Paper Group NANR 275
An LSTM-CRF Based Approach to Token-Level Metaphor Detection. Towards a Linked Open Data Edition of Sumerian Corpora. Visual Object Networks: Image Generation with Disentangled 3D Representations. Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA. Parametric Manifold Learning Via Sparse Multidimensional Scaling. End-to-End Co …
An LSTM-CRF Based Approach to Token-Level Metaphor Detection
| Title | An LSTM-CRF Based Approach to Token-Level Metaphor Detection |
| Authors | Malay Pramanick, Ashim Gupta, Pabitra Mitra |
| Abstract | Automatic processing of figurative languages is gaining popularity in NLP community for their ubiquitous nature and increasing volume. In this era of web 2.0, automatic analysis of sarcasm and metaphors is important for their extensive usage. Metaphors are a part of figurative language that compares different concepts, often on a cognitive level. Many approaches have been proposed for automatic detection of metaphors, even using sequential models or neural networks. In this paper, we propose a method for detection of metaphors at the token level using a hybrid model of Bidirectional-LSTM and CRF. We used fewer features, as compared to the previous state-of-the-art sequential model. On experimentation with VUAMC, our method obtained an F-score of 0.674. |
| Tasks | Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0908/ |
| https://www.aclweb.org/anthology/W18-0908 | |
| PWC | https://paperswithcode.com/paper/an-lstm-crf-based-approach-to-token-level |
| Repo | |
| Framework | |
Towards a Linked Open Data Edition of Sumerian Corpora
| Title | Towards a Linked Open Data Edition of Sumerian Corpora |
| Authors | Christian Chiarcos, {'E}milie Pag{'e}-Perron, Ilya Khait, Niko Schenk, Lucas Reckling |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1387/ |
| https://www.aclweb.org/anthology/L18-1387 | |
| PWC | https://paperswithcode.com/paper/towards-a-linked-open-data-edition-of |
| Repo | |
| Framework | |
Visual Object Networks: Image Generation with Disentangled 3D Representations
| Title | Visual Object Networks: Image Generation with Disentangled 3D Representations |
| Authors | Jun-Yan Zhu, Zhoutong Zhang, Chengkai Zhang, Jiajun Wu, Antonio Torralba, Josh Tenenbaum, Bill Freeman |
| Abstract | Recent progress in deep generative models has led to tremendous breakthroughs in image generation. While being able to synthesize photorealistic images, existing models lack an understanding of our underlying 3D world. Different from previous works built on 2D datasets and models, we present a new generative model, Visual Object Networks (VONs), synthesizing natural images of objects with a disentangled 3D representation. Inspired by classic graphics rendering pipelines, we unravel the image formation process into three conditionally independent factors—shape, viewpoint, and texture—and present an end-to-end adversarial learning framework that jointly models 3D shape and 2D texture. Our model first learns to synthesize 3D shapes that are indistinguishable from real shapes. It then renders the object’s 2.5D sketches (i.e., silhouette and depth map) from its shape under a sampled viewpoint. Finally, it learns to add realistic textures to these 2.5D sketches to generate realistic images. The VON not only generates images that are more realistic than the state-of-the-art 2D image synthesis methods but also enables many 3D operations such as changing the viewpoint of a generated image, shape and texture editing, linear interpolation in texture and shape space, and transferring appearance across different objects and viewpoints. |
| Tasks | Image Generation |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7297-visual-object-networks-image-generation-with-disentangled-3d-representations |
| http://papers.nips.cc/paper/7297-visual-object-networks-image-generation-with-disentangled-3d-representations.pdf | |
| PWC | https://paperswithcode.com/paper/visual-object-networks-image-generation-with-1 |
| Repo | |
| Framework | |
Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA
| Title | Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA |
| Authors | Jialiang Zhang, Soroosh Khoram, Jing Li |
| Abstract | We present a new method for Product Quantization (PQ) based approximated nearest neighbor search (ANN) in high dimensional spaces. Specifically, we first propose a quantization scheme for the codebook of coarse quantizer, product quantizer, and rotation matrix, to reduce the cost of accessing these codebooks. Our approach also combines a highly parallel k-selection method, which can be fused with the distance calculation to reduce the memory overhead. We implement the proposed method on Intel HARPv2 platform using OpenCL-FPGA. The proposed method significantly outperforms state-of-the-art methods on CPU and GPU for high dimensional nearest neighbor queries on billion-scale datasets in terms of query time and accuracy regardless of the batch size. To our best knowledge, this is the first work to demonstrate FPGA performance superior to CPU and GPU on high-dimensional, large-scale ANN datasets. |
| Tasks | Quantization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Efficient_Large-Scale_Approximate_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Efficient_Large-Scale_Approximate_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-large-scale-approximate-nearest-1 |
| Repo | |
| Framework | |
Parametric Manifold Learning Via Sparse Multidimensional Scaling
