Paper Group NANR 170
Explicitly modeling case improves neural dependency parsing. Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis. Listening Comprehension over Argumentative Content. Binarized LSTM Language Model. Dynamic Feature Learning for Partial Face Recognition. INTERPRETATION OF NEURAL NETWORK I …
Explicitly modeling case improves neural dependency parsing
| Title | Explicitly modeling case improves neural dependency parsing |
| Authors | Clara Vania, Adam Lopez |
| Abstract | Neural dependency parsing models that compose word representations from characters can presumably exploit morphosyntax when making attachment decisions. How much do they know about morphology? We investigate how well they handle morphological case, which is important for parsing. Our experiments on Czech, German and Russian suggest that adding explicit morphological case{—}either oracle or predicted{—}improves neural dependency parsing, indicating that the learned representations in these models do not fully encode the morphological knowledge that they need, and can still benefit from targeted forms of explicit linguistic modeling. |
| Tasks | Dependency Parsing, Multi-Task Learning |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5447/ |
| https://www.aclweb.org/anthology/W18-5447 | |
| PWC | https://paperswithcode.com/paper/explicitly-modeling-case-improves-neural |
| Repo | |
| Framework | |
Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis
| Title | Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis |
| Authors | Kelly Zhang, Samuel Bowman |
| Abstract | Recently, researchers have found that deep LSTMs trained on tasks like machine translation learn substantial syntactic and semantic information about their input sentences, including part-of-speech. These findings begin to shed light on why pretrained representations, like ELMo and CoVe, are so beneficial for neural language understanding models. We still, though, do not yet have a clear understanding of how the choice of pretraining objective affects the type of linguistic information that models learn. With this in mind, we compare four objectives{—}language modeling, translation, skip-thought, and autoencoding{—}on their ability to induce syntactic and part-of-speech information, holding constant the quantity and genre of the training data, as well as the LSTM architecture. |
| Tasks | CCG Supertagging, Language Modelling, Machine Translation, Part-Of-Speech Tagging, Transfer Learning |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5448/ |
| https://www.aclweb.org/anthology/W18-5448 | |
| PWC | https://paperswithcode.com/paper/language-modeling-teaches-you-more-than |
| Repo | |
| Framework | |
Listening Comprehension over Argumentative Content
| Title | Listening Comprehension over Argumentative Content |
| Authors | Shachar Mirkin, Guy Moshkowich, Matan Orbach, Lili Kotlerman, Yoav Kantor, Tamar Lavee, Michal Jacovi, Yonatan Bilu, Ranit Aharonov, Noam Slonim |
| Abstract | This paper presents a task for machine listening comprehension in the argumentation domain and a corresponding dataset in English. We recorded 200 spontaneous speeches arguing for or against 50 controversial topics. For each speech, we formulated a question, aimed at confirming or rejecting the occurrence of potential arguments in the speech. Labels were collected by listening to the speech and marking which arguments were mentioned by the speaker. We applied baseline methods addressing the task, to be used as a benchmark for future work over this dataset. All data used in this work is freely available for research. |
| Tasks | Machine Reading Comprehension, Question Answering, Reading Comprehension, Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1078/ |
| https://www.aclweb.org/anthology/D18-1078 | |
| PWC | https://paperswithcode.com/paper/listening-comprehension-over-argumentative |
| Repo | |
| Framework | |
Binarized LSTM Language Model
| Title | Binarized LSTM Language Model |
| Authors | Xuan Liu, Di Cao, Kai Yu |
| Abstract | Long short-term memory (LSTM) language model (LM) has been widely investigated for automatic speech recognition (ASR) and natural language processing (NLP). Although excellent performance is obtained for large vocabulary tasks, tremendous memory consumption prohibits the use of LSTM LM in low-resource devices. The memory consumption mainly comes from the word embedding layer. In this paper, a novel binarized LSTM LM is proposed to address the problem. Words are encoded into binary vectors and other LSTM parameters are further binarized to achieve high memory compression. This is the first effort to investigate binary LSTM for large vocabulary LM. Experiments on both English and Chinese LM and ASR tasks showed that can achieve a compression ratio of 11.3 without any loss of LM and ASR performances and a compression ratio of 31.6 with acceptable minor performance degradation. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1192/ |
