarity of input images and corresponding output images in super-resolution task. Experimental results demonstrated that the newly proposed loss function made CycleGAN and UNIT to successfully perform SR of clinical CT images of lung cancer patients into micro CT level resolution, while original CycleGAN and UNIT failed in super-resolution. |
| Tasks | Computed Tomography (CT), Super-Resolution |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12838v1 |
| https://arxiv.org/pdf/1912.12838v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modality-super-resolution-loss-for-gan |
| Repo | |
| Framework | |
Reflective Decoding Network for Image Captioning
| Title | Reflective Decoding Network for Image Captioning |
| Authors | Lei Ke, Wenjie Pei, Ruiyu Li, Xiaoyong Shen, Yu-Wing Tai |
| Abstract | State-of-the-art image captioning methods mostly focus on improving visual features, less attention has been paid to utilizing the inherent properties of language to boost captioning performance. In this paper, we show that vocabulary coherence between words and syntactic paradigm of sentences are also important to generate high-quality image caption. Following the conventional encoder-decoder framework, we propose the Reflective Decoding Network (RDN) for image captioning, which enhances both the long-sequence dependency and position perception of words in a caption decoder. Our model learns to collaboratively attend on both visual and textual features and meanwhile perceive each word’s relative position in the sentence to maximize the information delivered in the generated caption. We evaluate the effectiveness of our RDN on the COCO image captioning datasets and achieve superior performance over the previous methods. Further experiments reveal that our approach is particularly advantageous for hard cases with complex scenes to describe by captions. |
| Tasks | Image Captioning |
| Published | 2019-08-30 |
| URL | https://arxiv.org/abs/1908.11824v1 |
| https://arxiv.org/pdf/1908.11824v1.pdf | |
| PWC | https://paperswithcode.com/paper/reflective-decoding-network-for-image |
| Repo | |
| Framework | |
Using Wasserstein-2 regularization to ensure fair decisions with Neural-Network classifiers
| Title | Using Wasserstein-2 regularization to ensure fair decisions with Neural-Network classifiers |
| Authors | Laurent Risser, Quentin Vincenot, Nicolas Couellan, Jean-Michel Loubes |
| Abstract | In this paper, we propose a new method to build fair Neural-Network classifiers by using a constraint based on the Wasserstein distance. More specifically, we detail how to efficiently compute the gradients of Wasserstein-2 regularizers for Neural-Networks. The proposed strategy is then used to train Neural-Networks decision rules which favor fair predictions. Our method fully takes into account two specificities of Neural-Networks training: (1) The network parameters are indirectly learned based on automatic differentiation and on the loss gradients, and (2) batch training is the gold standard to approximate the parameter gradients, as it requires a reasonable amount of computations and it can efficiently explore the parameters space. Results are shown on synthetic data, as well as on the UCI Adult Income Dataset. Our method is shown to perform well compared with ‘ZafarICWWW17’ and linear-regression with Wasserstein-1 regularization, as in ‘JiangUAI19’, in particular when non-linear decision rules are required for accurate predictions. |
| Tasks | |
| Published | 2019-08-15 |
| URL | https://arxiv.org/abs/1908.05783v1 |
| https://arxiv.org/pdf/1908.05783v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-wasserstein-2-regularization-to-ensure |
| Repo | |
| Framework | |
Inference and Uncertainty Quantification for Noisy Matrix Completion
| Title | Inference and Uncertainty Quantification for Noisy Matrix Completion |
| Authors | Yuxin Chen, Jianqing Fan, Cong Ma, Yuling Yan |
| Abstract | Noisy matrix completion aims at estimating a low-rank matrix given only partial and corrupted entries. Despite substantial progress in designing efficient estimation algorithms, it remains largely unclear how to assess the uncertainty of the obtained estimates and how to perform statistical inference on the unknown matrix (e.g.~constructing a valid and short confidence interval for an unseen entry). This paper takes a step towards inference and uncertainty quantification for noisy matrix completion. We develop a simple procedure to compensate for the bias of the widely used convex and nonconvex estimators. The resulting de-biased estimators admit nearly precise non-asymptotic distributional characterizations, which in turn enable optimal construction of confidence intervals,/,regions for, say, the missing entries and the low-rank factors. Our inferential procedures do not rely on sample splitting, thus avoiding unnecessary loss of data efficiency. As a byproduct, we obtain a sharp characterization of the estimation accuracy of our de-biased estimators, which, to the best of our knowledge, are the first tractable algorithms that provably achieve full statistical efficiency (including the preconstant). The analysis herein is built upon the intimate link between convex and nonconvex optimization — an appealing feature recently discovered by \cite{chen2019noisy}. |
