Paper Group NANR 264
Representation-Constrained Autoencoders and an Application to Wireless Positioning. Linguistic Information in Neural Semantic Parsing with Multiple Encoders. Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition. CaRe: Open Knowledge Graph Embeddings. From Virtual to Real: A Framework for Verbal Interaction …
Representation-Constrained Autoencoders and an Application to Wireless Positioning
| Title | Representation-Constrained Autoencoders and an Application to Wireless Positioning |
| Authors | Pengzhi Huang, Emre Gonultas, Said Medjkouh, Oscar Castaneda, Olav Tirkkonen, Tom Goldstein, Christoph Studer |
| Abstract | In a number of practical applications that rely on dimensionality reduction, the dataset or measurement process provides valuable side information that can be incorporated when learning low-dimensional embeddings. We propose the inclusion of pairwise representation constraints into autoencoders (AEs) with the goal of promoting application-specific structure. We use synthetic results to show that only a small amount of AE representation constraints are required to substantially improve the local and global neighborhood preserving properties of the learned embeddings. To demonstrate the efficacy of our approach and to illustrate a practical application that naturally provides such representation constraints, we focus on wireless positioning using a recently proposed channel charting framework. We show that representation-constrained AEs recover the global geometry of the learned low-dimensional representations, which enables channel charting to perform approximate positioning without access to global navigation satellite systems or supervised learning methods that rely on extensive measurement campaigns. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryemosC9tm |
| https://openreview.net/pdf?id=ryemosC9tm | |
| PWC | https://paperswithcode.com/paper/representation-constrained-autoencoders-and |
| Repo | |
| Framework | |
Linguistic Information in Neural Semantic Parsing with Multiple Encoders
| Title | Linguistic Information in Neural Semantic Parsing with Multiple Encoders |
| Authors | Rik van Noord, Antonio Toral, Johan Bos |
| Abstract | Recently, sequence-to-sequence models have achieved impressive performance on a number of semantic parsing tasks. However, they often do not exploit available linguistic resources, while these, when employed correctly, are likely to increase performance even further. Research in neural machine translation has shown that employing this information has a lot of potential, especially when using a multi-encoder setup. We employ a range of semantic and syntactic resources to improve performance for the task of Discourse Representation Structure Parsing. We show that (i) linguistic features can be beneficial for neural semantic parsing and (ii) the best method of adding these features is by using multiple encoders. |
| Tasks | Machine Translation, Semantic Parsing |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0504/ |
| https://www.aclweb.org/anthology/W19-0504 | |
| PWC | https://paperswithcode.com/paper/linguistic-information-in-neural-semantic |
| Repo | |
| Framework | |
Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition
| Title | Big BiRD: A Large, Fine-Grained, Bigram Relatedness Dataset for Examining Semantic Composition |
| Authors | Shima Asaadi, Saif Mohammad, Svetlana Kiritchenko |
| Abstract | Bigrams (two-word sequences) hold a special place in semantic composition research since they are the smallest unit formed by composing words. A semantic relatedness dataset that includes bigrams will thus be useful in the development of automatic methods of semantic composition. However, existing relatedness datasets only include pairs of unigrams (single words). Further, existing datasets were created using rating scales and thus suffer from limitations such as in consistent annotations and scale region bias. In this paper, we describe how we created a large, fine-grained, bigram relatedness dataset (BiRD), using a comparative annotation technique called Best{–}Worst Scaling. Each of BiRD{'}s 3,345 English term pairs involves at least one bigram. We show that the relatedness scores obtained are highly reliable (split-half reliability r= 0.937). We analyze the data to obtain insights into bigram semantic relatedness. Finally, we present benchmark experiments on using the relatedness dataset as a testbed to evaluate simple unsupervised measures of semantic composition. BiRD is made freely available to foster further research on how meaning can be represented and how meaning can be composed. |
| Tasks | Semantic Composition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1050/ |
| https://www.aclweb.org/anthology/N19-1050 | |
| PWC | https://paperswithcode.com/paper/big-bird-a-large-fine-grained-bigram |
| Repo | |
| Framework | |
CaRe: Open Knowledge Graph Embeddings
| Title | CaRe: Open Knowledge Graph Embeddings |
| Authors | Swapnil Gupta, Sreyash Kenkre, Partha Talukdar |