| Title | Parametric Manifold Learning Via Sparse Multidimensional Scaling |
| Authors | Gautam Pai, Ronen Talmon, Ron Kimmel |
| Abstract | We propose a metric-learning framework for computing distance-preserving maps that generate low-dimensional embeddings for a certain class of manifolds. We employ Siamese networks to solve the problem of least squares multidimensional scaling for generating mappings that preserve geodesic distances on the manifold. In contrast to previous parametric manifold learning methods we show a substantial reduction in training effort enabled by the computation of geodesic distances in a farthest point sampling strategy. Additionally, the use of a network to model the distance-preserving map reduces the complexity of the multidimensional scaling problem and leads to an improved non-local generalization of the manifold compared to analogous non-parametric counterparts. We demonstrate our claims on point-cloud data and on image manifolds and show a numerical analysis of our technique to facilitate a greater understanding of the representational power of neural networks in modeling manifold data. |
| Tasks | Metric Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=B1uvH_gC- |
| https://openreview.net/pdf?id=B1uvH_gC- | |
| PWC | https://paperswithcode.com/paper/parametric-manifold-learning-via-sparse |
| Repo | |
| Framework | |
End-to-End Convolutional Semantic Embeddings
| Title | End-to-End Convolutional Semantic Embeddings |
| Authors | Quanzeng You, Zhengyou Zhang, Jiebo Luo |
| Abstract | Semantic embeddings for images and sentences have been widely studied recently. The ability of deep neural networks on learning rich and robust visual and textual representations offers the opportunity to develop effective semantic embedding models. Currently, the state-of-the-art approaches in semantic learning first employ deep neural networks to encode images and sentences into a common semantic space. Then, the learning objective is to ensure a larger similarity between matching image and sentence pairs than randomly sampled pairs. Usually, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are employed for learning image and sentence representations, respectively. On one hand, CNNs are known to produce robust visual features at different levels and RNNs are known for capturing dependencies in sequential data. Therefore, this simple framework can be sufficiently effective in learning visual and textual semantics. On the other hand, different from CNNs, RNNs cannot produce middle-level (e.g. phrase-level in text) representations. As a result, only global representations are available for semantic learning. This could potentially limit the performance of the model due to the hierarchical structures in images and sentences. In this work, we apply Convolutional Neural Networks to process both images and sentences. Consequently, we can employ mid-level representations to assist global semantic learning by introducing a new learning objective on the convolutional layers. The experimental results show that our proposed textual CNN models with the new learning objective lead to better performance than the state-of-the-art approaches. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/You_End-to-End_Convolutional_Semantic_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/You_End-to-End_Convolutional_Semantic_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-convolutional-semantic-embeddings |
| Repo | |
| Framework | |
Neural Text Generation in Stories Using Entity Representations as Context
| Title | Neural Text Generation in Stories Using Entity Representations as Context |
| Authors | Elizabeth Clark, Yangfeng Ji, Noah A. Smith |
| Abstract | We introduce an approach to neural text generation that explicitly represents entities mentioned in the text. Entity representations are vectors that are updated as the text proceeds; they are designed specifically for narrative text like fiction or news stories. Our experiments demonstrate that modeling entities offers a benefit in two automatic evaluations: mention generation (in which a model chooses which entity to mention next and which words to use in the mention) and selection between a correct next sentence and a distractor from later in the same story. We also conduct a human evaluation on automatically generated text in story contexts; this study supports our emphasis on entities and suggests directions for further research. |
| Tasks | Dialogue Generation, Representation Learning, Text Generation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1204/ |
| https://www.aclweb.org/anthology/N18-1204 | |
| PWC | https://paperswithcode.com/paper/neural-text-generation-in-stories-using |
| Repo | |
| Framework | |
Efficient inference for time-varying behavior during learning
| Title | Efficient inference for time-varying behavior during learning |
| Authors | Nicholas G. Roy, Ji Hyun Bak, Athena Akrami, Carlos Brody, Jonathan W. Pillow |
