Paper Group NANR 43
Where’s Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection. Guided Neural Language Generation for Automated Storytelling. INRIA at SemEval-2019 Task 9: Suggestion Mining Using SVM with Handcrafted Features. PKUSE at SemEval-2019 Task 3: Emotion Detection with Emotion-Oriented Neural Attention Network. BIGODM System in th …
Where’s Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection
| Title | Where’s Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection |
| Authors | Philippe Burlina, Neil Joshi, I-Jeng Wang |
| Abstract | We develop a framework for novelty detection (ND) methods relying on deep embeddings, either discriminative or generative, and also propose a novel framework for assessing their performance. While much progress was made recently in these approaches, it has been accompanied by certain limitations: most methods were tested on relatively simple problems (low resolution images / small number of classes) or involved non-public data; comparative performance has often proven inconclusive because of lacking statistical significance; and evaluation has generally been done on non-canonical problem sets of differing complexity, making apples-to-apples comparative performance evaluation difficult. This has led to a relative confusing state of affairs. We address these challenges via the following contributions: We make a proposal for a novel framework to measure the performance of novelty detection methods using a trade-space demonstrating performance (measured by ROCAUC) as a function of problem complexity. We also make several proposals to formally characterize problem complexity. We conduct experiments with problems of higher complexity (higher image resolution / number of classes). To this end we design several canonical datasets built from CIFAR-10 and ImageNet (IN-125) which we make available to perform future benchmarks for novelty detection as well as other related tasks including semantic zero/adaptive shot and unsupervised learning. Finally, we demonstrate, as one of the methods in our ND framework, a generative novelty detection method whose performance exceeds that of all recent best-in-class generative ND methods. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Burlina_Wheres_Wally_Now_Deep_Generative_and_Discriminative_Embeddings_for_Novelty_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Burlina_Wheres_Wally_Now_Deep_Generative_and_Discriminative_Embeddings_for_Novelty_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/wheres-wally-now-deep-generative-and |
| Repo | |
| Framework | |
Guided Neural Language Generation for Automated Storytelling
| Title | Guided Neural Language Generation for Automated Storytelling |
| Authors | Prithviraj Ammanabrolu, Ethan Tien, Wesley Cheung, Zhaochen Luo, William Ma, Lara Martin, Mark Riedl |
| Abstract | Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events. Our method outperforms the baseline sequence-to-sequence model. Additionally, we provide results for a full end-to-end automated story generation system, demonstrating how our model works with existing systems designed for the event-to-event problem. |
| Tasks | Text Generation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3405/ |
| https://www.aclweb.org/anthology/W19-3405 | |
| PWC | https://paperswithcode.com/paper/guided-neural-language-generation-for-2 |
| Repo | |
| Framework | |
INRIA at SemEval-2019 Task 9: Suggestion Mining Using SVM with Handcrafted Features
| Title | INRIA at SemEval-2019 Task 9: Suggestion Mining Using SVM with Handcrafted Features |
| Authors | Ilia Markov, Eric Villemonte De la Clergerie |
| Abstract | We present the INRIA approach to the suggestion mining task at SemEval 2019. The task consists of two subtasks: suggestion mining under single-domain (Subtask A) and cross-domain (Subtask B) settings. We used the Support Vector Machines algorithm trained on handcrafted features, function words, sentiment features, digits, and verbs for Subtask A, and handcrafted features for Subtask B. Our best run archived a F1-score of 51.18{%} on Subtask A, and ranked in the top ten of the submissions for Subtask B with 73.30{%} F1-score. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2211/ |
| https://www.aclweb.org/anthology/S19-2211 | |
| PWC | https://paperswithcode.com/paper/inria-at-semeval-2019-task-9-suggestion |
| Repo | |
| Framework | |
PKUSE at SemEval-2019 Task 3: Emotion Detection with Emotion-Oriented Neural Attention Network
| Title | PKUSE at SemEval-2019 Task 3: Emotion Detection with Emotion-Oriented Neural Attention Network |
| Authors | Luyao Ma, Long Zhang, Wei Ye, Wenhui Hu |
| Abstract | This paper presents the system in SemEval-2019 Task 3, {``}EmoContext: Contextual Emotion Detection in Text{''}. We propose a deep learning architecture with bidirectional LSTM networks, augmented with an emotion-oriented attention network that is capable of extracting emotion information from an utterance. Experimental results show that our model outperforms its variants and the baseline. Overall, this system has achieved 75.57{%} for the microaveraged F1 score. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2049/ |
| https://www.aclweb.org/anthology/S19-2049 | |
| PWC | https://paperswithcode.com/paper/pkuse-at-semeval-2019-task-3-emotion |
| Repo | |
| Framework | |
BIGODM System in the Social Media Mining for Health Applications Shared Task 2019
| Title | BIGODM System in the Social Media Mining for Health Applications Shared Task 2019 |
| Authors | Chen-Kai Wang, Hong-Jie Dai, Bo-Hung Wang |