| Abstract | Open Information Extraction (OpenIE) methods are effective at extracting (noun phrase, relation phrase, noun phrase) triples from text, e.g., (Barack Obama, took birth in, Honolulu). Organization of such triples in the form of a graph with noun phrases (NPs) as nodes and relation phrases (RPs) as edges results in the construction of Open Knowledge Graphs (OpenKGs). In order to use such OpenKGs in downstream tasks, it is often desirable to learn embeddings of the NPs and RPs present in the graph. Even though several Knowledge Graph (KG) embedding methods have been recently proposed, all of those methods have targeted Ontological KGs, as opposed to OpenKGs. Straightforward application of existing Ontological KG embedding methods to OpenKGs is challenging, as unlike Ontological KGs, OpenKGs are not canonicalized, i.e., a real-world entity may be represented using multiple nodes in the OpenKG, with each node corresponding to a different NP referring to the entity. For example, nodes with labels Barack Obama, Obama, and President Obama may refer to the same real-world entity Barack Obama. Even though canonicalization of OpenKGs has received some attention lately, output of such methods has not been used to improve OpenKG embed- dings. We fill this gap in the paper and propose Canonicalization-infused Representations (CaRe) for OpenKGs. Through extensive experiments, we observe that CaRe enables existing models to adapt to the challenges in OpenKGs and achieve substantial improvements for the link prediction task. |
| Tasks | Knowledge Graph Embeddings, Knowledge Graphs, Link Prediction, Open Information Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1036/ |
| https://www.aclweb.org/anthology/D19-1036 | |
| PWC | https://paperswithcode.com/paper/care-open-knowledge-graph-embeddings |
| Repo | |
| Framework | |
From Virtual to Real: A Framework for Verbal Interaction with Robots
| Title | From Virtual to Real: A Framework for Verbal Interaction with Robots |
| Authors | Eugene Joseph |
| Abstract | A Natural Language Understanding (NLU) pipeline integrated with a 3D physics-based scene is a flexible way to develop and test language-based human-robot interaction, by virtualizing people, robot hardware and the target 3D environment. Here, interaction means both controlling robots using language and conversing with them about the user{'}s physical environment and her daily life. Such a virtual development framework was initially developed for the Bot Colony videogame launched on Steam in June 2014, and has been undergoing improvements since. The framework is focused of developing intuitive verbal interaction with various types of robots. Key robot functions (robot vision and object recognition, path planning and obstacle avoidance, task planning and constraints, grabbing and inverse kinematics), the human participants in the interaction, and the impact of gravity and other forces on the environment are all simulated using commercial 3D tools. The framework can be used as a robotics testbed: the results of our simulations can be compared with the output of algorithms in real robots, to validate such algorithms. A novelty of our framework is support for social interaction with robots - enabling robots to converse about people and objects in the user{'}s environment, as well as learning about human needs and everyday life topics from their owner. |
| Tasks | Object Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1603/ |
| https://www.aclweb.org/anthology/W19-1603 | |
| PWC | https://paperswithcode.com/paper/from-virtual-to-real-a-framework-for-verbal |
| Repo | |
| Framework | |
DANA: Scalable Out-of-the-box Distributed ASGD Without Retuning
| Title | DANA: Scalable Out-of-the-box Distributed ASGD Without Retuning |
| Authors | Ido Hakimi, Saar Barkai, Moshe Gabel, Assaf Schuster |
| Abstract | Distributed computing can significantly reduce the training time of neural networks. Despite its potential, however, distributed training has not been widely adopted: scaling the training process is difficult, and existing SGD methods require substantial tuning of hyperparameters and learning schedules to achieve sufficient accuracy when increasing the number of workers. In practice, such tuning can be prohibitively expensive given the huge number of potential hyperparameter configurations and the effort required to test each one. We propose DANA, a novel approach that scales out-of-the-box to large clusters using the same hyperparameters and learning schedule optimized for training on a single worker, while maintaining similar final accuracy without additional overhead. DANA estimates the future value of model parameters by adapting Nesterov Accelerated Gradient to a distributed setting, and so mitigates the effect of gradient staleness, one of the main difficulties in scaling SGD to more workers. Evaluation on three state-of-the-art network architectures and three datasets shows that DANA scales as well as or better than existing work without having to tune any hyperparameters or tweak the learning schedule. For example, DANA achieves 75.73% accuracy on ImageNet when training ResNet-50 with 16 workers, similar to the non-distributed baseline. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkGQujR5FX |
| https://openreview.net/pdf?id=SkGQujR5FX | |
| PWC | https://paperswithcode.com/paper/dana-scalable-out-of-the-box-distributed-asgd |