| Abstract | The process of learning new behaviors over time is a problem of great interest in both neuroscience and artificial intelligence. However, most standard analyses of animal training data either treat behavior as fixed or track only coarse performance statistics (e.g., accuracy, bias), providing limited insight into the evolution of the policies governing behavior. To overcome these limitations, we propose a dynamic psychophysical model that efficiently tracks trial-to-trial changes in behavior over the course of training. Our model consists of a dynamic logistic regression model, parametrized by a set of time-varying weights that express dependence on sensory stimuli as well as task-irrelevant covariates, such as stimulus, choice, and answer history. Our implementation scales to large behavioral datasets, allowing us to infer 500K parameters (e.g. 10 weights over 50K trials) in minutes on a desktop computer. We optimize hyperparameters governing how rapidly each weight evolves over time using the decoupled Laplace approximation, an efficient method for maximizing marginal likelihood in non-conjugate models. To illustrate performance, we apply our method to psychophysical data from both rats and human subjects learning a delayed sensory discrimination task. The model successfully tracks the psychophysical weights of rats over the course of training, capturing day-to-day and trial-to-trial fluctuations that underlie changes in performance, choice bias, and dependencies on task history. Finally, we investigate why rats frequently make mistakes on easy trials, and suggest that apparent lapses can be explained by sub-optimal weighting of known task covariates. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7812-efficient-inference-for-time-varying-behavior-during-learning |
| http://papers.nips.cc/paper/7812-efficient-inference-for-time-varying-behavior-during-learning.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-inference-for-time-varying-behavior |
| Repo | |
| Framework | |
Probabilistic Joint Face-Skull Modelling for Facial Reconstruction
| Title | Probabilistic Joint Face-Skull Modelling for Facial Reconstruction |
| Authors | Dennis Madsen, Marcel Lüthi, Andreas Schneider, Thomas Vetter |
| Abstract | We present a novel method for co-registration of two independent statistical shape models. We solve the problem of aligning a face model to a skull model with stochastic optimization based on Markov Chain Monte Carlo (MCMC). We create a probabilistic joint face-skull model and show how to obtain a distribution of plausible face shapes given a skull shape. Due to environmental and genetic factors, there exists a distribution of possible face shapes arising from the same skull. We pose facial reconstruction as a conditional distribution of plausible face shapes given a skull shape. Because it is very difficult to obtain the distribution directly from MRI or CT data, we create a dataset of artificial face-skull pairs. To do this, we propose to combine three data sources of independent origin to model the joint face-skull distribution: a face shape model, a skull shape model and tissue depth marker information. For a given skull, we compute the posterior distribution of faces matching the tissue depth distribution with Metropolis-Hastings. We estimate the joint face-skull distribution from samples of the posterior. To find faces matching to an unknown skull, we estimate the probability of the face under the joint face-skull model. To our knowledge, we are the first to provide a whole distribution of plausible faces arising from a skull instead of only a single reconstruction. We show how the face-skull model can be used to rank a face dataset and on average successfully identify the correct match in top 30%. The face ranking even works when obtaining the face shapes from 2D images. We furthermore show how the face-skull model can be useful to estimate the skull position in an MR-image. |
| Tasks | Stochastic Optimization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Madsen_Probabilistic_Joint_Face-Skull_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Madsen_Probabilistic_Joint_Face-Skull_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-joint-face-skull-modelling-for |
| Repo | |
| Framework | |
Learning to Collaborate for Question Answering and Asking
| Title | Learning to Collaborate for Question Answering and Asking |
| Authors | Duyu Tang, Nan Duan, Zhao Yan, Zhirui Zhang, Yibo Sun, Shujie Liu, Yuanhua Lv, Ming Zhou |
| Abstract | Question answering (QA) and question generation (QG) are closely related tasks that could improve each other; however, the connection of these two tasks is not well explored in literature. In this paper, we give a systematic study that seeks to leverage the connection to improve both QA and QG. We present a training algorithm that generalizes both Generative Adversarial Network (GAN) and Generative Domain-Adaptive Nets (GDAN) under the question answering scenario. The two key ideas are improving the QG model with QA through incorporating additional QA-specific signal as the loss function, and improving the QA model with QG through adding artificially generated training instances. We conduct experiments on both document based and knowledge based question answering tasks. We have two main findings. Firstly, the performance of a QG model (e.g in terms of BLEU score) could be easily improved by a QA model via policy gradient. Secondly, directly applying GAN that regards all the generated questions as negative instances could not improve the accuracy of the QA model. Learning when to regard generated questions as positive instances could bring performance boost. |
| Tasks | Answer Selection, Question Answering, Question Generation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1141/ |
| https://www.aclweb.org/anthology/N18-1141 | |
