Paper Group NANR 2
Summary Cloze: A New Task for Content Selection in Topic-Focused Summarization. SNAP-BATNET: Cascading Author Profiling and Social Network Graphs for Suicide Ideation Detection on Social Media. LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation. Neural machine translation system for the Kazakh language. A unified theory of a …
Summary Cloze: A New Task for Content Selection in Topic-Focused Summarization
| Title | Summary Cloze: A New Task for Content Selection in Topic-Focused Summarization |
| Authors | Daniel Deutsch, Dan Roth |
| Abstract | A key challenge in topic-focused summarization is determining what information should be included in the summary, a problem known as content selection. In this work, we propose a new method for studying content selection in topic-focused summarization called the summary cloze task. The goal of the summary cloze task is to generate the next sentence of a summary conditioned on the beginning of the summary, a topic, and a reference document(s). The main challenge is deciding what information in the references is relevant to the topic and partial summary and should be included in the summary. Although the cloze task does not address all aspects of the traditional summarization problem, the more narrow scope of the task allows us to collect a large-scale datset of nearly 500k summary cloze instances from Wikipedia. We report experimental results on this new dataset using various extractive models and a two-step abstractive model that first extractively selects a small number of sentences and then abstractively summarizes them. Our results show that the topic and partial summary help the models identify relevant content, but the task remains a significant challenge. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1386/ |
| https://www.aclweb.org/anthology/D19-1386 | |
| PWC | https://paperswithcode.com/paper/summary-cloze-a-new-task-for-content |
| Repo | |
| Framework | |
SNAP-BATNET: Cascading Author Profiling and Social Network Graphs for Suicide Ideation Detection on Social Media
| Title | SNAP-BATNET: Cascading Author Profiling and Social Network Graphs for Suicide Ideation Detection on Social Media |
| Authors | Rohan Mishra, Pradyumn Prakhar Sinha, Ramit Sawhney, Debanjan Mahata, Puneet Mathur, Rajiv Ratn Shah |
| Abstract | Suicide is a leading cause of death among youth and the use of social media to detect suicidal ideation is an active line of research. While it has been established that these users share a common set of properties, the current state-of-the-art approaches utilize only text-based (stylistic and semantic) cues. We contend that the use of information from networks in the form of condensed social graph embeddings and author profiling using features from historical data can be combined with an existing set of features to improve the performance. To that end, we experiment on a manually annotated dataset of tweets created using a three-phase strategy and propose SNAP-BATNET, a deep learning based model to extract text-based features and a novel Feature Stacking approach to combine other community-based information such as historical author profiling and graph embeddings that outperform the current state-of-the-art. We conduct a comprehensive quantitative analysis with baselines, both generic and specific, that presents the case for SNAP-BATNET, along with an error analysis that highlights the limitations and challenges faced paving the way to the future of AI-based suicide ideation detection. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-3019/ |
| https://www.aclweb.org/anthology/N19-3019 | |
| PWC | https://paperswithcode.com/paper/snap-batnet-cascading-author-profiling-and |
| Repo | |
| Framework | |
LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation
| Title | LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation |
| Authors | Sunok Kim, Seungryong Kim, Dongbo Min, Kwanghoon Sohn |
| Abstract | We present a novel method that estimates confidence map of an initial disparity by making full use of tri-modal input, including matching cost, disparity, and color image through deep networks. The proposed network, termed as Locally Adaptive Fusion Networks (LAF-Net), learns locally-varying attention and scale maps to fuse the tri-modal confidence features. The attention inference networks encode the importance of tri-modal confidence features and then concatenate them using the attention maps in an adaptive and dynamic fashion. This enables us to make an optimal fusion of the heterogeneous features, compared to a simple concatenation technique that is commonly used in conventional approaches. In addition, to encode the confidence features with locally-varying receptive fields, the scale inference networks learn the scale map and warp the fused confidence features through convolutional spatial transformer networks. Finally, the confidence map is progressively estimated in the recursive refinement networks to enforce a spatial context and local consistency. Experimental results show that this model outperforms the state-of-the-art methods on various benchmarks. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Kim_LAF-Net_Locally_Adaptive_Fusion_Networks_for_Stereo_Confidence_Estimation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Kim_LAF-Net_Locally_Adaptive_Fusion_Networks_for_Stereo_Confidence_Estimation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/laf-net-locally-adaptive-fusion-networks-for |