| Repo | |
| Framework | |
Latin script keyboards for South Asian languages with finite-state normalization
| Title | Latin script keyboards for South Asian languages with finite-state normalization |
| Authors | Lawrence Wolf-Sonkin, Vlad Schogol, Brian Roark, Michael Riley |
| Abstract | The use of the Latin script for text entry of South Asian languages is common, even though there is no standard orthography for these languages in the script. We explore several compact finite-state architectures that permit variable spellings of words during mobile text entry. We find that approaches making use of transliteration transducers provide large accuracy improvements over baselines, but that simpler approaches involving a compact representation of many attested alternatives yields much of the accuracy gain. This is particularly important when operating under constraints on model size (e.g., on inexpensive mobile devices with limited storage and memory for keyboard models), and on speed of inference, since people typing on mobile keyboards expect no perceptual delay in keyboard responsiveness. |
| Tasks | Transliteration |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-3114/ |
| https://www.aclweb.org/anthology/W19-3114 | |
| PWC | https://paperswithcode.com/paper/latin-script-keyboards-for-south-asian |
| Repo | |
| Framework | |
Metaphors in Text Simplification: To change or not to change, that is the question
| Title | Metaphors in Text Simplification: To change or not to change, that is the question |
| Authors | Yulia Clausen, Vivi Nastase |
| Abstract | We present an analysis of metaphors in news text simplification. Using features that capture general and metaphor specific characteristics, we test whether we can automatically identify which metaphors will be changed or preserved, and whether there are features that have different predictive power for metaphors or literal words. The experiments show that the Age of Acquisition is the most distinctive feature for both metaphors and literal words. Features that capture Imageability and Concreteness are useful when used alone, but within the full set of features they lose their impact. Frequency of use seems to be the best feature to differentiate metaphors that should be changed and those to be preserved. |
| Tasks | Text Simplification |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4444/ |
| https://www.aclweb.org/anthology/W19-4444 | |
| PWC | https://paperswithcode.com/paper/metaphors-in-text-simplification-to-change-or |
| Repo | |
| Framework | |
A Modular Architecture for Unsupervised Sarcasm Generation
| Title | A Modular Architecture for Unsupervised Sarcasm Generation |
| Authors | Abhijit Mishra, Tarun Tater, Karthik Sankaranarayanan |
| Abstract | In this paper, we propose a novel framework for sarcasm generation; the system takes a literal negative opinion as input and translates it into a sarcastic version. Our framework does not require any paired data for training. Sarcasm emanates from context-incongruity which becomes apparent as the sentence unfolds. Our framework introduces incongruity into the literal input version through modules that: (a) filter factual content from the input opinion, (b) retrieve incongruous phrases related to the filtered facts and (c) synthesize sarcastic text from the incongruous filtered and incongruous phrases. The framework employs reinforced neural sequence to sequence learning and information retrieval and is trained only using unlabeled non-sarcastic and sarcastic opinions. Since no labeled dataset exists for such a task, for evaluation, we manually prepare a benchmark dataset containing literal opinions and their sarcastic paraphrases. Qualitative and quantitative performance analyses on the data reveal our system{'}s superiority over baselines built using known unsupervised statistical and neural machine translation and style transfer techniques. |
| Tasks | Information Retrieval, Machine Translation, Style Transfer |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1636/ |
| https://www.aclweb.org/anthology/D19-1636 | |
| PWC | https://paperswithcode.com/paper/a-modular-architecture-for-unsupervised |
| Repo | |
| Framework | |
Link Prediction in Hypergraphs using Graph Convolutional Networks
| Title | Link Prediction in Hypergraphs using Graph Convolutional Networks |
| Authors | Naganand Yadati, Vikram Nitin, Madhav Nimishakavi, Prateek Yadav, Anand Louis, Partha Talukdar |
| Abstract | Link prediction in simple graphs is a fundamental problem in which new links between nodes are predicted based on the observed structure of the graph. However, in many real-world applications, there is a need to model relationships among nodes which go beyond pairwise associations. For example, in a chemical reaction, relationship among the reactants and products is inherently higher-order. Additionally, there is need to represent the direction from reactants to products. Hypergraphs provide a natural way to represent such complex higher-order relationships. Even though Graph Convolutional Networks (GCN) have recently emerged as a powerful deep learning-based approach for link prediction over simple graphs, their suitability for link prediction in hypergraphs is unexplored – we fill this gap in this paper and propose Neural Hyperlink Predictor (NHP). NHP adapts GCNs for link prediction in hypergraphs. We propose two variants of NHP –NHP-U and NHP-D – for link prediction over undirected and directed hypergraphs, respectively. To the best of our knowledge, NHP-D is the first method for link prediction over directed hypergraphs. Through extensive experiments on multiple real-world datasets, we show NHP’s effectiveness. |
