Paper Group NANR 66
Neural News Recommendation with Heterogeneous User Behavior. Comparison between Automatic and Human Subtitling: A Case Study with Game of Thrones. Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks. Second-order contexts from lexical substitutes for few-shot learning of word representations. Overview of t …
Neural News Recommendation with Heterogeneous User Behavior
| Title | Neural News Recommendation with Heterogeneous User Behavior |
| Authors | Chuhan Wu, Fangzhao Wu, Mingxiao An, Tao Qi, Jianqiang Huang, Yongfeng Huang, Xing Xie |
| Abstract | News recommendation is important for online news platforms to help users find interested news and alleviate information overload. Existing news recommendation methods usually rely on the news click history to model user interest. However, these methods may suffer from the data sparsity problem, since the news click behaviors of many users in online news platforms are usually very limited. Fortunately, some other kinds of user behaviors such as webpage browsing and search queries can also provide useful clues of users{'} news reading interest. In this paper, we propose a neural news recommendation approach which can exploit heterogeneous user behaviors. Our approach contains two major modules, i.e., news representation and user representation. In the news representation module, we learn representations of news from their titles via CNN networks, and apply attention networks to select important words. In the user representation module, we propose an attentive multi-view learning framework to learn unified representations of users from their heterogeneous behaviors such as search queries, clicked news and browsed webpages. In addition, we use word- and record-level attentions to select informative words and behavior records. Experiments on a real-world dataset validate the effectiveness of our approach. |
| Tasks | MULTI-VIEW LEARNING |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1493/ |
| https://www.aclweb.org/anthology/D19-1493 | |
| PWC | https://paperswithcode.com/paper/neural-news-recommendation-with-heterogeneous |
| Repo | |
| Framework | |
Comparison between Automatic and Human Subtitling: A Case Study with Game of Thrones
| Title | Comparison between Automatic and Human Subtitling: A Case Study with Game of Thrones |
| Authors | Sabrina Baldo de Br{'e}bisson |
| Abstract | In this submission, I would like to share my experiences with the software DeepL and the comparison analysis I have made with human subtitling offered by the DVD version of the corpus I have chosen as the topic of my study {–} the eight Seasons of Game of Thrones. The idea is to study if the version proposed by an automatic translation program could be used as a first draft for the professional subtitler. It is expected that the latter would work on the form of the subtitles, that is to say mainly on their length, in a second step. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8701/ |
| https://www.aclweb.org/anthology/W19-8701 | |
| PWC | https://paperswithcode.com/paper/comparison-between-automatic-and-human |
| Repo | |
| Framework | |
Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks
| Title | Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks |
| Authors | Junjie Zhang, Qi Wu, Jian Zhang, Chunhua Shen, Jianfeng Lu |
| Abstract | As the visual reflections of our daily lives, images are frequently shared on the social network, which generates the abundant ‘metadata’ that records user interactions with images. Due to the diverse contents and complex styles, some images can be challenging to recognise when neglecting the context. Images with the similar metadata, such as ‘relevant topics and textual descriptions’, ‘common friends of users’ and ‘nearby locations’, form a neighbourhood for each image, which can be used to assist the annotation. In this paper, we propose a Metadata Neighbourhood Graph Co-Attention Network (MangoNet) to model the correlations between each target image and its neighbours. To accurately capture the visual clues from the neighbourhood, a co-attention mechanism is introduced to embed the target image and its neighbours as graph nodes, while the graph edges capture the node pair correlations. By reasoning on the neighbourhood graph, we obtain the graph representation to help annotate the target image. Experimental results on three benchmark datasets indicate that our proposed model achieves the best performance compared to the state-of-the-art methods. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Mind_Your_Neighbours_Image_Annotation_With_Metadata_Neighbourhood_Graph_Co-Attention_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Mind_Your_Neighbours_Image_Annotation_With_Metadata_Neighbourhood_Graph_Co-Attention_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mind-your-neighbours-image-annotation-with |
| Repo | |
| Framework | |
Second-order contexts from lexical substitutes for few-shot learning of word representations
| Title | Second-order contexts from lexical substitutes for few-shot learning of word representations |
| Authors | Qianchu Liu, Diana McCarthy, Anna Korhonen |
