Paper Group NANR 73
Optimistic mirror descent in saddle-point problems: Going the extra(-gradient) mile. Towards Answer-unaware Conversational Question Generation. Derivational Morphological Relations in Word Embeddings. Saama Research at MEDIQA 2019: Pre-trained BioBERT with Attention Visualisation for Medical Natural Language Inference. Practical Correlated Topic Mo …
Optimistic mirror descent in saddle-point problems: Going the extra(-gradient) mile
| Title | Optimistic mirror descent in saddle-point problems: Going the extra(-gradient) mile |
| Authors | Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar, Georgios Piliouras |
| Abstract | Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By necessity, most theoretical guarantees revolve around convex-concave (or even linear) problems; however, making theoretical inroads towards efficient GAN training depends crucially on moving beyond this classic framework. To make piecemeal progress along these lines, we analyze the behavior of mirror descent (MD) in a class of non-monotone problems whose solutions coincide with those of a naturally associated variational inequality – a property which we call coherence. We first show that ordinary, “vanilla” MD converges under a strict version of this condition, but not otherwise; in particular, it may fail to converge even in bilinear models with a unique solution. We then show that this deficiency is mitigated by optimism: by taking an “extra-gradient” step, optimistic mirror descent (OMD) converges in all coherent problems. Our analysis generalizes and extends the results of Daskalakis et al. [2018] for optimistic gradient descent (OGD) in bilinear problems, and makes concrete headway for provable convergence beyond convex-concave games. We also provide stochastic analogues of these results, and we validate our analysis by numerical experiments in a wide array of GAN models (including Gaussian mixture models, and the CelebA and CIFAR-10 datasets). |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Bkg8jjC9KQ |
| https://openreview.net/pdf?id=Bkg8jjC9KQ | |
| PWC | https://paperswithcode.com/paper/optimistic-mirror-descent-in-saddle-point-1 |
| Repo | |
| Framework | |
Towards Answer-unaware Conversational Question Generation
| Title | Towards Answer-unaware Conversational Question Generation |
| Authors | Mao Nakanishi, Tetsunori Kobayashi, Yoshihiko Hayashi |
| Abstract | Conversational question generation is a novel area of NLP research which has a range of potential applications. This paper is first to presents a framework for conversational question generation that is unaware of the corresponding answers. To properly generate a question coherent to the grounding text and the current conversation history, the proposed framework first locates the focus of a question in the text passage, and then identifies the question pattern that leads the sequential generation of the words in a question. The experiments using the CoQA dataset demonstrate that the quality of generated questions greatly improves if the question foci and the question patterns are correctly identified. In addition, it was shown that the question foci, even estimated with a reasonable accuracy, could contribute to the quality improvement. These results established that our research direction may be promising, but at the same time revealed that the identification of question patterns is a challenging issue, and it has to be largely refined to achieve a better quality in the end-to-end automatic question generation. |
| Tasks | Question Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5809/ |
| https://www.aclweb.org/anthology/D19-5809 | |
| PWC | https://paperswithcode.com/paper/towards-answer-unaware-conversational |
| Repo | |
| Framework | |
Derivational Morphological Relations in Word Embeddings
| Title | Derivational Morphological Relations in Word Embeddings |
| Authors | Tom{'a}{\v{s}} Musil, Jon{'a}{\v{s}} Vidra, David Mare{\v{c}}ek |
| Abstract | Derivation is a type of a word-formation process which creates new words from existing ones by adding, changing or deleting affixes. In this paper, we explore the potential of word embeddings to identify properties of word derivations in the morphologically rich Czech language. We extract derivational relations between pairs of words from DeriNet, a Czech lexical network, which organizes almost one million Czech lemmas into derivational trees. For each such pair, we compute the difference of the embeddings of the two words, and perform unsupervised clustering of the resulting vectors. Our results show that these clusters largely match manually annotated semantic categories of the derivational relations (e.g. the relation {}bake{--}baker{'} belongs to category {}actor{'}, and a correct clustering puts it into the same cluster as {`}govern{–}governor{'}). | |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4818/ |
| https://www.aclweb.org/anthology/W19-4818 | |
| PWC | https://paperswithcode.com/paper/derivational-morphological-relations-in-word-1 |
| Repo | |
| Framework | |
Saama Research at MEDIQA 2019: Pre-trained BioBERT with Attention Visualisation for Medical Natural Language Inference
| Title | Saama Research at MEDIQA 2019: Pre-trained BioBERT with Attention Visualisation for Medical Natural Language Inference |