| Tasks | Matrix Completion |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04159v2 |
| https://arxiv.org/pdf/1906.04159v2.pdf | |
| PWC | https://paperswithcode.com/paper/inference-and-uncertainty-quantification-for |
| Repo | |
| Framework | |
MODL: A Modular Ontology Design Library
| Title | MODL: A Modular Ontology Design Library |
| Authors | Cogan Shimizu, Quinn Hirt, Pascal Hitzler |
| Abstract | Pattern-based, modular ontologies have several beneficial properties that lend themselves to FAIR data practices, especially as it pertains to Interoperability and Reusability. However, developing such ontologies has a high upfront cost, e.g. reusing a pattern is predicated upon being aware of its existence in the first place. Thus, to help overcome these barriers, we have developed MODL: a modular ontology design library. MODL is a curated collection of well-documented ontology design patterns, drawn from a wide variety of interdisciplinary use-cases. In this paper we present MODL as a resource, discuss its use, and provide some examples of its contents. |
| Tasks | |
| Published | 2019-04-10 |
| URL | http://arxiv.org/abs/1904.05405v1 |
| http://arxiv.org/pdf/1904.05405v1.pdf | |
| PWC | https://paperswithcode.com/paper/modl-a-modular-ontology-design-library |
| Repo | |
| Framework | |
Evaluating Gender Bias in Machine Translation
| Title | Evaluating Gender Bias in Machine Translation |
| Authors | Gabriel Stanovsky, Noah A. Smith, Luke Zettlemoyer |
| Abstract | We present the first challenge set and evaluation protocol for the analysis of gender bias in machine translation (MT). Our approach uses two recent coreference resolution datasets composed of English sentences which cast participants into non-stereotypical gender roles (e.g., “The doctor asked the nurse to help her in the operation”). We devise an automatic gender bias evaluation method for eight target languages with grammatical gender, based on morphological analysis (e.g., the use of female inflection for the word “doctor”). Our analyses show that four popular industrial MT systems and two recent state-of-the-art academic MT models are significantly prone to gender-biased translation errors for all tested target languages. Our data and code are made publicly available. |
| Tasks | Coreference Resolution, Machine Translation, Morphological Analysis |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00591v1 |
| https://arxiv.org/pdf/1906.00591v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600591 |
| Repo | |
| Framework | |
Gradient Boost with Convolution Neural Network for Stock Forecast
| Title | Gradient Boost with Convolution Neural Network for Stock Forecast |
| Authors | Jialin Liu, Chih-Min Lin, Fei Chao |
| Abstract | Market economy closely connects aspects to all walks of life. The stock forecast is one of task among studies on the market economy. However, information on markets economy contains a lot of noise and uncertainties, which lead economy forecasting to become a challenging task. Ensemble learning and deep learning are the most methods to solve the stock forecast task. In this paper, we present a model combining the advantages of two methods to forecast the change of stock price. The proposed method combines CNN and GBoost. The experimental results on six market indexes show that the proposed method has better performance against current popular methods. |
| Tasks | |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.09563v1 |
| https://arxiv.org/pdf/1909.09563v1.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-boost-with-convolution-neural |
| Repo | |
| Framework | |
Two-stage Federated Phenotyping and Patient Representation Learning
| Title | Two-stage Federated Phenotyping and Patient Representation Learning |
| Authors | Dianbo Liu, Dmitriy Dligach, Timothy Miller |
| Abstract | A large percentage of medical information is in unstructured text format in electronic medical record systems. Manual extraction of information from clinical notes is extremely time consuming. Natural language processing has been widely used in recent years for automatic information extraction from medical texts. However, algorithms trained on data from a single healthcare provider are not generalizable and error-prone due to the heterogeneity and uniqueness of medical documents. We develop a two-stage federated natural language processing method that enables utilization of clinical notes from different hospitals or clinics without moving the data, and demonstrate its performance using obesity and comorbities phenotyping as medical task. This approach not only improves the quality of a specific clinical task but also facilitates knowledge progression in the whole healthcare system, which is an essential part of learning health system. To the best of our knowledge, this is the first application of federated machine learning in clinical NLP. |
| Tasks | Representation Learning |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05596v1 |
| https://arxiv.org/pdf/1908.05596v1.pdf | |
| PWC | https://paperswithcode.com/paper/two-stage-federated-phenotyping-and-patient-1 |
| Repo | |
| Framework | |