| Abstract | In this study, we describe our methods to automatically classify Twitter posts conveying events of adverse drug reaction (ADR). Based on our previous experience in tackling the ADR classification task, we empirically applied the vote-based under-sampling ensemble approach along with linear support vector machine (SVM) to develop our classifiers as part of our participation in ACL 2019 Social Media Mining for Health Applications (SMM4H) shared task 1. The best-performed model on the test sets were trained on a merged corpus consisting of the datasets released by SMM4H 2017 and 2019. By using VUE, the corpus was randomly under-sampled with 2:1 ratio between the negative and positive classes to create an ensemble using the linear kernel trained with features including bag-of-word, domain knowledge, negation and word embedding. The best performing model achieved an F-measure of 0.551 which is about 5{%} higher than the average F-scores of 16 teams. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3220/ |
| https://www.aclweb.org/anthology/W19-3220 | |
| PWC | https://paperswithcode.com/paper/bigodm-system-in-the-social-media-mining-for |
| Repo | |
| Framework | |
Discrimination in Online Markets: Effects of Social Bias on Learning from Reviews and Policy Design
| Title | Discrimination in Online Markets: Effects of Social Bias on Learning from Reviews and Policy Design |
| Authors | Faidra Georgia Monachou, Itai Ashlagi |
| Abstract | The increasing popularity of online two-sided markets such as ride-sharing, accommodation and freelance labor platforms, goes hand in hand with new socioeconomic challenges. One major issue remains the existence of bias and discrimination against certain social groups. We study this problem using a two-sided large market model with employers and workers mediated by a platform. Employers who seek to hire workers face uncertainty about a candidate worker’s skill level. Therefore, they base their hiring decision on learning from past reviews about an individual worker as well as on their (possibly misspecified) prior beliefs about the ability level of the social group the worker belongs to. Drawing upon the social learning literature with bounded rationality and limited information, uncertainty combined with social bias leads to unequal hiring opportunities between workers of different social groups. Although the effect of social bias decreases as the number of reviews increases (consistent with empirical findings), minority workers still receive lower expected payoffs. Finally, we consider a simple directed matching policy (DM), which combines learning and matching to make better matching decisions for minority workers. Under this policy, there exists a steady-state equilibrium, in which DM reduces the discrimination gap. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8487-discrimination-in-online-markets-effects-of-social-bias-on-learning-from-reviews-and-policy-design |
| http://papers.nips.cc/paper/8487-discrimination-in-online-markets-effects-of-social-bias-on-learning-from-reviews-and-policy-design.pdf | |
| PWC | https://paperswithcode.com/paper/discrimination-in-online-markets-effects-of |
| Repo | |
| Framework | |
INVASE: Instance-wise Variable Selection using Neural Networks
| Title | INVASE: Instance-wise Variable Selection using Neural Networks |
| Authors | Jinsung Yoon, James Jordon, Mihaela van der Schaar |
| Abstract | The advent of big data brings with it data with more and more dimensions and thus a growing need to be able to efficiently select which features to use for a variety of problems. While global feature selection has been a well-studied problem for quite some time, only recently has the paradigm of instance-wise feature selection been developed. In this paper, we propose a new instance-wise feature selection method, which we term INVASE. INVASE consists of 3 neural networks, a selector network, a predictor network and a baseline network which are used to train the selector network using the actor-critic methodology. Using this methodology, INVASE is capable of flexibly discovering feature subsets of a different size for each instance, which is a key limitation of existing state-of-the-art methods. We demonstrate through a mixture of synthetic and real data experiments that INVASE significantly outperforms state-of-the-art benchmarks. |
| Tasks | Feature Selection |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJg_roAcK7 |
| https://openreview.net/pdf?id=BJg_roAcK7 | |
| PWC | https://paperswithcode.com/paper/invase-instance-wise-variable-selection-using |
| Repo | |
| Framework | |
A Regularization-based Framework for Bilingual Grammar Induction
| Title | A Regularization-based Framework for Bilingual Grammar Induction |
| Authors | Yong Jiang, Wenjuan Han, Kewei Tu |
| Abstract | Grammar induction aims to discover syntactic structures from unannotated sentences. In this paper, we propose a framework in which the learning process of the grammar model of one language is influenced by knowledge from the model of another language. Unlike previous work on multilingual grammar induction, our approach does not rely on any external resource, such as parallel corpora, word alignments or linguistic phylogenetic trees. We propose three regularization methods that encourage similarity between model parameters, dependency edge scores, and parse trees respectively. We deploy our methods on a state-of-the-art unsupervised discriminative parser and evaluate it on both transfer grammar induction and bilingual grammar induction. Empirical results on multiple languages show that our methods outperform strong baselines. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1148/ |
| https://www.aclweb.org/anthology/D19-1148 | |
| PWC | https://paperswithcode.com/paper/a-regularization-based-framework-for |
| Repo | |
| Framework | |
What A Sunny Day ☔: Toward Emoji-Sensitive Irony Detection
| Title | What A Sunny Day ☔: Toward Emoji-Sensitive Irony Detection |