| Authors | Kamal raj Kanakarajan, Suriyadeepan Ramamoorthy, Vaidheeswaran Archana, Soham Chatterjee, Malaikannan Sankarasubbu |
| Abstract | Natural Language inference is the task of identifying relation between two sentences as entailment, contradiction or neutrality. MedNLI is a biomedical flavour of NLI for clinical domain. This paper explores the use of Bidirectional Encoder Representation from Transformer (BERT) for solving MedNLI. The proposed model, BERT pre-trained on PMC, PubMed and fine-tuned on MIMICIII v1.4, achieves state of the art results on MedNLI (83.45{%}) and an accuracy of 78.5{%} in MEDIQA challenge. The authors present an analysis of the attention patterns that emerged as a result of training BERT on MedNLI using a visualization tool, bertviz. |
| Tasks | Natural Language Inference |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5055/ |
| https://www.aclweb.org/anthology/W19-5055 | |
| PWC | https://paperswithcode.com/paper/saama-research-at-mediqa-2019-pre-trained |
| Repo | |
| Framework | |
Practical Correlated Topic Modeling and Analysis via the Rectified Anchor Word Algorithm
| Title | Practical Correlated Topic Modeling and Analysis via the Rectified Anchor Word Algorithm |
| Authors | Moontae Lee, Sungjun Cho, David Bindel, David Mimno |
| Abstract | Despite great scalability on large data and their ability to understand correlations between topics, spectral topic models have not been widely used due to the absence of reliability in real data and lack of practical implementations. This paper aims to solidify the foundations of spectral topic inference and provide a practical implementation for anchor-based topic modeling. Beginning with vocabulary curation, we scrutinize every single inference step with other viable options. We also evaluate our matrix-based approach against popular alternatives including a tensor-based spectral method as well as probabilistic algorithms. Our quantitative and qualitative experiments demonstrate the power of Rectified Anchor Word algorithm in various real datasets, providing a complete guide to practical correlated topic modeling. |
| Tasks | Topic Models |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1504/ |
| https://www.aclweb.org/anthology/D19-1504 | |
| PWC | https://paperswithcode.com/paper/practical-correlated-topic-modeling-and |
| Repo | |
| Framework | |
Competitiveness Analysis of the European Machine Translation Market
| Title | Competitiveness Analysis of the European Machine Translation Market |
| Authors | Andrejs Vasi{\c{l}}jevs, Inguna Skadi{\c{n}}a, Indra S{=a}m{=\i}te, Kaspars Kauli{\c{n}}{\v{s}}, {{=E}riks Ajausks}, J{=u}lija Me{\c{l}}{\c{n}}ika, Aivars B{=e}rzi{\c{n}}{\v{s}} |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6701/ |
| https://www.aclweb.org/anthology/W19-6701 | |
| PWC | https://paperswithcode.com/paper/competitiveness-analysis-of-the-european |
| Repo | |
| Framework | |
Part-Regularized Near-Duplicate Vehicle Re-Identification
| Title | Part-Regularized Near-Duplicate Vehicle Re-Identification |
| Authors | Bing He, Jia Li, Yifan Zhao, Yonghong Tian |
| Abstract | Vehicle re-identification (Re-ID) has been attracting more interests in computer vision owing to its great contributions in urban surveillance and intelligent transportation. With the development of deep learning approaches, vehicle Re-ID still faces a near-duplicate challenge, which is to distinguish different instances with nearly identical appearances. Previous methods simply rely on the global visual features to handle this problem. In this paper, we proposed a simple but efficient part-regularized discriminative feature preserving method which enhances the perceptive ability of subtle discrepancies. We further develop a novel framework to integrate part constrains with the global Re-ID modules by introducing an detection branch. Our framework is trained end-to-end with combined local and global constrains. Specially, without the part-regularized local constrains in inference step, our Re-ID network outperforms the state-of-the-art method by a large margin on large benchmark datasets VehicleID and VeRi-776. |
| Tasks | Vehicle Re-Identification |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/He_Part-Regularized_Near-Duplicate_Vehicle_Re-Identification_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/He_Part-Regularized_Near-Duplicate_Vehicle_Re-Identification_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/part-regularized-near-duplicate-vehicle-re |
| Repo | |
| Framework | |
Investigating Speech Recognition for Improving Predictive AAC
| Title | Investigating Speech Recognition for Improving Predictive AAC |
| Authors | Jiban Adhikary, Robbie Watling, Crystal Fletcher, Alex Stanage, Keith Vertanen |
| Abstract | Making good letter or word predictions can help accelerate the communication of users of high-tech AAC devices. This is particularly important for real-time person-to-person conversations. We investigate whether per forming speech recognition on the speaking-side of a conversation can improve language model based predictions. We compare the accuracy of three plausible microphone deployment options and the accuracy of two commercial speech recognition engines (Google and IBM Watson). We found that despite recognition word error rates of 7-16{%}, our ensemble of N-gram and recurrent neural network language models made predictions nearly as good as when they used the reference transcripts. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1706/ |
