Paper Group NANR 211
m_y at SemEval-2019 Task 9: Exploring BERT for Suggestion Mining. Encoding Social Information with Graph Convolutional Networks forPolitical Perspective Detection in News Media. A Neural Multi-digraph Model for Chinese NER with Gazetteers. DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features. Discourse- …
m_y at SemEval-2019 Task 9: Exploring BERT for Suggestion Mining
| Title | m_y at SemEval-2019 Task 9: Exploring BERT for Suggestion Mining |
| Authors | Masahiro Yamamoto, Toshiyuki Sekiya |
| Abstract | This paper presents our system to the SemEval-2019 Task 9, Suggestion Mining from Online Reviews and Forums. The goal of this task is to extract suggestions such as the expressions of tips, advice, and recommendations. We explore Bidirectional Encoder Representations from Transformers (BERT) focusing on target domain pre-training in Subtask A which provides training and test datasets in the same domain. In Subtask B, the cross domain suggestion mining task, we apply the idea of distant supervision. Our system obtained the third place in Subtask A and the fifth place in Subtask B, which demonstrates its efficacy of our approaches. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2152/ |
| https://www.aclweb.org/anthology/S19-2152 | |
| PWC | https://paperswithcode.com/paper/m_y-at-semeval-2019-task-9-exploring-bert-for |
| Repo | |
| Framework | |
Encoding Social Information with Graph Convolutional Networks forPolitical Perspective Detection in News Media
| Title | Encoding Social Information with Graph Convolutional Networks forPolitical Perspective Detection in News Media |
| Authors | Chang Li, Dan Goldwasser |
| Abstract | Identifying the political perspective shaping the way news events are discussed in the media is an important and challenging task. In this paper, we highlight the importance of contextualizing social information, capturing how this information is disseminated in social networks. We use Graph Convolutional Networks, a recently proposed neural architecture for representing relational information, to capture the documents{'} social context. We show that social information can be used effectively as a source of distant supervision, and when direct supervision is available, even little social information can significantly improve performance. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1247/ |
| https://www.aclweb.org/anthology/P19-1247 | |
| PWC | https://paperswithcode.com/paper/encoding-social-information-with-graph |
| Repo | |
| Framework | |
A Neural Multi-digraph Model for Chinese NER with Gazetteers
| Title | A Neural Multi-digraph Model for Chinese NER with Gazetteers |
| Authors | Ruixue Ding, Pengjun Xie, Xiaoyan Zhang, Wei Lu, Linlin Li, Luo Si |
| Abstract | Gazetteers were shown to be useful resources for named entity recognition (NER). Many existing approaches to incorporating gazetteers into machine learning based NER systems rely on manually defined selection strategies or handcrafted templates, which may not always lead to optimal effectiveness, especially when multiple gazetteers are involved. This is especially the case for the task of Chinese NER, where the words are not naturally tokenized, leading to additional ambiguities. To automatically learn how to incorporate multiple gazetteers into an NER system, we propose a novel approach based on graph neural networks with a multi-digraph structure that captures the information that the gazetteers offer. Experiments on various datasets show that our model is effective in incorporating rich gazetteer information while resolving ambiguities, outperforming previous approaches. |
| Tasks | Named Entity Recognition |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1141/ |
| https://www.aclweb.org/anthology/P19-1141 | |
| PWC | https://paperswithcode.com/paper/a-neural-multi-digraph-model-for-chinese-ner |
| Repo | |
| Framework | |
DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features
| Title | DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features |
| Authors | Chang Tang, Xinzhong Zhu, Xinwang Liu, Lizhe Wang, Albert Zomaya |
| Abstract | Defocus blur detection aims to detect out-of-focus regions from an image. Although attracting more and more attention due to its widespread applications, defocus blur detection still confronts several challenges such as the interference of background clutter, sensitivity to scales and missing boundary details of defocus blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We firstly utilize a fully convolutional network to extract multi-scale deep features. The features from bottom layers are able to capture rich low-level features for details preservation, while the features from top layers can characterize the semantic information to locate blur regions. These features from different layers are fused as shallow features and semantic features, respectively. After that, the fused shallow features are propagated to top layers for refining the fine details of detected defocus blur regions, and the fused semantic features are propagated to bottom layers to assist in better locating the defocus regions. The feature fusing and refining are carried out in a recurrent manner. Also, we finally fuse the output of each layer at the last recurrent step to obtain the final defocus blur map by considering the sensitivity to scales of the defocus degree. Experiments on two commonly used defocus blur detection benchmark datasets are conducted to demonstrate the superority of DeFusionNet when compared with other 10 competitors. Code and more results can be found at: http://tangchang.net |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Tang_DeFusionNET_Defocus_Blur_Detection_via_Recurrently_Fusing_and_Refining_Multi-Scale_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Tang_DeFusionNET_Defocus_Blur_Detection_via_Recurrently_Fusing_and_Refining_Multi-Scale_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/defusionnet-defocus-blur-detection-via |