| Authors | Shirley Anugrah Hayati, Aditi Chaudhary, Naoki Otani, Alan W Black |
| Abstract | Irony detection is an important task with applications in identification of online abuse and harassment. With the ubiquitous use of non-verbal cues such as emojis in social media, in this work we aim to study the role of these structures in irony detection. Since the existing irony detection datasets have {\textless}10{%} ironic tweets with emoji, classifiers trained on them are insensitive to emojis. We propose an automated pipeline for creating a more balanced dataset. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5527/ |
| https://www.aclweb.org/anthology/D19-5527 | |
| PWC | https://paperswithcode.com/paper/dataset-analysis-and-augmentation-for-emoji |
| Repo | |
| Framework | |
Neural Machine Translation between Myanmar (Burmese) and Rakhine (Arakanese)
| Title | Neural Machine Translation between Myanmar (Burmese) and Rakhine (Arakanese) |
| Authors | Thazin Myint Oo, Ye Kyaw Thu, Khin Mar Soe |
| Abstract | This work explores neural machine translation between Myanmar (Burmese) and Rakhine (Arakanese). Rakhine is a language closely related to Myanmar, often considered a dialect. We implemented three prominent neural machine translation (NMT) systems: recurrent neural networks (RNN), transformer, and convolutional neural networks (CNN). The systems were evaluated on a Myanmar-Rakhine parallel text corpus developed by us. In addition, two types of word segmentation schemes for word embeddings were studied: Word-BPE and Syllable-BPE segmentation. Our experimental results clearly show that the highest quality NMT and statistical machine translation (SMT) performances are obtained with Syllable-BPE segmentation for both types of translations. If we focus on NMT, we find that the transformer with Word-BPE segmentation outperforms CNN and RNN for both Myanmar-Rakhine and Rakhine-Myanmar translation. However, CNN with Syllable-BPE segmentation obtains a higher score than the RNN and transformer. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1408/ |
| https://www.aclweb.org/anthology/W19-1408 | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-between-myanmar |
| Repo | |
| Framework | |
Cross-lingual intent classification in a low resource industrial setting
| Title | Cross-lingual intent classification in a low resource industrial setting |
| Authors | Talaat Khalil, Kornel Kie{\l}czewski, Georgios Christos Chouliaras, Amina Keldibek, Maarten Versteegh |
| Abstract | This paper explores different approaches to multilingual intent classification in a low resource setting. Recent advances in multilingual text representations promise cross-lingual transfer for classifiers. We investigate the potential for this transfer in an applied industrial setting and compare to multilingual classification using machine translated text. Our results show that while the recently developed methods show promise, practical application calls for a combination of techniques for useful results. |
| Tasks | Cross-Lingual Transfer, Intent Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1676/ |
| https://www.aclweb.org/anthology/D19-1676 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-intent-classification-in-a-low |
| Repo | |
| Framework | |
Summarization Evaluation meets Short-Answer Grading
| Title | Summarization Evaluation meets Short-Answer Grading |
| Authors | Margot Mieskes, Ulrike Pad{'o} |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6308/ |
| https://www.aclweb.org/anthology/W19-6308 | |
| PWC | https://paperswithcode.com/paper/summarization-evaluation-meets-short-answer |
| Repo | |
| Framework | |
Proceedings of the The 17th Annual Workshop of the Australasian Language Technology Association
| Title | Proceedings of the The 17th Annual Workshop of the Australasian Language Technology Association |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1000/ |
| https://www.aclweb.org/anthology/U19-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-the-17th-annual-workshop |
| Repo | |
| Framework | |
M=aOri Loanwords: A Corpus of New Zealand English Tweets
| Title | M=aOri Loanwords: A Corpus of New Zealand English Tweets |
| Authors | David Trye, Andreea Calude, Felipe Bravo-Marquez, Te Taka Keegan |
| Abstract | M{=a}ori loanwords are widely used in New Zealand English for various social functions by New Zealanders within and outside of the M{=a}ori community. Motivated by the lack of linguistic resources for studying how M{=a}ori loanwords are used in social media, we present a new corpus of New Zealand English tweets. We collected tweets containing selected M{=a}ori words that are likely to be known by New Zealanders who do not speak M{=a}ori. Since over 30{%} of these words turned out to be irrelevant, we manually annotated a sample of our tweets into relevant and irrelevant categories. This data was used to train machine learning models to automatically filter out irrelevant tweets. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2018/ |
| https://www.aclweb.org/anthology/P19-2018 | |
| PWC | https://paperswithcode.com/paper/maori-loanwords-a-corpus-of-new-zealand |
| Repo | |
| Framework | |
aiai at FinSBD task: Sentence Boundary Detection in Noisy Texts From Financial Documents Using Deep Attention Model
| Title | aiai at FinSBD task: Sentence Boundary Detection in Noisy Texts From Financial Documents Using Deep Attention Model |
| Authors | Ke Tian, Zi Jun Peng |
| Abstract | |
| Tasks | Boundary Detection, Deep Attention |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5514/ |
| https://www.aclweb.org/anthology/W19-5514 | |
| PWC | https://paperswithcode.com/paper/aiai-at-finsbd-task-sentence-boundary |
| Repo | |
| Framework | |