| Repo | |
| Framework | |
Neural machine translation system for the Kazakh language
| Title | Neural machine translation system for the Kazakh language |
| Authors | Ualsher Tukeyev, Zh Zhumanov, os |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6724/ |
| https://www.aclweb.org/anthology/W19-6724 | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-system-for-the |
| Repo | |
| Framework | |
A unified theory of adaptive stochastic gradient descent as Bayesian filtering
| Title | A unified theory of adaptive stochastic gradient descent as Bayesian filtering |
| Authors | Laurence Aitchison |
| Abstract | We formulate stochastic gradient descent (SGD) as a novel factorised Bayesian filtering problem, in which each parameter is inferred separately, conditioned on the corresopnding backpropagated gradient. Inference in this setting naturally gives rise to BRMSprop and BAdam: Bayesian variants of RMSprop and Adam. Remarkably, the Bayesian approach recovers many features of state-of-the-art adaptive SGD methods, including amongst others root-mean-square normalization, Nesterov acceleration and AdamW. As such, the Bayesian approach provides one explanation for the empirical effectiveness of state-of-the-art adaptive SGD algorithms. Empirically comparing BRMSprop and BAdam with naive RMSprop and Adam on MNIST, we find that Bayesian methods have the potential to considerably reduce test loss and classification error. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BygREjC9YQ |
| https://openreview.net/pdf?id=BygREjC9YQ | |
| PWC | https://paperswithcode.com/paper/a-unified-theory-of-adaptive-stochastic-1 |
| Repo | |
| Framework | |
The Meaning of ``Most’’ for Visual Question Answering Models
| Title | The Meaning of ``Most’’ for Visual Question Answering Models | |
| Authors | Alex Kuhnle, er, Ann Copestake |
| Abstract | The correct interpretation of quantifier statements in the context of a visual scene requires non-trivial inference mechanisms. For the example of {``}most{''}, we discuss two strategies which rely on fundamentally different cognitive concepts. Our aim is to identify what strategy deep learning models for visual question answering learn when trained on such questions. To this end, we carefully design data to replicate experiments from psycholinguistics where the same question was investigated for humans. Focusing on the FiLM visual question answering model, our experiments indicate that a form of approximate number system emerges whose performance declines with more difficult scenes as predicted by Weber{'}s law. Moreover, we identify confounding factors, like spatial arrangement of the scene, which impede the effectiveness of this system. | |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4806/ |
| https://www.aclweb.org/anthology/W19-4806 | |
| PWC | https://paperswithcode.com/paper/the-meaning-of-most-for-visual-question-1 |
| Repo | |
| Framework | |
Multi-grained Attention with Object-level Grounding for Visual Question Answering
| Title | Multi-grained Attention with Object-level Grounding for Visual Question Answering |
| Authors | Pingping Huang, Jianhui Huang, Yuqing Guo, Min Qiao, Yong Zhu |
| Abstract | Attention mechanisms are widely used in Visual Question Answering (VQA) to search for visual clues related to the question. Most approaches train attention models from a coarse-grained association between sentences and images, which tends to fail on small objects or uncommon concepts. To address this problem, this paper proposes a multi-grained attention method. It learns explicit word-object correspondence by two types of word-level attention complementary to the sentence-image association. Evaluated on the VQA benchmark, the multi-grained attention model achieves competitive performance with state-of-the-art models. And the visualized attention maps demonstrate that addition of object-level groundings leads to a better understanding of the images and locates the attended objects more precisely. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1349/ |
| https://www.aclweb.org/anthology/P19-1349 | |
| PWC | https://paperswithcode.com/paper/multi-grained-attention-with-object-level |
| Repo | |
| Framework | |
Inferring Reward Functions from Demonstrators with Unknown Biases
| Title | Inferring Reward Functions from Demonstrators with Unknown Biases |
| Authors | Rohin Shah, Noah Gundotra, Pieter Abbeel, Anca Dragan |