| Abstract | There is a growing awareness of the need to handle rare and unseen words in word representation modelling. In this paper, we focus on few-shot learning of emerging concepts that fully exploits only a few available contexts. We introduce a substitute-based context representation technique that can be applied on an existing word embedding space. Previous context-based approaches to modelling unseen words only consider bag-of-word first-order contexts, whereas our method aggregates contexts as second-order substitutes that are produced by a sequence-aware sentence completion model. We experimented with three tasks that aim to test the modelling of emerging concepts. We found that these tasks show different emphasis on first and second order contexts, and our substitute-based method achieves superior performance on naturally-occurring contexts from corpora. |
| Tasks | Few-Shot Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1007/ |
| https://www.aclweb.org/anthology/S19-1007 | |
| PWC | https://paperswithcode.com/paper/second-order-contexts-from-lexical |
| Repo | |
| Framework | |
Overview of the 2019 ALTA Shared Task: Sarcasm Target Identification
| Title | Overview of the 2019 ALTA Shared Task: Sarcasm Target Identification |
| Authors | Diego Molla, Aditya Joshi |
| Abstract | We present an overview of the 2019 ALTA shared task. This is the 10th of the series of shared tasks organised by ALTA since 2010. The task was to detect the target of sarcastic comments posted on social media. We intro- duce the task, describe the data and present the results of baselines and participants. This year{'}s shared task was particularly challenging and no participating systems improved the re- sults of our baseline. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1026/ |
| https://www.aclweb.org/anthology/U19-1026 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-2019-alta-shared-task-sarcasm |
| Repo | |
| Framework | |
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
| Title | Intrinsic Social Motivation via Causal Influence in Multi-Agent RL |
| Authors | Natasha Jaques, Angeliki Lazaridou, Edward Hughes, Caglar Gulcehre, Pedro A. Ortega, DJ Strouse, Joel Z. Leibo, Nando de Freitas |
| Abstract | We derive a new intrinsic social motivation for multi-agent reinforcement learning (MARL), in which agents are rewarded for having causal influence over another agent’s actions, where causal influence is assessed using counterfactual reasoning. The reward does not depend on observing another agent’s reward function, and is thus a more realistic approach to MARL than taken in previous work. We show that the causal influence reward is related to maximizing the mutual information between agents’ actions. We test the approach in challenging social dilemma environments, where it consistently leads to enhanced cooperation between agents and higher collective reward. Moreover, we find that rewarding influence can lead agents to develop emergent communication protocols. Therefore, we also employ influence to train agents to use an explicit communication channel, and find that it leads to more effective communication and higher collective reward. Finally, we show that influence can be computed by equipping each agent with an internal model that predicts the actions of other agents. This allows the social influence reward to be computed without the use of a centralised controller, and as such represents a significantly more general and scalable inductive bias for MARL with independent agents. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1lG42C9Km |
| https://openreview.net/pdf?id=B1lG42C9Km | |
| PWC | https://paperswithcode.com/paper/intrinsic-social-motivation-via-causal |
| Repo | |
| Framework | |
Curio SmartChat : A system for Natural Language Question Answering for Self-Paced K-12 Learning
| Title | Curio SmartChat : A system for Natural Language Question Answering for Self-Paced K-12 Learning |
| Authors | Srikrishna Raamadhurai, Ryan Baker, Vikraman Poduval |
| Abstract | During learning, students often have questions which they would benefit from responses to in real time. In class, a student can ask a question to a teacher. During homework, or even in class if the student is shy, it can be more difficult to receive a rapid response. In this work, we introduce Curio SmartChat, an automated question answering system for middle school Science topics. Our system has now been used by around 20,000 students who have so far asked over 100,000 questions. We present data on the challenge created by students{'} grammatical errors and spelling mistakes, and discuss our system{'}s approach and degree of effectiveness at disambiguating questions that the system is initially unsure about. We also discuss the prevalence of student {``}small talk{''} not related to science topics, the pluses and minuses of this behavior, and how a system should respond to these conversational acts. We conclude with discussions and point to directions for potential future work. | |
| Tasks | Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4435/ |
| https://www.aclweb.org/anthology/W19-4435 | |
| PWC | https://paperswithcode.com/paper/curio-smartchat-a-system-for-natural-language |
