Paper Group NANR 251
Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies. SCIA at SemEval-2019 Task 3: Sentiment Analysis in Textual Conversations Using Deep Learning. Contextualized Cross-Lingual Event Trigger Extraction with Minimal Resources. Gradient Information for Representation and Modeling. On Testing for Biases in Peer Review. Learning Entrop …
Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
| Title | Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies |
| Authors | Kenneth Marino, Abhinav Gupta, Rob Fergus, Arthur Szlam |
| Abstract | In this paper we introduce a simple, robust approach to hierarchically training an agent in the setting of sparse reward tasks. The agent is split into a low-level and a high-level policy. The low-level policy only accesses internal, proprioceptive dimensions of the state observation. The low-level policies are trained with a simple reward that encourages changing the values of the non-proprioceptive dimensions. Furthermore, it is induced to be periodic with the use a ``phase function.’’ The high-level policy is trained using a sparse, task-dependent reward, and operates by choosing which of the low-level policies to run at any given time. Using this approach, we solve difficult maze and navigation tasks with sparse rewards using the Mujoco Ant and Humanoid agents and show improvement over recent hierarchical methods. | |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SJz1x20cFQ |
| https://openreview.net/pdf?id=SJz1x20cFQ | |
| PWC | https://paperswithcode.com/paper/hierarchical-rl-using-an-ensemble-of |
| Repo | |
| Framework | |
SCIA at SemEval-2019 Task 3: Sentiment Analysis in Textual Conversations Using Deep Learning
| Title | SCIA at SemEval-2019 Task 3: Sentiment Analysis in Textual Conversations Using Deep Learning |
| Authors | Zinedine Rebiai, Simon Andersen, Antoine Debrenne, Victor Lafargue |
| Abstract | In this paper we present our submission for SemEval-2019 Task 3: EmoContext. The task consisted of classifying a textual dialogue into one of four emotion classes: happy, sad, angry or others. Our approach tried to improve on multiple aspects, preprocessing with an emphasis on spell-checking and ensembling with four different models: Bi-directional contextual LSTM (BC-LSTM), categorical Bi-LSTM (CAT-LSTM), binary convolutional Bi-LSTM (BIN-LSTM) and Gated Recurrent Unit (GRU). On the leader-board, we submitted two systems that obtained a micro F1 score (F1μ) of 0.711 and 0.712. After the competition, we merged our two systems with ensembling, which achieved a F1μ of 0.7324 on the test dataset. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2051/ |
| https://www.aclweb.org/anthology/S19-2051 | |
| PWC | https://paperswithcode.com/paper/scia-at-semeval-2019-task-3-sentiment |
| Repo | |
| Framework | |
Contextualized Cross-Lingual Event Trigger Extraction with Minimal Resources
| Title | Contextualized Cross-Lingual Event Trigger Extraction with Minimal Resources |
| Authors | Meryem M{'}hamdi, Marjorie Freedman, Jonathan May |
| Abstract | Event trigger extraction is an information extraction task of practical utility, yet it is challenging due to the difficulty of disambiguating word sense meaning. Previous approaches rely extensively on hand-crafted language-specific features and are applied mainly to English for which annotated datasets and Natural Language Processing (NLP) tools are available. However, the availability of such resources varies from one language to another. Recently, contextualized Bidirectional Encoder Representations from Transformers (BERT) models have established state-of-the-art performance for a variety of NLP tasks. However, there has not been much effort in exploring language transfer using BERT for event extraction. In this work, we treat event trigger extraction as a sequence tagging problem and propose a cross-lingual framework for training it without any hand-crafted features. We experiment with different flavors of transfer learning from high-resourced to low-resourced languages and compare the performance of different multilingual embeddings for event trigger extraction. Our results show that training in a multilingual setting outperforms language-specific models for both English and Chinese. Our work is the first to experiment with two event architecture variants in a cross-lingual setting, to show the effectiveness of contextualized embeddings obtained using BERT, and to explore and analyze its performance on Arabic. |
| Tasks | Transfer Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1061/ |
| https://www.aclweb.org/anthology/K19-1061 | |
| PWC | https://paperswithcode.com/paper/contextualized-cross-lingual-event-trigger |
| Repo | |
| Framework | |
Gradient Information for Representation and Modeling
| Title | Gradient Information for Representation and Modeling |
| Authors | Jie Ding, Robert Calderbank, Vahid Tarokh |