| Tasks | Link Prediction |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryeaZhRqFm |
| https://openreview.net/pdf?id=ryeaZhRqFm | |
| PWC | https://paperswithcode.com/paper/link-prediction-in-hypergraphs-using-graph |
| Repo | |
| Framework | |
Training Hard-Threshold Networks with Combinatorial Search in a Discrete Target Propagation Setting
| Title | Training Hard-Threshold Networks with Combinatorial Search in a Discrete Target Propagation Setting |
| Authors | Lukas Nabergall, Justin Toth, Leah Cousins |
| Abstract | Learning deep neural networks with hard-threshold activation has recently become an important problem due to the proliferation of resource-constrained computing devices. In order to circumvent the inability to train with backpropagation in the present of hard-threshold activations, \cite{friesen2017} introduced a discrete target propagation framework for training hard-threshold networks in a layer-by-layer fashion. Rather than using a gradient-based target heuristic, we explore the use of search methods for solving the target setting problem. Building on both traditional combinatorial optimization algorithms and gradient-based techniques, we develop a novel search algorithm Guided Random Local Search (GRLS). We demonstrate the effectiveness of our algorithm in training small networks on several datasets and evaluate our target-setting algorithm compared to simpler search methods and gradient-based techniques. Our results indicate that combinatorial optimization is a viable method for training hard-threshold networks that may have the potential to eventually surpass gradient-based methods in many settings. |
| Tasks | Combinatorial Optimization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkeX-3Rqtm |
| https://openreview.net/pdf?id=rkeX-3Rqtm | |
| PWC | https://paperswithcode.com/paper/training-hard-threshold-networks-with |
| Repo | |
| Framework | |
Toward Realistic Image Compositing With Adversarial Learning
| Title | Toward Realistic Image Compositing With Adversarial Learning |
| Authors | Bor-Chun Chen, Andrew Kae |
| Abstract | Compositing a realistic image is a challenging task and usually requires considerable human supervision using professional image editing software. In this work we propose a generative adversarial network (GAN) architecture for automatic image compositing. The proposed model consists of four sub-networks: a transformation network that improves the geometric and color consistency of the composite image, a refinement network that polishes the boundary of the composite image, and a pair of discriminator network and a segmentation network for adversarial learning. Experimental results on both synthesized images and real images show that our model, Geometrically and Color Consistent GANs (GCC-GANs), can automatically generate realistic composite images compared to several state-of-the-art methods, and does not require any manual effort. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Toward_Realistic_Image_Compositing_With_Adversarial_Learning_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_Toward_Realistic_Image_Compositing_With_Adversarial_Learning_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/toward-realistic-image-compositing-with |
| Repo | |
| Framework | |
Amharic Word Sequence Prediction
| Title | Amharic Word Sequence Prediction |
| Authors | Nuniyat Kifle |
| Abstract | The significance of computers and handheld devices are not deniable in the modern world of today. Texts are entered to these devices using word processing programs as well as other techniques and word prediction is one of the techniques. Word Prediction is the action of guessing or forecasting what word comes after, based on some current information, and it is the main focus of this study. Even though Amharic is used by a large number of populations, no significant work is done on the topic of word sequence prediction. In this study, Amharic word sequence prediction model is developed with statistical methods using Hidden Markov Model by incorporating detailed Part of speech tag. Evaluation of the model is performed using developed prototype and keystroke savings (KSS) as a metrics. According to our experiment, prediction result using a bi-gram with detailed Part of Speech tag model has higher KSS and it is better compared to tri-gram model and better than those without Part of Speech tag. Therefore, statistical approach with Detailed POS has quite good potential on word sequence prediction for Amharic language. This research deals with designing word sequence prediction model in Amharic language. It is a language that is spoken in eastern Africa. One of the needs for Amharic word