Paper Group NANR 50
View-LSTM: Novel-View Video Synthesis Through View Decomposition. A System to Monitor Cyberbullying based on Message Classification and Social Network Analysis. Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units. A Semantic Ontology of Danish Adjectives. Gradient constraints on the use of Estonian possessive refle …
View-LSTM: Novel-View Video Synthesis Through View Decomposition
| Title | View-LSTM: Novel-View Video Synthesis Through View Decomposition |
| Authors | Mohamed Ilyes Lakhal, Oswald Lanz, Andrea Cavallaro |
| Abstract | We tackle the problem of synthesizing a video of multiple moving people as seen from a novel view, given only an input video and depth information or human poses of the novel view as prior. This problem requires a model that learns to transform input features into target features while maintaining temporal consistency. To this end, we learn an invariant feature from the input video that is shared across all viewpoints of the same scene and a view-dependent feature obtained using the target priors. The proposed approach, View-LSTM, is a recurrent neural network structure that accounts for the temporal consistency and target feature approximation constraints. We validate View-LSTM by designing an end-to-end generator for novel-view video synthesis. Experiments on a large multi-view action recognition dataset validate the proposed model. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Lakhal_View-LSTM_Novel-View_Video_Synthesis_Through_View_Decomposition_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Lakhal_View-LSTM_Novel-View_Video_Synthesis_Through_View_Decomposition_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/view-lstm-novel-view-video-synthesis-through |
| Repo | |
| Framework | |
A System to Monitor Cyberbullying based on Message Classification and Social Network Analysis
| Title | A System to Monitor Cyberbullying based on Message Classification and Social Network Analysis |
| Authors | Stefano Menini, Giovanni Moretti, Michele Corazza, Elena Cabrio, Sara Tonelli, Serena Villata |
| Abstract | Social media platforms like Twitter and Instagram face a surge in cyberbullying phenomena against young users and need to develop scalable computational methods to limit the negative consequences of this kind of abuse. Despite the number of approaches recently proposed in the Natural Language Processing (NLP) research area for detecting different forms of abusive language, the issue of identifying cyberbullying phenomena at scale is still an unsolved problem. This is because of the need to couple abusive language detection on textual message with network analysis, so that repeated attacks against the same person can be identified. In this paper, we present a system to monitor cyberbullying phenomena by combining message classification and social network analysis. We evaluate the classification module on a data set built on Instagram messages, and we describe the cyberbullying monitoring user interface. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3511/ |
| https://www.aclweb.org/anthology/W19-3511 | |
| PWC | https://paperswithcode.com/paper/a-system-to-monitor-cyberbullying-based-on |
| Repo | |
| Framework | |
Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units
| Title | Accelerating Sparse Matrix Operations in Neural Networks on Graphics Processing Units |
| Authors | Arturo Argueta, David Chiang |
| Abstract | Graphics Processing Units (GPUs) are commonly used to train and evaluate neural networks efficiently. While previous work in deep learning has focused on accelerating operations on dense matrices/tensors on GPUs, efforts have concentrated on operations involving sparse data structures. Operations using sparse structures are common in natural language models at the input and output layers, because these models operate on sequences over discrete alphabets. We present two new GPU algorithms: one at the input layer, for multiplying a matrix by a few-hot vector (generalizing the more common operation of multiplication by a one-hot vector) and one at the output layer, for a fused softmax and top-N selection (commonly used in beam search). Our methods achieve speedups over state-of-the-art parallel GPU baselines of up to 7x and 50x, respectively. We also illustrate how our methods scale on different GPU architectures. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1626/ |
| https://www.aclweb.org/anthology/P19-1626 | |
| PWC | https://paperswithcode.com/paper/accelerating-sparse-matrix-operations-in |
| Repo | |
| Framework | |
A Semantic Ontology of Danish Adjectives
| Title | A Semantic Ontology of Danish Adjectives |
| Authors | Eckhard Bick |
| Abstract | This paper presents a semantic annotation scheme for Danish adjectives, focusing both on prototypical semantic content and semantic collocational restrictions on an adjective{'}s head noun. The core type set comprises about 110 categories ordered in a shallow hierarchy with 14 primary and 25 secondary umbrella categories. In addition, domain information and binary sentiment tags are provided, as well as VerbNet-derived frames and semantic roles for those adjectives governing arguments. The scheme has been almost fully implemented on the lexicon of the Danish VISL parser, DanGram, containing 14,000 adjectives. We discuss the annotation scheme and its applicational perspectives, and present a statistical breakdown and coverage evaluation for three Danish reference corpora. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0406/ |
| https://www.aclweb.org/anthology/W19-0406 | |
| PWC | https://paperswithcode.com/paper/a-semantic-ontology-of-danish-adjectives |
| Repo | |
| Framework | |
Gradient constraints on the use of Estonian possessive reflexives
| Title | Gradient constraints on the use of Estonian possessive reflexives |