| https://www.aclweb.org/anthology/W19-1706 | |
| PWC | https://paperswithcode.com/paper/investigating-speech-recognition-for |
| Repo | |
| Framework | |
BLCU_NLP at SemEval-2019 Task 8: A Contextual Knowledge-enhanced GPT Model for Fact Checking
| Title | BLCU_NLP at SemEval-2019 Task 8: A Contextual Knowledge-enhanced GPT Model for Fact Checking |
| Authors | Wanying Xie, Mengxi Que, Ruoyao Yang, Chunhua Liu, Dong Yu |
| Abstract | Since the resources of Community Question Answering are abundant and information sharing becomes universal, it will be increasingly difficult to find factual information for questioners in massive messages. SemEval 2019 task 8 is focusing on these issues. We participate in the task and use Generative Pre-trained Transformer (OpenAI GPT) as our system. Our innovations are data extension, feature extraction, and input transformation. For contextual knowledge enhancement, we extend the training set of subtask A, use several features to improve the results of our system and adapt the input formats to be more suitable for this task. We demonstrate the effectiveness of our approaches, which achieves 81.95{%} of subtask A and 61.08{%} of subtask B in accuracy on the SemEval 2019 task 8. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2198/ |
| https://www.aclweb.org/anthology/S19-2198 | |
| PWC | https://paperswithcode.com/paper/blcu_nlp-at-semeval-2019-task-8-a-contextual |
| Repo | |
| Framework | |
Look Ma, No GANs! Image Transformation with ModifAE
| Title | Look Ma, No GANs! Image Transformation with ModifAE |
| Authors | Chad Atalla, Bartholomew Tam, Amanda Song, Gary Cottrell |
| Abstract | Existing methods of image to image translation require multiple steps in the training or modification process, and suffer from either an inability to generalize, or long training times. These methods also focus on binary trait modification, ignoring continuous traits. To address these problems, we propose ModifAE: a novel standalone neural network, trained exclusively on an autoencoding task, that implicitly learns to make continuous trait image modifications. As a standalone image modification network, ModifAE requires fewer parameters and less time to train than existing models. We empirically show that ModifAE produces significantly more convincing and more consistent continuous face trait modifications than the previous state-of-the-art model. |
| Tasks | Image-to-Image Translation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1ethsR9Ym |
| https://openreview.net/pdf?id=B1ethsR9Ym | |
| PWC | https://paperswithcode.com/paper/look-ma-no-gans-image-transformation-with |
| Repo | |
| Framework | |
Machine Learning-Based EDoS Attack Detection Technique Using Execution Trace Analysis
| Title | Machine Learning-Based EDoS Attack Detection Technique Using Execution Trace Analysis |
| Authors | Hossein Abbasi, Naser Ezzati-Jivan, Martine Bellaiche, Chamseddine Talhi, Michel R. Dagenais |
| Abstract | One of the most important benefits of using cloud computing is the benefit of on-demand services. Accordingly, the method of payment in the cloud environment is pay per use. This feature results in a new kind of DDOS attack called Economic Denial of Sustainability (EDoS), in which the customer pays extra to the cloud provider as a result of the attack. Similar to other DDoS attacks, EDoS attacks are divided into different types, such as (1) bandwidth-consuming attacks, (2) attacks that target specific applications, and 3) connection-layer exhaustion attacks. In this work, we propose a novel framework to detect different types of EDoS attacks by designing a profile that learns from and classifies the normal and abnormal behaviors. In this framework, the extra demanding resources are only allocated to VMs that are detected to be in a normal situation and therefore prevent the cloud environment from attack and resource misuse propagation. |
| Tasks | |
| Published | 2019-01-26 |
| URL | https://www.researchgate.net/publication/330656735_Machine_Learning-Based_EDoS_Attack_Detection_Technique_Using_Execution_Trace_Analysis |
| https://www.researchgate.net/publication/330656735_Machine_Learning-Based_EDoS_Attack_Detection_Technique_Using_Execution_Trace_Analysis | |
| PWC | https://paperswithcode.com/paper/machine-learning-based-edos-attack-detection |
| Repo | |
| Framework | |
Cross-lingual Semantic Specialization via Lexical Relation Induction
| Title | Cross-lingual Semantic Specialization via Lexical Relation Induction |
| Authors | Edoardo Maria Ponti, Ivan Vuli{'c}, Goran Glava{\v{s}}, Roi Reichart, Anna Korhonen |