| Repo | |
| Framework | |
Learning Instance Activation Maps for Weakly Supervised Instance Segmentation
| Title | Learning Instance Activation Maps for Weakly Supervised Instance Segmentation |
| Authors | Yi Zhu, Yanzhao Zhou, Huijuan Xu, Qixiang Ye, David Doermann, Jianbin Jiao |
| Abstract | Discriminative region responses residing inside an object instance can be extracted from networks trained with image-level label supervision. However, learning the full extent of pixel-level instance response in a weakly supervised manner remains unexplored. In this work, we tackle this challenging problem by using a novel instance extent filling approach. We first design a process to selectively collect pseudo supervision from noisy segment proposals obtained with previously published techniques. The pseudo supervision is used to learn a differentiable filling module that predicts a class-agnostic activation map for each instance given the image and an incomplete region response. We refer to the above maps as Instance Activation Maps (IAMs), which provide a fine-grained instance-level representation and allow instance masks to be extracted by lightweight CRF. Extensive experiments on the PASCAL VOC12 dataset show that our approach beats the state-of-the-art weakly supervised instance segmentation methods by a significant margin and increases the inference speed by an order of magnitude. Our method also generalizes well across domains and to unseen object categories. Without fine-tuning for the specific tasks, our model trained on VOC12 dataset (20 classes) obtains top performance for weakly supervised object localization on the CUB dataset (200 classes) and achieves competitive results on three widely used salient object detection benchmarks. |
| Tasks | Instance Segmentation, Object Detection, Object Localization, Salient Object Detection, Semantic Segmentation, Weakly-supervised instance segmentation, Weakly-Supervised Object Localization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhu_Learning_Instance_Activation_Maps_for_Weakly_Supervised_Instance_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhu_Learning_Instance_Activation_Maps_for_Weakly_Supervised_Instance_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-instance-activation-maps-for-weakly |
| Repo | |
| Framework | |
Robustness Verification of Classification Deep Neural Networks via Linear Programming
| Title | Robustness Verification of Classification Deep Neural Networks via Linear Programming |
| Authors | Wang Lin, Zhengfeng Yang, Xin Chen, Qingye Zhao, Xiangkun Li, Zhiming Liu, Jifeng He |
| Abstract | There is a pressing need to verify robustness of classification deep neural networks (CDNNs) as they are embedded in many safety-critical applications. Existing robustness verification approaches rely on computing the over-approximation of the output set, and can hardly scale up to practical CDNNs, as the result of error accumulation accompanied with approximation. In this paper, we develop a novel method for robustness verification of CDNNs with sigmoid activation functions. It converts the robustness verification problem into an equivalent problem of inspecting the most suspected point in the input region which constitutes a nonlinear optimization problem. To make it amenable, by relaxing the nonlinear constraints into the linear inclusions, it is further refined as a linear programming problem. We conduct comparison experiments on a few CDNNs trained for classifying images in some state-of-the-art benchmarks, showing our advantages of precision and scalability that enable effective verification of practical CDNNs. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lin_Robustness_Verification_of_Classification_Deep_Neural_Networks_via_Linear_Programming_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lin_Robustness_Verification_of_Classification_Deep_Neural_Networks_via_Linear_Programming_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robustness-verification-of-classification |
| Repo | |
| Framework | |
Computational Linguistics for Enhancing Scientific Reproducibility and Reducing Healthcare Inequities
| Title | Computational Linguistics for Enhancing Scientific Reproducibility and Reducing Healthcare Inequities |
| Authors | Julia Parish-Morris |
| Abstract | Computational linguistics holds promise for improving scientific integrity in clinical psychology, and for reducing longstanding inequities in healthcare access and quality. This paper describes how computational linguistics approaches could address the {``}reproducibility crisis{''} facing social science, particularly with regards to reliable diagnosis of neurodevelopmental and psychiatric conditions including autism spectrum disorder (ASD). It is argued that these improvements in scientific integrity are poised to naturally reduce persistent healthcare inequities in neglected subpopulations, such as verbally fluent girls and women with ASD, but that concerted attention to this issue is necessary to avoid reproducing biases built into training data. Finally, it is suggested that computational linguistics is just one component of an emergent digital phenotyping toolkit that could ultimately be used for clinical decision support, to improve clinical care via precision medicine (i.e., personalized intervention planning), granular treatment response monitoring (including remotely), and for gene-brain-behavior studies aiming to pinpoint the underlying biological etiology of otherwise behaviorally-defined conditions like ASD. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3011/ |