| Authors | Suzanne Lesage, Olivier Bonami |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7914/ |
| https://www.aclweb.org/anthology/W19-7914 | |
| PWC | https://paperswithcode.com/paper/gradient-constraints-on-the-use-of-estonian |
| Repo | |
| Framework | |
Survey of Uralic Universal Dependencies development
| Title | Survey of Uralic Universal Dependencies development |
| Authors | Niko Partanen, Jack Rueter |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-8009/ |
| https://www.aclweb.org/anthology/W19-8009 | |
| PWC | https://paperswithcode.com/paper/survey-of-uralic-universal-dependencies |
| Repo | |
| Framework | |
Toward Cross-theory Discourse Relation Annotation
| Title | Toward Cross-theory Discourse Relation Annotation |
| Authors | Peter Bourgonje, Olha Zolotarenko |
| Abstract | In this exploratory study, we attempt to automatically induce PDTB-style relations from RST trees. We work with a German corpus of news commentary articles, annotated for RST trees and explicit PDTB-style relations and we focus on inducing the implicit relations in an automated way. Preliminary results look promising as a high-precision (but low-recall) way of finding implicit relations where there is no shallow structure annotated at all, but mapping proves more difficult in cases where EDUs and relation arguments overlap, yet do not seem to signal the same relation. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2702/ |
| https://www.aclweb.org/anthology/W19-2702 | |
| PWC | https://paperswithcode.com/paper/toward-cross-theory-discourse-relation |
| Repo | |
| Framework | |
From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion
| Title | From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion |
| Authors | Roy Bar-Haim, Dalia Krieger, Orith Toledo-Ronen, Lilach Edelstein, Yonatan Bilu, Alon Halfon, Yoav Katz, Amir Menczel, Ranit Aharonov, Noam Slonim |
| Abstract | When debating a controversial topic, it is often desirable to expand the boundaries of discussion. For example, we may consider the pros and cons of possible alternatives to the debate topic, make generalizations, or give specific examples. We introduce the task of Debate Topic Expansion - finding such related topics for a given debate topic, along with a novel annotated dataset for the task. We focus on relations between Wikipedia concepts, and show that they differ from well-studied lexical-semantic relations such as hypernyms, hyponyms and antonyms. We present algorithms for finding both consistent and contrastive expansions and demonstrate their effectiveness empirically. We suggest that debate topic expansion may have various use cases in argumentation mining. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1094/ |
| https://www.aclweb.org/anthology/P19-1094 | |
| PWC | https://paperswithcode.com/paper/from-surrogacy-to-adoption-from-bitcoin-to |
| Repo | |
| Framework | |
Multi-task Learning with Gradient Communication
| Title | Multi-task Learning with Gradient Communication |
| Authors | Pengfei Liu, Xuanjing Huang |
| Abstract | In this paper, we describe a general framework to systematically analyze current neural models for multi-task learning, in which we find that existing models expect to disentangle features into different spaces while features learned in practice are still entangled in shared space, leaving potential hazards for other training or unseen tasks. We propose to alleviate this problem by incorporating a new inductive bias into the process of multi-task learning, that different tasks can communicate with each other not only by passing hidden variables but gradients explicitly. Experimentally, we evaluate proposed methods on three groups of tasks and two types of settings (\textsc{in-task} and \textsc{out-of-task}). Quantitative and qualitative results show their effectiveness. |
| Tasks | Multi-Task Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1e9W3AqFX |
| https://openreview.net/pdf?id=B1e9W3AqFX | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-with-gradient |
| Repo | |
| Framework | |
Controlled Semi-automatic Annotation of Classical Ethiopic
| Title | Controlled Semi-automatic Annotation of Classical Ethiopic |
| Authors | Cristina Vertan |
| Abstract | Preservation of the cultural heritage by means of digital methods became extremely popular during last years. After intensive digitization campaigns the focus moves slowly from the genuine preservation (i.e digital archiving together with standard search mechanisms) to research-oriented usage of materials available electronically. This usage is intended to go far beyond simple reading of digitized materials; researchers should be able to gain new insigts in materials, discover new facts by means of tools relying on innovative algorithms. In this article we will describe the workflow necessary for the annotation of a dichronic corpus of classical Ethiopic, language of essential importance for the study of Early Christianity |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-9004/ |
| https://www.aclweb.org/anthology/W19-9004 | |
| PWC | https://paperswithcode.com/paper/controlled-semi-automatic-annotation-of |
| Repo | |
| Framework | |
FriendsQA: Open-Domain Question Answering on TV Show Transcripts
| Title | FriendsQA: Open-Domain Question Answering on TV Show Transcripts |
| Authors | Zhengzhe Yang, Jinho D. Choi |