| https://www.aclweb.org/anthology/N18-1192 | |
| PWC | https://paperswithcode.com/paper/binarized-lstm-language-model |
| Repo | |
| Framework | |
Dynamic Feature Learning for Partial Face Recognition
| Title | Dynamic Feature Learning for Partial Face Recognition |
| Authors | Lingxiao He, Haiqing Li, Qi Zhang, Zhenan Sun |
| Abstract | Partial face recognition (PFR) in unconstrained environment is a very important task, especially in video surveillance, mobile devices, etc. However, a few studies have tackled how to recognize an arbitrary patch of a face image. This study combines Fully Convolutional Network (FCN) with Sparse Representation Classification (SRC) to propose a novel partial face recognition approach, called Dynamic Feature Matching (DFM), to address partial face images regardless of sizes. Based on DFM, we propose a sliding loss to optimize FCN by reducing the intra-variation between a face patch and face images of a subject, which further improves the performance of DFM. The proposed DFM is evaluated on several partial face databases, including LFW, YTF and CASIA-NIR-Distance databases. Experimental results demonstrate the effectiveness and advantages of DFM in comparison with state-of-the-art PFR methods. |
| Tasks | Face Recognition |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/He_Dynamic_Feature_Learning_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/He_Dynamic_Feature_Learning_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-feature-learning-for-partial-face |
| Repo | |
| Framework | |
INTERPRETATION OF NEURAL NETWORK IS FRAGILE
| Title | INTERPRETATION OF NEURAL NETWORK IS FRAGILE |
| Authors | Amirata Ghorbani, Abubakar Abid, James Zou |
| Abstract | In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predictions. For example, if an algorithm classifies a given pathology image to be a malignant tumor, then the doctor may need to know which parts of the image led the algorithm to this classification. How to interpret black-box predictors is thus an important and active area of research. A fundamental question is: how much can we trust the interpretation itself? In this paper, we show that interpretation of deep learning predictions is extremely fragile in the following sense: two perceptively indistinguishable inputs with the same predicted label can be assigned very different}interpretations. We systematically characterize the fragility of the interpretations generated by several widely-used feature-importance interpretation methods (saliency maps, integrated gradient, and DeepLIFT) on ImageNet and CIFAR-10. Our experiments show that even small random perturbation can change the feature importance and new systematic perturbations can lead to dramatically different interpretations without changing the label. We extend these results to show that interpretations based on exemplars (e.g. influence functions) are similarly fragile. Our analysis of the geometry of the Hessian matrix gives insight on why fragility could be a fundamental challenge to the current interpretation approaches. |
| Tasks | Feature Importance |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=H1xJjlbAZ |
| https://openreview.net/pdf?id=H1xJjlbAZ | |
| PWC | https://paperswithcode.com/paper/interpretation-of-neural-network-is-fragile |
| Repo | |
| Framework | |
Inferring Shared Attention in Social Scene Videos
| Title | Inferring Shared Attention in Social Scene Videos |
| Authors | Lifeng Fan, Yixin Chen, Ping Wei, Wenguan Wang, Song-Chun Zhu |
| Abstract | This paper addresses a new problem of inferring shared attention in third-person social scene videos. Shared attention is a phenomenon that two or more individuals simultaneously look at a common target in social scenes. Perceiving and identifying shared attention in videos plays crucial roles in social activities and social scene understanding. We propose a spatial-temporal neural network to detect shared attention intervals in videos and predict shared attention locations in frames. In each video frame, human gaze directions and potential target boxes are two key features for spatially detecting shared attention in the social scene. In temporal domain, a convolutional Long Short- Term Memory network utilizes the temporal continuity and transition constraints to optimize the predicted shared attention heatmap. We collect a new dataset VideoCoAtt from public TV show videos, containing 380 complex video sequences with more than 492,000 frames that include diverse social scenes for shared attention study. Experiments on this dataset show that our model can effectively infer shared attention in videos. We also empirically verify the effectiveness of different components in our model. |
| Tasks | Scene Understanding |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Fan_Inferring_Shared_Attention_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Fan_Inferring_Shared_Attention_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-shared-attention-in-social-scene |