| Repo | |
| Framework | |
Discourse-Based Approach to Involvement of Background Knowledge for Question Answering
| Title | Discourse-Based Approach to Involvement of Background Knowledge for Question Answering |
| Authors | Boris Galitsky, Dmitry Ilvovsky |
| Abstract | We introduce a concept of a virtual discourse tree to improve question answering (Q/A) recall for complex, multi-sentence questions. Augmenting the discourse tree of an answer with tree fragments obtained from text corpora playing the role of ontology, we obtain on the fly a canonical discourse representation of this answer that is independent of the thought structure of a given author. This mechanism is critical for finding an answer that is not only relevant in terms of questions entities but also in terms of inter-relations between these entities in an answer and its style. We evaluate the Q/A system enabled with virtual discourse trees and observe a substantial increase of performance answering complex questions such as Yahoo! Answers and www.2carpros.com. |
| Tasks | Question Answering |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1044/ |
| https://www.aclweb.org/anthology/R19-1044 | |
| PWC | https://paperswithcode.com/paper/discourse-based-approach-to-involvement-of |
| Repo | |
| Framework | |
Bridging the Gap Between Detection and Tracking: A Unified Approach
| Title | Bridging the Gap Between Detection and Tracking: A Unified Approach |
| Authors | Lianghua Huang, Xin Zhao, Kaiqi Huang |
| Abstract | Object detection models have been a source of inspiration for many tracking-by-detection algorithms over the past decade. Recent deep trackers borrow designs or modules from the latest object detection methods, such as bounding box regression, RPN and ROI pooling, and can deliver impressive performance. In this paper, instead of redesigning a new tracking-by-detection algorithm, we aim to explore a general framework for building trackers directly upon almost any advanced object detector. To achieve this, three key gaps must be bridged: (1) Object detectors are class-specific, while trackers are class-agnostic. (2) Object detectors do not differentiate intra-class instances, while this is a critical capability of a tracker. (3) Temporal cues are important for stable long-term tracking while they are not considered in still-image detectors. To address the above issues, we first present a simple target-guidance module for guiding the detector to locate target-relevant objects. Then a meta-learner is adopted for the detector to fast learn and adapt a target-distractor classifier online. We further introduce an anchored updating strategy to alleviate the problem of overfitting. The framework is instantiated on SSD and FasterRCNN, the typical one- and two-stage detectors, respectively. Experiments on OTB, UAV123 and NfS have verified our framework and show that our trackers can benefit from deeper backbone networks, as opposed to many recent trackers. |
| Tasks | Object Detection |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_Bridging_the_Gap_Between_Detection_and_Tracking_A_Unified_Approach_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Huang_Bridging_the_Gap_Between_Detection_and_Tracking_A_Unified_Approach_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/bridging-the-gap-between-detection-and |
| Repo | |
| Framework | |
Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition
| Title | Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition |
| Authors | Genta Indra Winata, Zhaojiang Lin, Pascale Fung |
| Abstract | In this paper, we propose Multilingual Meta-Embeddings (MME), an effective method to learn multilingual representations by leveraging monolingual pre-trained embeddings. MME learns to utilize information from these embeddings via a self-attention mechanism without explicit language identification. We evaluate the proposed embedding method on the code-switching English-Spanish Named Entity Recognition dataset in a multilingual and cross-lingual setting. The experimental results show that our proposed method achieves state-of-the-art performance on the multilingual setting, and it has the ability to generalize to an unseen language task. |
| Tasks | Language Identification, Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4320/ |
| https://www.aclweb.org/anthology/W19-4320 | |
| PWC | https://paperswithcode.com/paper/learning-multilingual-meta-embeddings-for |
| Repo | |
| Framework | |
SymantoResearch at SemEval-2019 Task 3: Combined Neural Models for Emotion Classification in Human-Chatbot Conversations
| Title | SymantoResearch at SemEval-2019 Task 3: Combined Neural Models for Emotion Classification in Human-Chatbot Conversations |
| Authors | Angelo Basile, Marc Franco-Salvador, Neha Pawar, Sanja {\v{S}}tajner, Mara Chinea Rios, Yassine Benajiba |