| Abstract | Our goal is to infer reward functions from demonstrations. In order to infer the correct reward function, we must account for the systematic ways in which the demonstrator is suboptimal. Prior work in inverse reinforcement learning can account for specific, known biases, but cannot handle demonstrators with unknown biases. In this work, we explore the idea of learning the demonstrator’s planning algorithm (including their unknown biases), along with their reward function. What makes this challenging is that any demonstration could be explained either by positing a term in the reward function, or by positing a particular systematic bias. We explore what assumptions are sufficient for avoiding this impossibility result: either access to tasks with known rewards which enable estimating the planner separately, or that the demonstrator is sufficiently close to optimal that this can serve as a regularizer. In our exploration with synthetic models of human biases, we find that it is possible to adapt to different biases and perform better than assuming a fixed model of the demonstrator, such as Boltzmann rationality. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkgqCiRqKQ |
| https://openreview.net/pdf?id=rkgqCiRqKQ | |
| PWC | https://paperswithcode.com/paper/inferring-reward-functions-from-demonstrators |
| Repo | |
| Framework | |
Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew
| Title | Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew |
| Authors | Amir More, Amit Seker, Victoria Basmova, Reut Tsarfaty |
| Abstract | In standard NLP pipelines, morphological analysis and disambiguation (MA{&}D) precedes syntactic and semantic downstream tasks. However, for languages with complex and ambiguous word-internal structure, known as morphologically rich languages (MRLs), it has been hypothesized that syntactic context may be crucial for accurate MA{&}D, and vice versa. In this work we empirically confirm this hypothesis for Modern Hebrew, an MRL with complex morphology and severe word-level ambiguity, in a novel transition-based framework. Specifically, we propose a joint morphosyntactic transition-based framework which formally unifies two distinct transition systems, morphological and syntactic, into a single transition-based system with joint training and joint inference. We empirically show that MA{&}D results obtained in the joint settings outperform MA{&}D results obtained by the respective standalone components, and that end-to-end parsing results obtained by our joint system present a new state of the art for Hebrew dependency parsing. |
| Tasks | Dependency Parsing, Morphological Analysis |
| Published | 2019-03-01 |
| URL | https://www.aclweb.org/anthology/Q19-1003/ |
| https://www.aclweb.org/anthology/Q19-1003 | |
| PWC | https://paperswithcode.com/paper/joint-transition-based-models-for-morpho |
| Repo | |
| Framework | |
Online Infix Probability Computation for Probabilistic Finite Automata
| Title | Online Infix Probability Computation for Probabilistic Finite Automata |
| Authors | Marco Cognetta, Yo-Sub Han, Soon Chan Kwon |
| Abstract | Probabilistic finite automata (PFAs) are com- mon statistical language model in natural lan- guage and speech processing. A typical task for PFAs is to compute the probability of all strings that match a query pattern. An impor- tant special case of this problem is computing the probability of a string appearing as a pre- fix, suffix, or infix. These problems find use in many natural language processing tasks such word prediction and text error correction. Recently, we gave the first incremental algorithm to efficiently compute the infix probabilities of each prefix of a string (Cognetta et al., 2018). We develop an asymptotic improvement of that algorithm and solve the open problem of computing the infix probabilities of PFAs from streaming data, which is crucial when process- ing queries online and is the ultimate goal of the incremental approach. |
| Tasks | Language Modelling |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1528/ |
| https://www.aclweb.org/anthology/P19-1528 | |
| PWC | https://paperswithcode.com/paper/online-infix-probability-computation-for |
| Repo | |
| Framework | |
Improving Evidence Detection by Leveraging Warrants
| Title | Improving Evidence Detection by Leveraging Warrants |
| Authors | Keshav Singh, Paul Reisert, Naoya Inoue, Pride Kavumba, Kentaro Inui |
| Abstract | Recognizing the implicit link between a claim and a piece of evidence (i.e. warrant) is the key to improving the performance of evidence detection. In this work, we explore the effectiveness of automatically extracted warrants for evidence detection. Given a claim and candidate evidence, our proposed method extracts multiple warrants via similarity search from an existing, structured corpus of arguments. We then attentively aggregate the extracted warrants, considering the consistency between the given argument and the acquired warrants. Although a qualitative analysis on the warrants shows that the extraction method needs to be improved, our results indicate that our method can still improve the performance of evidence detection. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6610/ |
| https://www.aclweb.org/anthology/D19-6610 | |
| PWC | https://paperswithcode.com/paper/improving-evidence-detection-by-leveraging |
| Repo | |
| Framework | |
Understanding Opportunities for Efficiency in Single-image Super Resolution Networks
| Title | Understanding Opportunities for Efficiency in Single-image Super Resolution Networks |