| Repo | |
| Framework | |
Proceedings of the First International Workshop on Spatial Language Understanding
| Title | Proceedings of the First International Workshop on Spatial Language Understanding |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1400/ |
| https://www.aclweb.org/anthology/W18-1400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-international-2 |
| Repo | |
| Framework | |
Knowledge Graph Embedding with Hierarchical Relation Structure
| Title | Knowledge Graph Embedding with Hierarchical Relation Structure |
| Authors | Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He |
| Abstract | The rapid development of knowledge graphs (KGs), such as Freebase and WordNet, has changed the paradigm for AI-related applications. However, even though these KGs are impressively large, most of them are suffering from incompleteness, which leads to performance degradation of AI applications. Most existing researches are focusing on knowledge graph embedding (KGE) models. Nevertheless, those models simply embed entities and relations into latent vectors without leveraging the rich information from the relation structure. Indeed, relations in KGs conform to a three-layer hierarchical relation structure (HRS), i.e., semantically similar relations can make up relation clusters and some relations can be further split into several fine-grained sub-relations. Relation clusters, relations and sub-relations can fit in the top, the middle and the bottom layer of three-layer HRS respectively. To this end, in this paper, we extend existing KGE models TransE, TransH and DistMult, to learn knowledge representations by leveraging the information from the HRS. Particularly, our approach is capable to extend other KGE models. Finally, the experiment results clearly validate the effectiveness of the proposed approach against baselines. |
| Tasks | Graph Embedding, Information Retrieval, Knowledge Base Completion, Knowledge Graph Embedding, Knowledge Graphs, Question Answering |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1358/ |
| https://www.aclweb.org/anthology/D18-1358 | |
| PWC | https://paperswithcode.com/paper/knowledge-graph-embedding-with-hierarchical |
| Repo | |
| Framework | |
WildDash - Creating Hazard-Aware Benchmarks
| Title | WildDash - Creating Hazard-Aware Benchmarks |
| Authors | Oliver Zendel, Katrin Honauer, Markus Murschitz, Daniel Steininger, Gustavo Fernandez Dominguez |
| Abstract | Test datasets should contain many different challenging aspects so that the robustness and real-world applicability of algorithms can be assessed. In this work, we present a new test dataset for semantic and instance segmentation for the automotive domain. We have conducted a thorough risk analysis to identify situations and aspects that can reduce the output performance for these tasks. Based on this analysis we have designed our new dataset. Meta-information is supplied to mark which individual visual hazards are present in each test case. Furthermore, a new benchmark evaluation method is presented that uses the meta-information to calculate the robustness of a given algorithm with respect to the individual hazards. We show how this new approach allows for a more expressive characterization of algorithm robustness by comparing three baseline algorithms. |
| Tasks | Instance Segmentation, Semantic Segmentation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Oliver_Zendel_WildDash_-_Creating_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Oliver_Zendel_WildDash_-_Creating_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/wilddash-creating-hazard-aware-benchmarks |
| Repo | |
| Framework | |
Simplified Corpus with Core Vocabulary
| Title | Simplified Corpus with Core Vocabulary |
| Authors | Takumi Maruyama, Kazuhide Yamamoto |
| Abstract | |
| Tasks | Text Simplification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1185/ |
| https://www.aclweb.org/anthology/L18-1185 | |
| PWC | https://paperswithcode.com/paper/simplified-corpus-with-core-vocabulary |
| Repo | |
| Framework | |
Annotating Modality Expressions and Event Factuality for a Japanese Chess Commentary Corpus
| Title | Annotating Modality Expressions and Event Factuality for a Japanese Chess Commentary Corpus |
| Authors | Suguru Matsuyoshi, Hirotaka Kameko, Yugo Murawaki, Shinsuke Mori |
| Abstract | |
| Tasks | Image Captioning, Text Generation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1393/ |
| https://www.aclweb.org/anthology/L18-1393 | |
| PWC | https://paperswithcode.com/paper/annotating-modality-expressions-and-event |
| Repo | |
| Framework | |
Fighting Boredom in Recommender Systems with Linear Reinforcement Learning
| Title | Fighting Boredom in Recommender Systems with Linear Reinforcement Learning |
| Authors | Romain Warlop, Alessandro Lazaric, Jérémie Mary |
