Paper Group NANR 63
Character Identification Refined: A Proposal. Skeleton-Aware 3D Human Shape Reconstruction From Point Clouds. Encoding Category Trees Into Word-Embeddings Using Geometric Approach. Dynamics Are Important for the Recognition of Equine Pain in Video. Learning to Augment Influential Data. Deep Learning for Light Field Saliency Detection. Are Fictional …
Character Identification Refined: A Proposal
| Title | Character Identification Refined: A Proposal |
| Authors | Labiba Jahan, Mark Finlayson |
| Abstract | Characters are a key element of narrative and so character identification plays an important role in automatic narrative understanding. Unfortunately, most prior work that incorporates character identification is not built upon a clear, theoretically grounded concept of character. They either take character identification for granted (e.g., using simple heuristics on referring expressions), or rely on simplified definitions that do not capture important distinctions between characters and other referents in the story. Prior approaches have also been rather complicated, relying, for example, on predefined case bases or ontologies. In this paper we propose a narratologically grounded definition of character for discussion at the workshop, and also demonstrate a preliminary yet straightforward supervised machine learning model with a small set of features that performs well on two corpora. The most important of the two corpora is a set of 46 Russian folktales, on which the model achieves an F1 of 0.81. Error analysis suggests that features relevant to the plot will be necessary for further improvements in performance. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2402/ |
| https://www.aclweb.org/anthology/W19-2402 | |
| PWC | https://paperswithcode.com/paper/character-identification-refined-a-proposal |
| Repo | |
| Framework | |
Skeleton-Aware 3D Human Shape Reconstruction From Point Clouds
| Title | Skeleton-Aware 3D Human Shape Reconstruction From Point Clouds |
| Authors | Haiyong Jiang, Jianfei Cai, Jianmin Zheng |
| Abstract | This work addresses the problem of 3D human shape reconstruction from point clouds. Considering that human shapes are of high dimensions and with large articulations, we adopt the state-of-the-art parametric human body model, SMPL, to reduce the dimension of learning space and generate smooth and valid reconstruction. However, SMPL parameters, especially pose parameters, are not easy to learn because of ambiguity and locality of the pose representation. Thus, we propose to incorporate skeleton awareness into the deep learning based regression of SMPL parameters for 3D human shape reconstruction. Our basic idea is to use the state-of-the-art technique PointNet++ to extract point features, and then map point features to skeleton joint features and finally to SMPL parameters for the reconstruction from point clouds. Particularly, we develop an end-to-end framework, where we propose a graph aggregation module to augment PointNet++ by extracting better point features, an attention module to better map unordered point features into ordered skeleton joint features, and a skeleton graph module to extract better joint features for SMPL parameter regression. The entire framework network is first trained in an end-to-end manner on synthesized dataset, and then online fine-tuned on unseen dataset with unsupervised loss to bridges gaps between training and testing. The experiments on multiple datasets show that our method is on par with the state-of-the-art solution. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Jiang_Skeleton-Aware_3D_Human_Shape_Reconstruction_From_Point_Clouds_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Jiang_Skeleton-Aware_3D_Human_Shape_Reconstruction_From_Point_Clouds_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/skeleton-aware-3d-human-shape-reconstruction |
| Repo | |
| Framework | |
Encoding Category Trees Into Word-Embeddings Using Geometric Approach
| Title | Encoding Category Trees Into Word-Embeddings Using Geometric Approach |
| Authors | Tiansi Dong, Olaf Cremers, Hailong Jin, Juanzi Li, Chrisitan Bauckhage, Armin B. Cremers, Daniel Speicher, Joerg Zimmermann |