| Abstract | Motivated by Fisher divergence, in this paper we present a new set of information quantities which we refer to as gradient information. These measures serve as surrogates for classical information measures such as those based on logarithmic loss, Kullback-Leibler divergence, directed Shannon information, etc. in many data-processing scenarios of interest, and often provide significant computational advantage, improved stability and robustness. As an example, we apply these measures to the Chow-Liu tree algorithm, and demonstrate remarkable performance and significant computational reduction using both synthetic and real data. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8510-gradient-information-for-representation-and-modeling |
| http://papers.nips.cc/paper/8510-gradient-information-for-representation-and-modeling.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-information-for-representation-and |
| Repo | |
| Framework | |
On Testing for Biases in Peer Review
| Title | On Testing for Biases in Peer Review |
| Authors | Ivan Stelmakh, Nihar Shah, Aarti Singh |
| Abstract | We consider the issue of biases in scholarly research, specifically, in peer review. There is a long standing debate on whether exposing author identities to reviewers induces biases against certain groups, and our focus is on designing tests to detect the presence of such biases. Our starting point is a remarkable recent work by Tomkins, Zhang and Heavlin which conducted a controlled, large-scale experiment to investigate existence of biases in the peer reviewing of the WSDM conference. We present two sets of results in this paper. The first set of results is negative, and pertains to the statistical tests and the experimental setup used in the work of Tomkins et al. We show that the test employed therein does not guarantee control over false alarm probability and under correlations between relevant variables, coupled with any of the following conditions, with high probability can declare a presence of bias when it is in fact absent: (a) measurement error, (b) model mismatch, (c) reviewer calibration. Moreover, we show that the setup of their experiment may itself inflate false alarm probability if (d) bidding is performed in non-blind manner or (e) popular reviewer assignment procedure is employed. Our second set of results is positive, in that we present a general framework for testing for biases in (single vs. double blind) peer review. We then present a hypothesis test with guaranteed control over false alarm probability and non-trivial power even under conditions (a)–(c). Conditions (d) and (e) are more fundamental problems that are tied to the experimental setup and not necessarily related to the test. |
| Tasks | Calibration |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8770-on-testing-for-biases-in-peer-review |
| http://papers.nips.cc/paper/8770-on-testing-for-biases-in-peer-review.pdf | |
| PWC | https://paperswithcode.com/paper/on-testing-for-biases-in-peer-review |
| Repo | |
| Framework | |
Learning Entropic Wasserstein Embeddings
| Title | Learning Entropic Wasserstein Embeddings |
| Authors | Charlie Frogner, Farzaneh Mirzazadeh, Justin Solomon |
| Abstract | Despite their prevalence, Euclidean embeddings of data are fundamentally limited in their ability to capture latent semantic structures, which need not conform to Euclidean spatial assumptions. Here we consider an alternative, which embeds data as discrete probability distributions in a Wasserstein space, endowed with an optimal transport metric. Wasserstein spaces are much larger and more flexible than Euclidean spaces, in that they can successfully embed a wider variety of metric structures. We propose to exploit this flexibility by learning an embedding that captures the semantic information in the Wasserstein distance between embedded distributions. We examine empirically the representational capacity of such learned Wasserstein embeddings, showing that they can embed a wide variety of complex metric structures with smaller distortion than an equivalent Euclidean embedding. We also investigate an application to word embedding, demonstrating a unique advantage of Wasserstein embeddings: we can directly visualize the high-dimensional embedding, as it is a probability distribution on a low-dimensional space. This obviates the need for dimensionality reduction techniques such as t-SNE for visualization. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJg4J3CqFm |
| https://openreview.net/pdf?id=rJg4J3CqFm | |
| PWC | https://paperswithcode.com/paper/learning-entropic-wasserstein-embeddings |
| Repo | |
| Framework | |
Neural Diffusion Distance for Image Segmentation
| Title | Neural Diffusion Distance for Image Segmentation |
| Authors | Jian Sun, Zongben Xu |
| Abstract | Diffusion distance is a spectral method for measuring distance among nodes on graph considering global data structure. In this work, we propose a spec-diff-net for computing diffusion distance on graph based on approximate spectral decomposition. The network is a differentiable deep architecture consisting of feature extraction and diffusion distance modules for computing diffusion distance on image by end-to-end training. We design low resolution kernel matching loss and high resolution segment matching loss to enforce the network’s output to be consistent with human-labeled image segments. To compute high-resolution diffusion distance or segmentation mask, we design an up-sampling strategy by feature-attentional interpolation which can be learned when training spec-diff-net. With the learned diffusion distance, we propose a hierarchical image segmentation method outperforming previous segmentation methods. Moreover, a weakly supervised semantic segmentation network is designed using diffusion distance and achieved promising results on PASCAL VOC 2012 segmentation dataset. |