| Abstract | A common assumption in recommender systems (RS) is the existence of a best fixed recommendation strategy. Such strategy may be simple and work at the item level (e.g., in multi-armed bandit it is assumed one best fixed arm/item exists) or implement more sophisticated RS (e.g., the objective of A/B testing is to find the best fixed RS and execute it thereafter). We argue that this assumption is rarely verified in practice, as the recommendation process itself may impact the user’s preferences. For instance, a user may get bored by a strategy, while she may gain interest again, if enough time passed since the last time that strategy was used. In this case, a better approach consists in alternating different solutions at the right frequency to fully exploit their potential. In this paper, we first cast the problem as a Markov decision process, where the rewards are a linear function of the recent history of actions, and we show that a policy considering the long-term influence of the recommendations may outperform both fixed-action and contextual greedy policies. We then introduce an extension of the UCRL algorithm ( L IN UCRL ) to effectively balance exploration and exploitation in an unknown environment, and we derive a regret bound that is independent of the number of states. Finally, we empirically validate the model assumptions and the algorithm in a number of realistic scenarios. |
| Tasks | Recommendation Systems |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7447-fighting-boredom-in-recommender-systems-with-linear-reinforcement-learning |
| http://papers.nips.cc/paper/7447-fighting-boredom-in-recommender-systems-with-linear-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/fighting-boredom-in-recommender-systems-with |
| Repo | |
| Framework | |
Automatic 3D Indoor Scene Modeling From Single Panorama
| Title | Automatic 3D Indoor Scene Modeling From Single Panorama |
| Authors | Yang Yang, Shi Jin, Ruiyang Liu, Sing Bing Kang, Jingyi Yu |
| Abstract | We describe a system that automatically extracts 3D geometry of an indoor scene from a single 2D panorama. Our system recovers the spatial layout by finding the floor, walls, and ceiling; it also recovers shapes of typical indoor objects such as furniture. Using sampled perspective sub-views, we extract geometric cues (lines, vanishing points, orientation map, and surface normals) and semantic cues (saliency and object detection information). These cues are used for ground plane estimation and occlusion reasoning. The global spatial layout is inferred through a constraint graph on line segments and planar superpixels. The recovered layout is then used to guide shape estimation of the remaining objects using their normal information. Experiments on synthetic and real datasets show that our approach is state-of-the-art in both accuracy and efficiency. Our system can handle cluttered scenes with complex geometry that are challenging to existing techniques. |
| Tasks | Object Detection |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Yang_Automatic_3D_Indoor_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_Automatic_3D_Indoor_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-3d-indoor-scene-modeling-from |
| Repo | |
| Framework | |
Multimodal Named Entity Disambiguation for Noisy Social Media Posts
| Title | Multimodal Named Entity Disambiguation for Noisy Social Media Posts |
| Authors | Seungwhan Moon, Leonardo Neves, Vitor Carvalho |
| Abstract | We introduce the new Multimodal Named Entity Disambiguation (MNED) task for multimodal social media posts such as Snapchat or Instagram captions, which are composed of short captions with accompanying images. Social media posts bring significant challenges for disambiguation tasks because 1) ambiguity not only comes from polysemous entities, but also from inconsistent or incomplete notations, 2) very limited context is provided with surrounding words, and 3) there are many emerging entities often unseen during training. To this end, we build a new dataset called SnapCaptionsKB, a collection of Snapchat image captions submitted to public and crowd-sourced stories, with named entity mentions fully annotated and linked to entities in an external knowledge base. We then build a deep zeroshot multimodal network for MNED that 1) extracts contexts from both text and image, and 2) predicts correct entity in the knowledge graph embeddings space, allowing for zeroshot disambiguation of entities unseen in training set as well. The proposed model significantly outperforms the state-of-the-art text-only NED models, showing efficacy and potentials of the MNED task. |
| Tasks | Entity Disambiguation, Image Captioning, Knowledge Graph Embeddings, Opinion Mining |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1186/ |
| https://www.aclweb.org/anthology/P18-1186 | |
| PWC | https://paperswithcode.com/paper/multimodal-named-entity-disambiguation-for |
| Repo | |
| Framework | |