| Abstract | Semantic specialization integrates structured linguistic knowledge from external resources (such as lexical relations in WordNet) into pretrained distributional vectors in the form of constraints. However, this technique cannot be leveraged in many languages, because their structured external resources are typically incomplete or non-existent. To bridge this gap, we propose a novel method that transfers specialization from a resource-rich source language (English) to virtually any target language. Our specialization transfer comprises two crucial steps: 1) Inducing noisy constraints in the target language through automatic word translation; and 2) Filtering the noisy constraints via a state-of-the-art relation prediction model trained on the source language constraints. This allows us to specialize any set of distributional vectors in the target language with the refined constraints. We prove the effectiveness of our method through intrinsic word similarity evaluation in 8 languages, and with 3 downstream tasks in 5 languages: lexical simplification, dialog state tracking, and semantic textual similarity. The gains over the previous state-of-art specialization methods are substantial and consistent across languages. Our results also suggest that the transfer method is effective even for lexically distant source-target language pairs. Finally, as a by-product, our method produces lists of WordNet-style lexical relations in resource-poor languages. |
| Tasks | Lexical Simplification, Semantic Textual Similarity |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1226/ |
| https://www.aclweb.org/anthology/D19-1226 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-semantic-specialization-via |
| Repo | |
| Framework | |
Language-Agnostic Twitter-Bot Detection
| Title | Language-Agnostic Twitter-Bot Detection |
| Authors | J{"u}rgen Knauth |
| Abstract | In this paper we address the problem of detecting Twitter bots. We analyze a dataset of 8385 Twitter accounts and their tweets consisting of both humans and different kinds of bots. We use this data to train machine learning classifiers that distinguish between real and bot accounts. We identify features that are easy to extract while still providing good results. We analyze different feature groups based on account specific, tweet specific and behavioral specific features and measure their performance compared to other state of the art bot detection methods. For easy future portability of our work we focus on language-agnostic features. With AdaBoost, the best performing classifier, we achieve an accuracy of 0.988 and an AUC of 0.995. As the creation of good training data in machine learning is often difficult - especially in the domain of Twitter bot detection - we additionally analyze to what extent smaller amounts of training data lead to useful results by reviewing cross-validated learning curves. Our results indicate that using few but expressive features already has a good practical benefit for bot detection, especially if only a small amount of training data is available. |
| Tasks | Twitter Bot Detection |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1065/ |
| https://www.aclweb.org/anthology/R19-1065 | |
| PWC | https://paperswithcode.com/paper/language-agnostic-twitter-bot-detection |
| Repo | |
| Framework | |
Analysing Rhetorical Structure as a Key Feature of Summary Coherence
| Title | Analysing Rhetorical Structure as a Key Feature of Summary Coherence |
| Authors | Jan {\v{S}}najder, Tamara Sladoljev-Agejev, Svjetlana Koli{'c} Vehovec |
| Abstract | We present a model for automatic scoring of coherence based on comparing the rhetorical structure (RS) of college student summaries in L2 (English) against expert summaries. Coherence is conceptualised as a construct consisting of the rhetorical relation and its arguments. Comparison with expert-assigned scores shows that RS scores correlate with both cohesion and coherence. Furthermore, RS scores improve the accuracy of a regression model for cohesion score prediction. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4405/ |
| https://www.aclweb.org/anthology/W19-4405 | |
| PWC | https://paperswithcode.com/paper/analysing-rhetorical-structure-as-a-key |
| Repo | |
| Framework | |
Telling the Whole Story: A Manually Annotated Chinese Dataset for the Analysis of Humor in Jokes
| Title | Telling the Whole Story: A Manually Annotated Chinese Dataset for the Analysis of Humor in Jokes |
| Authors | Dongyu Zhang, Heting Zhang, Xikai Liu, Hongfei Lin, Feng Xia |
| Abstract | Humor plays important role in human communication, which makes it important problem for natural language processing. Prior work on the analysis of humor focuses on whether text is humorous or not, or the degree of funniness, but this is insufficient to explain why it is funny. We therefore create a dataset on humor with 9,123 manually annotated jokes in Chinese. We propose a novel annotation scheme to give scenarios of how humor arises in text. Specifically, our annotations of linguistic humor not only contain the degree of funniness, like previous work, but they also contain key words that trigger humor as well as character relationship, scene, and humor categories. We report reasonable agreement between annota-tors. We also conduct an analysis and exploration of the dataset. To the best of our knowledge, we are the first to approach humor annotation for exploring the underlying mechanism of the use of humor, which may contribute to a significantly deeper analysis of humor. We also contribute with a scarce and valuable dataset, which we will release publicly. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1673/ |
| https://www.aclweb.org/anthology/D19-1673 | |
| PWC | https://paperswithcode.com/paper/telling-the-whole-story-a-manually-annotated |
| Repo | |
| Framework | |