| Tasks | Semantic Segmentation, Weakly-Supervised Semantic Segmentation |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8424-neural-diffusion-distance-for-image-segmentation |
| http://papers.nips.cc/paper/8424-neural-diffusion-distance-for-image-segmentation.pdf | |
| PWC | https://paperswithcode.com/paper/neural-diffusion-distance-for-image |
| Repo | |
| Framework | |
THU-HCSI at SemEval-2019 Task 3: Hierarchical Ensemble Classification of Contextual Emotion in Conversation
| Title | THU-HCSI at SemEval-2019 Task 3: Hierarchical Ensemble Classification of Contextual Emotion in Conversation |
| Authors | Xihao Liang, Ye Ma, Mingxing Xu |
| Abstract | In this paper, we describe our hierarchical ensemble system designed for the SemEval-2019 task3, EmoContext. In our system, three sets of classifiers are trained for different sub-targets and the predicted labels of these base classifiers are combined through three steps of voting to make the final prediction. Effective details for developing base classifiers are highlighted. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2060/ |
| https://www.aclweb.org/anthology/S19-2060 | |
| PWC | https://paperswithcode.com/paper/thu-hcsi-at-semeval-2019-task-3-hierarchical |
| Repo | |
| Framework | |
TokyoTech_NLP at SemEval-2019 Task 3: Emotion-related Symbols in Emotion Detection
| Title | TokyoTech_NLP at SemEval-2019 Task 3: Emotion-related Symbols in Emotion Detection |
| Authors | Zhishen Yang, Sam Vijlbrief, Naoaki Okazaki |
| Abstract | This paper presents our contextual emotion detection system in approaching the SemEval2019 shared task 3: EmoContext: Contextual Emotion Detection in Text. This system cooperates with an emotion detection neural network method (Poria et al., 2017), emoji2vec (Eisner et al., 2016) embedding, word2vec embedding (Mikolov et al., 2013), and our proposed emoticon and emoji preprocessing method. The experimental results demonstrate the usefulness of our emoticon and emoji prepossessing method, and representations of emoticons and emoji contribute model{'}s emotion detection. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2061/ |
| https://www.aclweb.org/anthology/S19-2061 | |
| PWC | https://paperswithcode.com/paper/tokyotech_nlp-at-semeval-2019-task-3-emotion |
| Repo | |
| Framework | |
UAIC at SemEval-2019 Task 3: Extracting Much from Little
| Title | UAIC at SemEval-2019 Task 3: Extracting Much from Little |
| Authors | Cristian Simionescu, Ingrid Stoleru, Diana Lucaci, Gheorghe Balan, Iulian Bute, Adrian Iftene |
| Abstract | In this paper, we present a system description for implementing a sentiment analysis agent capable of interpreting the state of an interlocutor engaged in short three message conversations. We present the results and observations of our work and which parts could be further improved in the future. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2062/ |
| https://www.aclweb.org/anthology/S19-2062 | |
| PWC | https://paperswithcode.com/paper/uaic-at-semeval-2019-task-3-extracting-much |
| Repo | |
| Framework | |
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices
| Title | ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices |
| Authors | Zheng Qin, Zeming Li, Zhaoning Zhang, Yiping Bao, Gang Yu, Yuxing Peng, Jian Sun |
| Abstract | Real-time generic object detection on mobile platforms is a crucial but challenging computer vision task. Prior lightweight CNN-based detectors are inclined to use one-stage pipeline. In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight two-stage detector named ThunderNet. In the backbone part, we analyze the drawbacks in previous lightweight backbones and present a lightweight backbone designed for object detection. In the detection part, we exploit an extremely efficient RPN and detection head design. To generate more discriminative feature representation, we design two efficient architecture blocks, Context Enhancement Module and Spatial Attention Module. At last, we investigate the balance between the input resolution, the backbone, and the detection head. Benefit from the highly efficient backbone and detection part design, ThunderNet surpasses previous lightweight one-stage detectors with only 40% of the computational cost on PASCAL VOC and COCO benchmarks. Without bells and whistles, ThunderNet runs at 24.1 fps on an ARM-based device with 19.2 AP on COCO. To the best of our knowledge, this is the first real-time detector reported on ARM platforms. Code will be released for paper reproduction. |
| Tasks | Object Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Qin_ThunderNet_Towards_Real-Time_Generic_Object_Detection_on_Mobile_Devices_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Qin_ThunderNet_Towards_Real-Time_Generic_Object_Detection_on_Mobile_Devices_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/thundernet-towards-real-time-generic-object-1 |