| Abstract | We present a novel method to implicitly encode a tree-structured category information into word-embeddings, resulting in super-dimensional ball representations ($n$-ball embedding for short). Inclusion relations among $n$-balls precisely encode subordinate relations among categories. The cosine similarity function is enriched by category information. A large $n$-ball dataset is constructed using geometrical method, which achieves zero energy cost in embedding tree structures into word embedding. A new benchmark dataset is created for predicting the category of unknown words. Experiments show that $n$-ball embeddings, carried with category information, significantly out-perform word-embeddings in the neighbourhood test, while only slightly change the original word-embeddings. Experiment results also show that $n$-ball embeddings demonstrate surprisingly good performance in validating the category of unknown word. Source codes and data-sets are free for public access \url{https://github.com/gnodisnait/nball4tree.git} and \url{https://github.com/gnodisnait/bp94nball.git}. |
| Tasks | Word Embeddings |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJlWOj0qF7 |
| https://openreview.net/pdf?id=rJlWOj0qF7 | |
| PWC | https://paperswithcode.com/paper/encoding-category-trees-into-word-embeddings |
| Repo | |
| Framework | |
Dynamics Are Important for the Recognition of Equine Pain in Video
| Title | Dynamics Are Important for the Recognition of Equine Pain in Video |
| Authors | Sofia Broome, Karina Bech Gleerup, Pia Haubro Andersen, Hedvig Kjellstrom |
| Abstract | A prerequisite to successfully alleviate pain in animals is to recognize it, which is a great challenge in non-verbal species. Furthermore, prey animals such as horses tend to hide their pain. In this study, we propose a deep recurrent two-stream architecture for the task of distinguishing pain from non-pain in videos of horses. Different models are evaluated on a unique dataset showing horses under controlled trials with moderate pain induction, which has been presented in earlier work. Sequential models are experimentally compared to single-frame models, showing the importance of the temporal dimension of the data, and are benchmarked against a veterinary expert classification of the data. We additionally perform baseline comparisons with generalized versions of state-of-the-art human pain recognition methods. While equine pain detection in machine learning is a novel field, our results surpass veterinary expert performance and outperform pain detection results reported for other larger non-human species. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Broome_Dynamics_Are_Important_for_the_Recognition_of_Equine_Pain_in_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Broome_Dynamics_Are_Important_for_the_Recognition_of_Equine_Pain_in_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dynamics-are-important-for-the-recognition-of-1 |
| Repo | |
| Framework | |
Learning to Augment Influential Data
| Title | Learning to Augment Influential Data |
| Authors | Donghoon Lee, Chang D. Yoo |
| Abstract | Data augmentation is a technique to reduce overfitting and to improve generalization by increasing the number of labeled data samples by performing label preserving transformations; however, it is currently conducted in a trial and error manner. A composition of predefined transformations, such as rotation, scaling and cropping, is performed on training samples, and its effect on performance over test samples can only be empirically evaluated and cannot be predicted. This paper considers an influence function which predicts how generalization is affected by a particular augmented training sample in terms of validation loss. The influence function provides an approximation of the change in validation loss without comparing the performance which includes and excludes the sample in the training process. A differentiable augmentation model that generalizes the conventional composition of predefined transformations is also proposed. The differentiable augmentation model and reformulation of the influence function allow the parameters of the augmented model to be directly updated by backpropagation to minimize the validation loss. The experimental results show that the proposed method provides better generalization over conventional data augmentation methods. |
| Tasks | Data Augmentation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BygIV2CcKm |
| https://openreview.net/pdf?id=BygIV2CcKm | |
| PWC | https://paperswithcode.com/paper/learning-to-augment-influential-data |
| Repo | |
| Framework | |
Deep Learning for Light Field Saliency Detection
| Title | Deep Learning for Light Field Saliency Detection |
| Authors | Tiantian Wang, Yongri Piao, Xiao Li, Lihe Zhang, Huchuan Lu |