| https://www.aclweb.org/anthology/W19-3011 | |
| PWC | https://paperswithcode.com/paper/computational-linguistics-for-enhancing |
| Repo | |
| Framework | |
Highly Effective Arabic Diacritization using Sequence to Sequence Modeling
| Title | Highly Effective Arabic Diacritization using Sequence to Sequence Modeling |
| Authors | Hamdy Mubarak, Ahmed Abdelali, Hassan Sajjad, Younes Samih, Kareem Darwish |
| Abstract | Arabic text is typically written without short vowels (or diacritics). However, their presence is required for properly verbalizing Arabic and is hence essential for applications such as text to speech. There are two types of diacritics, namely core-word diacritics and case-endings. Most previous works on automatic Arabic diacritic recovery rely on a large number of manually engineered features, particularly for case-endings. In this work, we present a unified character level sequence-to-sequence deep learning model that recovers both types of diacritics without the use of explicit feature engineering. Specifically, we employ a standard neural machine translation setup on overlapping windows of words (broken down into characters), and then we use voting to select the most likely diacritized form of a word. The proposed model outperforms all previous state-of-the-art systems. Our best settings achieve a word error rate (WER) of 4.49{%} compared to the state-of-the-art of 12.25{%} on a standard dataset. |
| Tasks | Feature Engineering, Machine Translation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1248/ |
| https://www.aclweb.org/anthology/N19-1248 | |
| PWC | https://paperswithcode.com/paper/highly-effective-arabic-diacritization-using |
| Repo | |
| Framework | |
Proceedings of the IWCS 2019 Workshop on Computing Semantics with Types, Frames and Related Structures
| Title | Proceedings of the IWCS 2019 Workshop on Computing Semantics with Types, Frames and Related Structures |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1000/ |
| https://www.aclweb.org/anthology/W19-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-iwcs-2019-workshop-on |
| Repo | |
| Framework | |
ImageTTR: Grounding Type Theory with Records in Image Classification for Visual Question Answering
| Title | ImageTTR: Grounding Type Theory with Records in Image Classification for Visual Question Answering |
| Authors | Arild Matsson, Simon Dobnik, Staffan Larsson |
| Abstract | |
| Tasks | Image Classification, Question Answering, Visual Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1007/ |
| https://www.aclweb.org/anthology/W19-1007 | |
| PWC | https://paperswithcode.com/paper/imagettr-grounding-type-theory-with-records |
| Repo | |
| Framework | |
Proceedings of the Sixth Workshop on Natural Language and Computer Science
| Title | Proceedings of the Sixth Workshop on Natural Language and Computer Science |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-1100/ |
| https://www.aclweb.org/anthology/W19-1100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-sixth-workshop-on-natural |
| Repo | |
| Framework | |
Evaluation of named entity coreference
| Title | Evaluation of named entity coreference |
| Authors | Oshin Agarwal, Sanjay Subramanian, Ani Nenkova, Dan Roth |
| Abstract | In many NLP applications like search and information extraction for named entities, it is necessary to find all the mentions of a named entity, some of which appear as pronouns (she, his, etc.) or nominals (the professor, the German chancellor, etc.). It is therefore important that coreference resolution systems are able to link these different types of mentions to the correct entity name. We evaluate state-of-the-art coreference resolution systems for the task of resolving all mentions to named entities. Our analysis reveals that standard coreference metrics do not reflect adequately the requirements in this task: they do not penalize systems for not identifying any mentions by name to an entity and they reward systems even if systems find correctly mentions to the same entity but fail to link these to a proper name (she{–}the student{–}no name). We introduce new metrics for evaluating named entity coreference that address these discrepancies and show that for the comparisons of competitive systems, standard coreference evaluations could give misleading results for this task. We are, however, able to confirm that the state-of-the art system according to traditional evaluations also performs vastly better than other systems on the named entity coreference task. |
| Tasks | Coreference Resolution |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2801/ |
| https://www.aclweb.org/anthology/W19-2801 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-named-entity-coreference |
| Repo | |
| Framework | |