| Abstract | In this paper, we present our participation to the EmoContext shared task on detecting emotions in English textual conversations between a human and a chatbot. We propose four neural systems and combine them to further improve the results. We show that our neural ensemble systems can successfully distinguish three emotions (SAD, HAPPY, and ANGRY) and separate them from the rest (OTHERS) in a highly-imbalanced scenario. Our best system achieved a 0.77 F1-score and was ranked fourth out of 165 submissions. |
| Tasks | Chatbot, Emotion Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2057/ |
| https://www.aclweb.org/anthology/S19-2057 | |
| PWC | https://paperswithcode.com/paper/symantoresearch-at-semeval-2019-task-3 |
| Repo | |
| Framework | |
Developing the Old Tibetan Treebank
| Title | Developing the Old Tibetan Treebank |
| Authors | Christian Faggionato, Marieke Meelen |
| Abstract | This paper presents a full procedure for the development of a segmented, POS-tagged and chunkparsed corpus of Old Tibetan. As an extremely low-resource language, Old Tibetan poses non-trivial problems in every step towards the development of a searchable treebank. We demonstrate, however, that a carefully developed, semisupervised method of optimising and extending existing tools for Classical Tibetan, as well as creating specific ones for Old Tibetan can address these issues. We thus also present the first very Tibetan Treebank in a variety of formats to facilitate research in the fields of NLP, historical linguistics and Tibetan Studies. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1035/ |
| https://www.aclweb.org/anthology/R19-1035 | |
| PWC | https://paperswithcode.com/paper/developing-the-old-tibetan-treebank |
| Repo | |
| Framework | |
A Combination Method for Android Malware Detection Based on Control Flow Graphs and Machine Learning Algorithms
| Title | A Combination Method for Android Malware Detection Based on Control Flow Graphs and Machine Learning Algorithms |
| Authors | Zhuo Ma, Haoran Ge, Yang Liu, Meng Zhao, Jianfeng Ma |
| Abstract | Android malware severely threaten system and user security in terms of privilege escalation, remote control, tariff theft, and privacy leakage. Therefore, it is of great importance and necessity to detect Android malware. In this paper, we present a combination method for Android malware detection based on the machine learning algorithm. First, we construct the control flow graph of the application to obtain API information. Based on the API information, we innovatively construct Boolean, frequency, and time-series data sets. Based on these three data sets, three detection models for Android malware detection regarding API calls, API frequency, and API sequence aspects are constructed. Ultimately, an ensemble model is constructed for conformity. We tested and compared the accuracy and stability of our detection models through a large number of experiments. The experiments were conducted on 10010 benign applications and 10683 malicious applications. The results show that our detection model achieves 98.98% detection precision and has high accuracy and stability. All of the results are consistent with the theoretical analysis in this paper. |
| Tasks | Android Malware Detection, Malware Detection, Time Series |
| Published | 2019-01-29 |
| URL | https://ieeexplore.ieee.org/document/8629067 |
| https://ieeexplore.ieee.org/ielx7/6287639/8600701/08629067.pdf?tp=&arnumber=8629067&isnumber=8600701&ref=aHR0cHM6Ly9pZWVleHBsb3JlLmllZWUub3JnL2RvY3VtZW50Lzg2MjkwNjc= | |
| PWC | https://paperswithcode.com/paper/a-combination-method-for-android-malware |
| Repo | |
| Framework | |
Using Graphs for Word Embedding with Enhanced Semantic Relations
| Title | Using Graphs for Word Embedding with Enhanced Semantic Relations |
| Authors | Matan Zuckerman, Mark Last |
| Abstract | Word embedding algorithms have become a common tool in the field of natural language processing. While some, like Word2Vec, are based on sequential text input, others are utilizing a graph representation of text. In this paper, we introduce a new algorithm, named WordGraph2Vec, or in short WG2V, which combines the two approaches to gain the benefits of both. The algorithm uses a directed word graph to provide additional information for sequential text input algorithms. Our experiments on benchmark datasets show that text classification algorithms are nearly as accurate with WG2V as with other word embedding models while preserving more stable accuracy rankings. |
| Tasks | Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5305/ |
| https://www.aclweb.org/anthology/D19-5305 | |
| PWC | https://paperswithcode.com/paper/using-graphs-for-word-embedding-with-enhanced |
| Repo | |
| Framework | |
Knowledge Distillation via Instance Relationship Graph
| Title | Knowledge Distillation via Instance Relationship Graph |
| Authors | Yufan Liu, Jiajiong Cao, Bing Li, Chunfeng Yuan, Weiming Hu, Yangxi Li, Yunqiang Duan |