| Abstract | Recent research in 4D saliency detection is limited by the deficiency of a large-scale 4D light field dataset. To address this, we introduce a new dataset to assist the subsequent research in 4D light field saliency detection. To the best of our knowledge, this is to date the largest light field dataset in which the dataset provides 1465 all-focus images with human-labeled ground truth masks and the corresponding focal stacks for every light field image. To verify the effectiveness of the light field data, we first introduce a fusion framework which includes two CNN streams where the focal stacks and all-focus images serve as the input. The focal stack stream utilizes a recurrent attention mechanism to adaptively learn to integrate every slice in the focal stack, which benefits from the extracted features of the good slices. Then it is incorporated with the output map generated by the all-focus stream to make the saliency prediction. In addition, we introduce adversarial examples by adding noise intentionally into images to help train the deep network, which can improve the robustness of the proposed network. The noise is designed by users, which is imperceptible but can fool the CNNs to make the wrong prediction. Extensive experiments show the effectiveness and superiority of the proposed model on the popular evaluation metrics. The proposed method performs favorably compared with the existing 2D, 3D and 4D saliency detection methods on the proposed dataset and existing LFSD light field dataset. The code and results can be found at https://github.com/OIPLab-DUT/ ICCV2019_Deeplightfield_Saliency. Moreover, to facilitate research in this field, all images we collected are shared in a ready-to-use manner. |
| Tasks | Saliency Detection, Saliency Prediction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Deep_Learning_for_Light_Field_Saliency_Detection_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Deep_Learning_for_Light_Field_Saliency_Detection_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-light-field-saliency |
| Repo | |
| Framework | |
Are Fictional Voices Distinguishable? Classifying Character Voices in Modern Drama
| Title | Are Fictional Voices Distinguishable? Classifying Character Voices in Modern Drama |
| Authors | Krishnapriya Vishnubhotla, Adam Hammond, Graeme Hirst |
| Abstract | According to the literary theory of Mikhail Bakhtin, a dialogic novel is one in which characters speak in their own distinct voices, rather than serving as mouthpieces for their authors. We use text classification to determine which authors best achieve dialogism, looking at a corpus of plays from the late nineteenth and early twentieth centuries. We find that the SAGE model of text generation, which highlights deviations from a background lexical distribution, is an effective method of weighting the words of characters{'} utterances. Our results show that it is indeed possible to distinguish characters by their speech in the plays of canonical writers such as George Bernard Shaw, whereas characters are clustered more closely in the works of lesser-known playwrights. |
| Tasks | Text Classification, Text Generation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2504/ |
| https://www.aclweb.org/anthology/W19-2504 | |
| PWC | https://paperswithcode.com/paper/are-fictional-voices-distinguishable |
| Repo | |
| Framework | |
Stylometric Classification of Ancient Greek Literary Texts by Genre
| Title | Stylometric Classification of Ancient Greek Literary Texts by Genre |
| Authors | Efthimios Gianitsos, Thomas Bolt, Pramit Chaudhuri, Joseph Dexter |
| Abstract | Classification of texts by genre is an important application of natural language processing to literary corpora but remains understudied for premodern and non-English traditions. We develop a stylometric feature set for ancient Greek that enables identification of texts as prose or verse. The set contains over 20 primarily syntactic features, which are calculated according to custom, language-specific heuristics. Using these features, we classify almost all surviving classical Greek literature as prose or verse with {\textgreater}97{%} accuracy and F1 score, and further classify a selection of the verse texts into the traditional genres of epic and drama. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2507/ |
| https://www.aclweb.org/anthology/W19-2507 | |
| PWC | https://paperswithcode.com/paper/stylometric-classification-of-ancient-greek |
| Repo | |
| Framework | |
Modeling Affirmative and Negated Action Processing in the Brain with Lexical and Compositional Semantic Models
| Title | Modeling Affirmative and Negated Action Processing in the Brain with Lexical and Compositional Semantic Models |
| Authors | Vesna Djokic, Jean Maillard, Luana Bulat, Ekaterina Shutova |