| PWC | https://paperswithcode.com/paper/learning-to-collaborate-for-question |
| Repo | |
| Framework | |
ValenTO at SemEval-2018 Task 3: Exploring the Role of Affective Content for Detecting Irony in English Tweets
| Title | ValenTO at SemEval-2018 Task 3: Exploring the Role of Affective Content for Detecting Irony in English Tweets |
| Authors | Delia Iraz{'u} Hern{'a}ndez Far{'\i}as, Viviana Patti, Paolo Rosso |
| Abstract | In this paper we describe the system used by the ValenTO team in the shared task on Irony Detection in English Tweets at SemEval 2018. The system takes as starting point emotIDM, an irony detection model that explores the use of affective features based on a wide range of lexical resources available for English, reflecting different facets of affect. We experimented with different settings, by exploiting different classifiers and features, and participated both to the binary irony detection task and to the task devoted to distinguish among different types of irony. We report on the results obtained by our system both in a constrained setting and unconstrained setting, where we explored the impact of using additional data in the training phase, such as corpora annotated for the presence of irony or sarcasm from the state of the art. Overall, the performance of our system seems to validate the important role that affective information has for identifying ironic content in Twitter. |
| Tasks | Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1105/ |
| https://www.aclweb.org/anthology/S18-1105 | |
| PWC | https://paperswithcode.com/paper/valento-at-semeval-2018-task-3-exploring-the |
| Repo | |
| Framework | |
Mixed Feelings: Natural Text Generation with Variable, Coexistent Affective Categories
| Title | Mixed Feelings: Natural Text Generation with Variable, Coexistent Affective Categories |
| Authors | Lee Kezar |
| Abstract | Conversational agents, having the goal of natural language generation, must rely on language models which can integrate emotion into their responses. Recent projects outline models which can produce emotional sentences, but unlike human language, they tend to be restricted to one affective category out of a few. To my knowledge, none allow for the intentional coexistence of multiple emotions on the word or sentence level. Building on prior research which allows for variation in the intensity of a singular emotion, this research proposal outlines an LSTM (Long Short-Term Memory) language model which allows for variation in multiple emotions simultaneously. |
| Tasks | Language Modelling, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-3020/ |
| https://www.aclweb.org/anthology/P18-3020 | |
| PWC | https://paperswithcode.com/paper/mixed-feelings-natural-text-generation-with |
| Repo | |
| Framework | |
Author Profiling from Facebook Corpora
| Title | Author Profiling from Facebook Corpora |
| Authors | Fern Hsieh, o, Rafael Dias, Iv Paraboni, r{'e} |
| Abstract | |
| Tasks | Document Classification, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1407/ |
| https://www.aclweb.org/anthology/L18-1407 | |
| PWC | https://paperswithcode.com/paper/author-profiling-from-facebook-corpora |
| Repo | |
| Framework | |
Tilde’s Parallel Corpus Filtering Methods for WMT 2018
| Title | Tilde’s Parallel Corpus Filtering Methods for WMT 2018 |
| Authors | M{=a}rcis Pinnis |
| Abstract | The paper describes parallel corpus filtering methods that allow reducing noise of noisy {``}parallel{''} corpora from a level where the corpora are not usable for neural machine translation training (i.e., the resulting systems fail to achieve reasonable translation quality; well below 10 BLEU points) up to a level where the trained systems show decent (over 20 BLEU points on a 10 million word dataset and up to 30 BLEU points on a 100 million word dataset). The paper also documents Tilde{'}s submissions to the WMT 2018 shared task on parallel corpus filtering. | |
| Tasks | Machine Translation, Transliteration, Word Alignment |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6486/ |
| https://www.aclweb.org/anthology/W18-6486 | |
| PWC | https://paperswithcode.com/paper/tildes-parallel-corpus-filtering-methods-for |
| Repo | |
| Framework | |
A Novel Approach to Part Name Discovery in Noisy Text
| Title | A Novel Approach to Part Name Discovery in Noisy Text |
| Authors | Nobal Bikram Niraula, Daniel Whyatt, Anne Kao |
| Abstract | As a specialized example of information extraction, part name extraction is an area that presents unique challenges. Part names are typically multi-word terms longer than two words. There is little consistency in how terms are described in noisy free text, with variations spawned by typos, ad hoc abbreviations, acronyms, and incomplete names. This makes search and analyses of parts in these data extremely challenging. In this paper, we present our algorithm, PANDA (Part Name Discovery Analytics), based on a unique method that exploits statistical, linguistic and machine learning techniques to discover part names in noisy text such as that in manufacturing quality documentation, supply chain management records, service communication logs, and maintenance reports. Experiments show that PANDA is scalable and outperforms existing techniques significantly. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-3021/ |
| https://www.aclweb.org/anthology/N18-3021 | |
| PWC | https://paperswithcode.com/paper/a-novel-approach-to-part-name-discovery-in |
| Repo | |
| Framework | |