| Repo | |
| Framework | |
Improving Cuneiform Language Identification with BERT
| Title | Improving Cuneiform Language Identification with BERT |
| Authors | Gabriel Bernier-Colborne, Cyril Goutte, Serge L{'e}ger |
| Abstract | We describe the systems developed by the National Research Council Canada for the Cuneiform Language Identification (CLI) shared task at the 2019 VarDial evaluation campaign. We compare a state-of-the-art baseline relying on character n-grams and a traditional statistical classifier, a voting ensemble of classifiers, and a deep learning approach using a Transformer network. We describe how these systems were trained, and analyze the impact of some preprocessing and model estimation decisions. The deep neural network achieved 77{%} accuracy on the test data, which turned out to be the best performance at the CLI evaluation, establishing a new state-of-the-art for cuneiform language identification. |
| Tasks | Language Identification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1402/ |
| https://www.aclweb.org/anthology/W19-1402 | |
| PWC | https://paperswithcode.com/paper/improving-cuneiform-language-identification |
| Repo | |
| Framework | |
Joint Approach to Deromanization of Code-mixed Texts
| Title | Joint Approach to Deromanization of Code-mixed Texts |
| Authors | Rashed Rubby Riyadh, Grzegorz Kondrak |
| Abstract | The conversion of romanized texts back to the native scripts is a challenging task because of the inconsistent romanization conventions and non-standard language use. This problem is compounded by code-mixing, i.e., using words from more than one language within the same discourse. In this paper, we propose a novel approach for handling these two problems together in a single system. Our approach combines three components: language identification, back-transliteration, and sequence prediction. The results of our experiments on Bengali and Hindi datasets establish the state of the art for the task of deromanization of code-mixed texts. |
| Tasks | Language Identification, Transliteration |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1403/ |
| https://www.aclweb.org/anthology/W19-1403 | |
| PWC | https://paperswithcode.com/paper/joint-approach-to-deromanization-of-code |
| Repo | |
| Framework | |
Few-Shot Intent Inference via Meta-Inverse Reinforcement Learning
| Title | Few-Shot Intent Inference via Meta-Inverse Reinforcement Learning |
| Authors | Kelvin Xu, Ellis Ratner, Anca Dragan, Sergey Levine, Chelsea Finn |
| Abstract | A significant challenge for the practical application of reinforcement learning toreal world problems is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert behavior. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e.g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly difficult to unambiguously recover a reward function. In this work, we exploit the insight that demonstrations from other tasks can be used to constrain the set of possible reward functions by learning a “prior” that is specifically optimized for the ability to infer expressive reward functions from limited numbers of demonstrations. We demonstrate that our method can efficiently recover rewards from images for novel tasks and provide intuition as to how our approach is analogous to learning a prior. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SyeLno09Fm |
| https://openreview.net/pdf?id=SyeLno09Fm | |
| PWC | https://paperswithcode.com/paper/few-shot-intent-inference-via-meta-inverse |
| Repo | |
| Framework | |
Grunn2019 at SemEval-2019 Task 5: Shared Task on Multilingual Detection of Hate
| Title | Grunn2019 at SemEval-2019 Task 5: Shared Task on Multilingual Detection of Hate |
| Authors | Mike Zhang, Roy David, Leon Graumans, Gerben Timmerman |
| Abstract | Hate speech occurs more often than ever and polarizes society. To help counter this polarization, SemEval 2019 organizes a shared task called the Multilingual Detection of Hate. The first task (A) is to decide whether a given tweet contains hate against immigrants or women, in a multilingual perspective, for English and Spanish. In the second task (B), the system is also asked to classify the following sub-tasks: hateful tweets as aggressive or not aggressive, and to identify the target harassed as individual or generic. We evaluate multiple models, and finally combine them in an ensemble setting. This ensemble setting is built of five and three submodels for the English and Spanish task respectively. In the current setup it shows that using a bigger ensemble for English tweets performs mediocre, while a slightly smaller ensemble does work well for detecting hate speech in Spanish tweets. Our results on the test set for English show 0.378 macro F1 on task A and 0.553 macro F1 on task B. For Spanish the results are significantly higher, 0.701 macro F1 on task A and 0.734 macro F1 for task B. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2069/ |
| https://www.aclweb.org/anthology/S19-2069 | |
| PWC | https://paperswithcode.com/paper/grunn2019-at-semeval-2019-task-5-shared-task |
| Repo | |
| Framework | |