| Abstract | Recent work shows that distributional semantic models can be used to decode patterns of brain activity associated with individual words and sentence meanings. However, it is yet unclear to what extent such models can be used to study and decode fMRI patterns associated with specific aspects of semantic composition such as the negation function. In this paper, we apply lexical and compositional semantic models to decode fMRI patterns associated with negated and affirmative sentences containing hand-action verbs. Our results show reduced decoding (correlation) of sentences where the verb is in the negated context, as compared to the affirmative one, within brain regions implicated in action-semantic processing. This supports behavioral and brain imaging studies, suggesting that negation involves reduced access to aspects of the affirmative mental representation. The results pave the way for testing alternate semantic models of negation against human semantic processing in the brain. |
| Tasks | Semantic Composition |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1508/ |
| https://www.aclweb.org/anthology/P19-1508 | |
| PWC | https://paperswithcode.com/paper/modeling-affirmative-and-negated-action |
| Repo | |
| Framework | |
Combining Lexical Substitutes in Neural Word Sense Induction
| Title | Combining Lexical Substitutes in Neural Word Sense Induction |
| Authors | Nikolay Arefyev, Boris Sheludko, Alex Panchenko, er |
| Abstract | Word Sense Induction (WSI) is the task of grouping of occurrences of an ambiguous word according to their meaning. In this work, we improve the approach to WSI proposed by Amrami and Goldberg (2018) based on clustering of lexical substitutes for an ambiguous word in a particular context obtained from neural language models. Namely, we propose methods for combining information from left and right context and similarity to the ambiguous word, which result in generating more accurate substitutes than the original approach. Our simple yet efficient improvement establishes a new state-of-the-art on WSI datasets for two languages. Besides, we show improvements to the original approach on a lexical substitution dataset. |
| Tasks | Word Sense Induction |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1008/ |
| https://www.aclweb.org/anthology/R19-1008 | |
| PWC | https://paperswithcode.com/paper/combining-lexical-substitutes-in-neural-word |
| Repo | |
| Framework | |
Visual Imitation with a Minimal Adversary
| Title | Visual Imitation with a Minimal Adversary |
| Authors | Scott Reed, Yusuf Aytar, Ziyu Wang, Tom Paine, Aäron van den Oord, Tobias Pfaff, Sergio Gomez, Alexander Novikov, David Budden, Oriol Vinyals |
| Abstract | High-dimensional sparse reward tasks present major challenges for reinforcement learning agents. In this work we use imitation learning to address two of these challenges: how to learn a useful representation of the world e.g. from pixels, and how to explore efficiently given the rarity of a reward signal? We show that adversarial imitation can work well even in this high dimensional observation space. Surprisingly the adversary itself, acting as the learned reward function, can be tiny, comprising as few as 128 parameters, and can be easily trained using the most basic GAN formulation. Our approach removes limitations present in most contemporary imitation approaches: requiring no demonstrator actions (only video), no special initial conditions or warm starts, and no explicit tracking of any single demo. The proposed agent can solve a challenging robot manipulation task of block stacking from only video demonstrations and sparse reward, in which the non-imitating agents fail to learn completely. Furthermore, our agent learns much faster than competing approaches that depend on hand-crafted, staged dense reward functions, and also better compared to standard GAIL baselines. Finally, we develop a new adversarial goal recognizer that in some cases allows the agent to learn stacking without any task reward, purely from imitation. |
| Tasks | Imitation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rygVV205KQ |
| https://openreview.net/pdf?id=rygVV205KQ | |
| PWC | https://paperswithcode.com/paper/visual-imitation-with-a-minimal-adversary |
| Repo | |
| Framework | |
Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods
| Title | Understanding the Polarity of Events in the Biomedical Literature: Deep Learning vs. Linguistically-informed Methods |
| Authors | Enrique Noriega-Atala, Zhengzhong Liang, John Bachman, Clayton Morrison, Mihai Surdeanu |
| Abstract | An important task in the machine reading of biochemical events expressed in biomedical texts is correctly reading the polarity, i.e., attributing whether the biochemical event is a promotion or an inhibition. Here we present a novel dataset for studying polarity attribution accuracy. We use this dataset to train and evaluate several deep learning models for polarity identification, and compare these to a linguistically-informed model. The best performing deep learning architecture achieves 0.968 average F1 performance in a five-fold cross-validation study, a considerable improvement over the linguistically informed model average F1 of 0.862. |