| Abstract | This paper presents FriendsQA, a challenging question answering dataset that contains 1,222 dialogues and 10,610 open-domain questions, to tackle machine comprehension on everyday conversations. Each dialogue, involving multiple speakers, is annotated with several types of questions regarding the dialogue contexts, and the answers are annotated with certain spans in the dialogue. A series of crowdsourcing tasks are conducted to ensure good annotation quality, resulting a high inter-annotator agreement of 81.82{%}. A comprehensive annotation analytics is provided for a deeper understanding in this dataset. Three state-of-the-art QA systems are experimented, R-Net, QANet, and BERT, and evaluated on this dataset. BERT in particular depicts promising results, an accuracy of 74.2{%} for answer utterance selection and an F1-score of 64.2{%} for answer span selection, suggesting that the FriendsQA task is hard yet has a great potential of elevating QA research on multiparty dialogue to another level. |
| Tasks | Open-Domain Question Answering, Question Answering, Reading Comprehension |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5923/ |
| https://www.aclweb.org/anthology/W19-5923 | |
| PWC | https://paperswithcode.com/paper/friendsqa-open-domain-question-answering-on |
| Repo | |
| Framework | |
Influence of Time and Risk on Response Acceptability in a Simple Spoken Dialogue System
| Title | Influence of Time and Risk on Response Acceptability in a Simple Spoken Dialogue System |
| Authors | Andisheh Partovi, Ingrid Zukerman |
| Abstract | We describe a longitudinal user study conducted in the context of a Spoken Dialogue System for a household robot, where we examined the influence of time displacement and situational risk on users{'} preferred responses. To this effect, we employed a corpus of spoken requests that asked a robot to fetch or move objects in a room. In the first stage of our study, participants selected among four response types to these requests under two risk conditions: low and high. After some time, the same participants rated several responses to the previous requests {—} these responses were instantiated from the four response types. Our results show that participants did not rate highly their own response types; moreover, they rated their own response types similarly to different ones. This suggests that, at least in this context, people{'}s preferences at a particular point in time may not reflect their general attitudes, and that various reasonable response types may be equally acceptable. Our study also reveals that situational risk influences the acceptability of some response types. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5936/ |
| https://www.aclweb.org/anthology/W19-5936 | |
| PWC | https://paperswithcode.com/paper/influence-of-time-and-risk-on-response |
| Repo | |
| Framework | |
Dissecting an Adversarial framework for Information Retrieval
| Title | Dissecting an Adversarial framework for Information Retrieval |
| Authors | Ameet Deshpande, Mitesh M.Khapra |
| Abstract | Recent advances in Generative Adversarial Networks facilitated by improvements to the framework and successful application to various problems has resulted in extensions to multiple domains. IRGAN attempts to leverage the framework for Information-Retrieval (IR), a task that can be described as modeling the correct conditional probability distribution p(dq) over the documents (d), given the query (q). The work that proposes IRGAN claims that optimizing their minimax loss function will result in a generator which can learn the distribution, but their setup and baseline term steer the model away from an exact adversarial formulation, and this work attempts to point out certain inaccuracies in their formulation. Analyzing their loss curves gives insight into possible mistakes in the loss functions and better performance can be obtained by using the co-training like setup we propose, where two models are trained in a co-operative rather than an adversarial fashion. |
| Tasks | Information Retrieval |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Syez3j0cKX |
| https://openreview.net/pdf?id=Syez3j0cKX | |
| PWC | https://paperswithcode.com/paper/dissecting-an-adversarial-framework-for |
| Repo | |
| Framework | |
Towards Latent Attribute Discovery From Triplet Similarities
| Title | Towards Latent Attribute Discovery From Triplet Similarities |
| Authors | Ishan Nigam, Pavel Tokmakov, Deva Ramanan |
| Abstract | This paper addresses the task of learning latent attributes from triplet similarity comparisons. Consider, for instance, the three shoes in Fig. 1(a). They can be compared according to color, comfort, size, or shape resulting in different rankings. Most approaches for embedding learning either make a simplifying assumption - that all inputs are comparable under a single criterion, or require expensive attribute supervision. We introduce Latent Similarity Networks (LSNs): a simple and effective technique to discover the underlying latent notions of similarity in data without any explicit attribute supervision. LSNs can be trained with standard triplet supervision and learn several latent embeddings that can be used to compare images under multiple notions of similarity. LSNs achieve state-of-the-art performance on UT-Zappos-50k Shoes and Celeb-A Faces datasets and also demonstrate the ability to uncover meaningful latent attributes. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Nigam_Towards_Latent_Attribute_Discovery_From_Triplet_Similarities_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Nigam_Towards_Latent_Attribute_Discovery_From_Triplet_Similarities_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/towards-latent-attribute-discovery-from |
| Repo | |
| Framework | |
An explanation of the decisive role of function words in driving syntactic development
| Title | An explanation of the decisive role of function words in driving syntactic development |
| Authors | Anat Ninio |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7907/ |
| https://www.aclweb.org/anthology/W19-7907 | |
| PWC | https://paperswithcode.com/paper/an-explanation-of-the-decisive-role-of |
| Repo | |
| Framework | |