| Abstract | The key challenge of knowledge distillation is to extract general, moderate and sufficient knowledge from a teacher network to guide a student network. In this paper, a novel Instance Relationship Graph (IRG) is proposed for knowledge distillation. It models three kinds of knowledge, including instance features, instance relationships and feature space transformation, while the latter two kinds of knowledge are neglected by previous methods. Firstly, the IRG is constructed to model the distilled knowledge of one network layer, by considering instance features and instance relationships as vertexes and edges respectively. Secondly, an IRG transformation is proposed to models the feature space transformation across layers. It is more moderate than directly mimicking the features at intermediate layers. Finally, hint loss functions are designed to force a student’s IRGs to mimic the structures of a teacher’s IRGs. The proposed method effectively captures the knowledge along the whole network via IRGs, and thus shows stable convergence and strong robustness to different network architectures. In addition, the proposed method shows superior performance over existing methods on datasets of various scales. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Knowledge_Distillation_via_Instance_Relationship_Graph_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Knowledge_Distillation_via_Instance_Relationship_Graph_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-distillation-via-instance |
| Repo | |
| Framework | |
A Topic Augmented Text Generation Model: Joint Learning of Semantics and Structural Features
| Title | A Topic Augmented Text Generation Model: Joint Learning of Semantics and Structural Features |
| Authors | Hongyin Tang, Miao Li, Beihong Jin |
| Abstract | Text generation is among the most fundamental tasks in natural language processing. In this paper, we propose a text generation model that learns semantics and structural features simultaneously. This model captures structural features by a sequential variational autoencoder component and leverages a topic modeling component based on Gaussian distribution to enhance the recognition of text semantics. To make the reconstructed text more coherent to the topics, the model further adapts the encoder of the topic modeling component for a discriminator. The results of experiments over several datasets demonstrate that our model outperforms several states of the art models in terms of text perplexity and topic coherence. Moreover, the latent representations learned by our model is superior to others in a text classification task. Finally, given the input texts, our model can generate meaningful texts which hold similar structures but under different topics. |
| Tasks | Text Classification, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1513/ |
| https://www.aclweb.org/anthology/D19-1513 | |
| PWC | https://paperswithcode.com/paper/a-topic-augmented-text-generation-model-joint |
| Repo | |
| Framework | |
Partially Mutual Exclusive Softmax for Positive and Unlabeled data
| Title | Partially Mutual Exclusive Softmax for Positive and Unlabeled data |
| Authors | Ugo Tanielian, Flavian vasile, Mike Gartrell |
| Abstract | In recent years, softmax together with its fast approximations has become the de-facto loss function for deep neural networks with multiclass predictions. However, softmax is used in many problems that do not fully fit the multiclass framework and where the softmax assumption of mutually exclusive outcomes can lead to biased results. This is often the case for applications such as language modeling, next event prediction and matrix factorization, where many of the potential outcomes are not mutually exclusive, but are more likely to be independent conditionally on the state. To this end, for the set of problems with positive and unlabeled data, we propose a relaxation of the original softmax formulation, where, given the observed state, each of the outcomes are conditionally independent but share a common set of negatives. Since we operate in a regime where explicit negatives are missing, we create an adversarially-trained model of negatives and derive a new negative sampling and weighting scheme which we denote as Cooperative Importance Sampling (CIS). We show empirically the advantages of our newly introduced negative sampling scheme by pluging it in the Word2Vec algorithm and benching it extensively against other negative sampling schemes on both language modeling and matrix factorization tasks and show large lifts in performance. |
| Tasks | Language Modelling |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkx0g3R5tX |
| https://openreview.net/pdf?id=rkx0g3R5tX | |
| PWC | https://paperswithcode.com/paper/partially-mutual-exclusive-softmax-for |
| Repo | |
| Framework | |
Recurrent Positional Embedding for Neural Machine Translation
| Title | Recurrent Positional Embedding for Neural Machine Translation |
| Authors | Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita |
| Abstract | In the Transformer network architecture, positional embeddings are used to encode order dependencies into the input representation. However, this input representation only involves static order dependencies based on discrete numerical information, that is, are independent of word content. To address this issue, this work proposes a recurrent positional embedding approach based on word vector. In this approach, these recurrent positional embeddings are learned by a recurrent neural network, encoding word content-based order dependencies into the input representation. They are then integrated into the existing multi-head self-attention model as independent heads or part of each head. The experimental results revealed that the proposed approach improved translation performance over that of the state-of-the-art Transformer baseline in WMT{'}14 English-to-German and NIST Chinese-to-English translation tasks. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1139/ |
| https://www.aclweb.org/anthology/D19-1139 | |
| PWC | https://paperswithcode.com/paper/recurrent-positional-embedding-for-neural |
| Repo | |
| Framework | |