| Tasks | Reading Comprehension |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2603/ |
| https://www.aclweb.org/anthology/W19-2603 | |
| PWC | https://paperswithcode.com/paper/understanding-the-polarity-of-events-in-the |
| Repo | |
| Framework | |
The Option Keyboard: Combining Skills in Reinforcement Learning
| Title | The Option Keyboard: Combining Skills in Reinforcement Learning |
| Authors | Andre Barreto, Diana Borsa, Shaobo Hou, Gheorghe Comanici, Eser Aygün, Philippe Hamel, Daniel Toyama, Jonathan Hunt, Shibl Mourad, David Silver, Doina Precup |
| Abstract | The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a robust way of combining skills is to define and manipulate them in the space of pseudo-rewards (or “cumulants”). Based on this premise, we propose a framework for combining skills using the formalism of options. We show that every deterministic option can be unambiguously represented as a cumulant defined in an extended domain. Building on this insight and on previous results on transfer learning, we show how to approximate options whose cumulants are linear combinations of the cumulants of known options. This means that, once we have learned options associated with a set of cumulants, we can instantaneously synthesise options induced by any linear combination of them, without any learning involved. We describe how this framework provides a hierarchical interface to the environment whose abstract actions correspond to combinations of basic skills. We demonstrate the practical benefits of our approach in a resource management problem and a navigation task involving a quadrupedal simulated robot. |
| Tasks | Transfer Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9463-the-option-keyboard-combining-skills-in-reinforcement-learning |
| http://papers.nips.cc/paper/9463-the-option-keyboard-combining-skills-in-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/the-option-keyboard-combining-skills-in |
| Repo | |
| Framework | |
An Analysis of Deep Contextual Word Embeddings and Neural Architectures for Toponym Mention Detection in Scientific Publications
| Title | An Analysis of Deep Contextual Word Embeddings and Neural Architectures for Toponym Mention Detection in Scientific Publications |
| Authors | Matthew Magnusson, Laura Dietz |
| Abstract | Toponym detection in scientific papers is an open task and a key first step in place entity enrichment of documents. We examine three common neural architectures in NLP: 1) convolutional neural network, 2) multi-layer perceptron (both applied in a sliding window context) and 3) bidirectional LSTM and apply contextual and non-contextual word embedding layers to these models. We find that deep contextual word embeddings improve the performance of the bi-LSTM with CRF neural architecture achieving the best performance when multiple layers of deep contextual embeddings are concatenated. Our best performing model achieves an average F1 of 0.910 when evaluated on overlap macro exceeding previous state-of-the-art models in the toponym detection task. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2607/ |
| https://www.aclweb.org/anthology/W19-2607 | |
| PWC | https://paperswithcode.com/paper/an-analysis-of-deep-contextual-word |
| Repo | |
| Framework | |
Keyphrase Generation: A Text Summarization Struggle
| Title | Keyphrase Generation: A Text Summarization Struggle |
| Authors | Erion {\c{C}}ano, Ond{\v{r}}ej Bojar |
| Abstract | Authors{'} keyphrases assigned to scientific articles are essential for recognizing content and topic aspects. Most of the proposed supervised and unsupervised methods for keyphrase generation are unable to produce terms that are valuable but do not appear in the text. In this paper, we explore the possibility of considering the keyphrase string as an abstractive summary of the title and the abstract. First, we collect, process and release a large dataset of scientific paper metadata that contains 2.2 million records. Then we experiment with popular text summarization neural architectures. Despite using advanced deep learning models, large quantities of data and many days of computation, our systematic evaluation on four test datasets reveals that the explored text summarization methods could not produce better keyphrases than the simpler unsupervised methods, or the existing supervised ones. |
| Tasks | Text Summarization |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1070/ |
| https://www.aclweb.org/anthology/N19-1070 | |
| PWC | https://paperswithcode.com/paper/keyphrase-generation-a-text-summarization-1 |
| Repo | |
| Framework | |