| Authors | Royson Lee, Nic Lane, Marko Stankovic, Sourav Bhattacharya |
| Abstract | A successful application of convolutional architectures is to increase the resolution of single low-resolution images – a image restoration task called super-resolution (SR). Naturally, SR is of value to resource constrained devices like mobile phones, electronic photograph frames and televisions to enhance image quality. However, SR demands perhaps the most extreme amounts of memory and compute operations of any mainstream vision task known today, preventing SR from being deployed to devices that require them. In this paper, we perform a early systematic study of system resource efficiency for SR, within the context of a variety of architectural and low-precision approaches originally developed for discriminative neural networks. We present a rich set of insights, representative SR architectures, and efficiency trade-offs; for example, the prioritization of ways to compress models to reach a specific memory and computation target and techniques to compact SR models so that they are suitable for DSPs and FPGAs. As a result of doing so, we manage to achieve better and comparable performance with previous models in the existing literature, highlighting the practicality of using existing efficiency techniques in SR tasks. Collectively, we believe these results provides the foundation for further research into the little explored area of resource efficiency for SR. |
| Tasks | Image Restoration, Image Super-Resolution, Super-Resolution |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BkgGmh09FQ |
| https://openreview.net/pdf?id=BkgGmh09FQ | |
| PWC | https://paperswithcode.com/paper/understanding-opportunities-for-efficiency-in |
| Repo | |
| Framework | |
From Brain Space to Distributional Space: The Perilous Journeys of fMRI Decoding
| Title | From Brain Space to Distributional Space: The Perilous Journeys of fMRI Decoding |
| Authors | Gosse Minnema, Aur{'e}lie Herbelot |
| Abstract | Recent work in cognitive neuroscience has introduced models for predicting distributional word meaning representations from brain imaging data. Such models have great potential, but the quality of their predictions has not yet been thoroughly evaluated from a computational linguistics point of view. Due to the limited size of available brain imaging datasets, standard quality metrics (e.g. similarity judgments and analogies) cannot be used. Instead, we investigate the use of several alternative measures for evaluating the predicted distributional space against a corpus-derived distributional space. We show that a state-of-the-art decoder, while performing impressively on metrics that are commonly used in cognitive neuroscience, performs unexpectedly poorly on our metrics. To address this, we propose strategies for improving the model{'}s performance. Despite returning promising results, our experiments also demonstrate that much work remains to be done before distributional representations can reliably be predicted from brain data. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2021/ |
| https://www.aclweb.org/anthology/P19-2021 | |
| PWC | https://paperswithcode.com/paper/from-brain-space-to-distributional-space-the |
| Repo | |
| Framework | |
Proceedings of the Workshop on NLP and Pseudonymisation
| Title | Proceedings of the Workshop on NLP and Pseudonymisation |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6500/ |
| https://www.aclweb.org/anthology/W19-6500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-nlp-and |
| Repo | |
| Framework | |
Anomaly Detection in Video Sequence With Appearance-Motion Correspondence
| Title | Anomaly Detection in Video Sequence With Appearance-Motion Correspondence |
| Authors | Trong-Nguyen Nguyen, Jean Meunier |
| Abstract | Anomaly detection in surveillance videos is currently a challenge because of the diversity of possible events. We propose a deep convolutional neural network (CNN) that addresses this problem by learning a correspondence between common object appearances (e.g. pedestrian, background, tree, etc.) and their associated motions. Our model is designed as a combination of a reconstruction network and an image translation model that share the same encoder. The former sub-network determines the most significant structures that appear in video frames and the latter one attempts to associate motion templates to such structures. The training stage is performed using only videos of normal events and the model is then capable to estimate frame-level scores for an unknown input. The experiments on 6 benchmark datasets demonstrate the competitive performance of the proposed approach with respect to state-of-the-art methods. |
| Tasks | Anomaly Detection, Anomaly Detection In Surveillance Videos |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Nguyen_Anomaly_Detection_in_Video_Sequence_With_Appearance-Motion_Correspondence_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Nguyen_Anomaly_Detection_in_Video_Sequence_With_Appearance-Motion_Correspondence_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-video-sequence-with-1 |
| Repo | |
| Framework | |