sequence prediction for mobile use and other digital devices is in order to facilitate data entry and communication in our language. Word sequence prediction is a challenging task for inflected languages. (Arora, 2007) These kinds of languages are morphologically rich and have enormous word forms. i.e. one word can have different forms. As Amharic language is highly inflected language and morphologically rich it shares this problem. (prediction, 2008) This problem makes word prediction system much more difficult and results poor performance. Due to this reason storing all forms in dictionary won{'}t solve the problem as in English and other less inflected languages. But considering other techniques that could help the predictor to suggest the next word like a POS based prediction should be used. Previous researches used dictionary approach with no consideration of context information. Hence storing all forms of words in dictionary for inflected languages such as Amharic language has been less effective. The main goal of this thesis is to implement Amharic word prediction model that works with better prediction speed and with narrowed search space as much as possible. We introduced two models; tags and words and linear interpolation that use part of speech tag information in addition to word n-grams in order to maximize the likelihood of syntactic appropriateness of the suggestions. We believe the results found reflect this. Amharic word sequence prediction using bi-gram model with higher POS weight and detailed Part of speech tag gave better keystroke savings in all scenarios of our experiment. The study followed Design Science Research Methodology (DSRM). Since DSRM includes approaches, techniques, tools, algorithms and evaluation mechanisms in the process, we followed statistical approach with statistical language modeling and built Amharic prediction model based on information from Part of Speech tagger. The statistics included in the systems varies from single word frequencies to part-of-speech tag n-grams. That means it included the statistics of Word frequencies, Word sequence frequencies, Part-of-speech sequence frequencies and other important information. Later on the system was evaluated using Keystroke Savings. (Lindh, 011). Linux mint was used as the main Operation System during the frame work design. We used corpus of 680,000 tagged words that has 31 tag sets, python programming language and its libraries for both the part of speech tagger and the predictor module. Other Tool that was used is the SRILIM (The SRI language modeling toolkit) in order to generate unigram bigram and trigram count as an input for the language model. SRILIM is toolkit that uses to build and apply statistical language modeling. This thesis presented Amharic word sequence prediction model using the statistical approach. We described a combined statistical and lexical word prediction system for handling inflected languages by making use of POS tags to build the language model. We developed Amharic language models of bigram and trigram for the training purpose. We obtained 29{%} of KSS using bigram model with detailed part ofspeech tag. Hence, Based on the experiments carried out for this study and the results obtained, the following conclusions were made. We concluded that employing syntactic information in the form of Part-of-Speech (POS) n-grams promises more effective predictions. We also can conclude data quantity, performance of POS tagger and data quality highly affects the keystroke savings. Here in our study the tests were done on a small collection of 100 phrases. According to our evaluation better Keystroke saving (KSS) is achieved when using bi-gram model than the tri-gram models. We believe the results obtained using the experiment of detailed Part of speech tags were effective Since speed and search space are the basic issues in word sequence prediction |
| Tasks | Language Modelling |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3607/ |
| https://www.aclweb.org/anthology/W19-3607 | |
| PWC | https://paperswithcode.com/paper/amharic-word-sequence-prediction |
| Repo | |
| Framework | |
Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings
| Title | Quality Estimation and Translation Metrics via Pre-trained Word and Sentence Embeddings |
| Authors | Elizaveta Yankovskaya, Andre T{"a}ttar, Mark Fishel |
| Abstract | We propose the use of pre-trained embeddings as features of a regression model for sentence-level quality estimation of machine translation. In our work we combine freely available BERT and LASER multilingual embeddings to train a neural-based regression model. In the second proposed method we use as an input features not only pre-trained embeddings, but also log probability of any machine translation (MT) system. Both methods are applied to several language pairs and are evaluated both as a classical quality estimation system (predicting the HTER score) as well as an MT metric (predicting human judgements of translation quality). |
| Tasks | Machine Translation, Sentence Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5410/ |
| https://www.aclweb.org/anthology/W19-5410 | |
| PWC | https://paperswithcode.com/paper/quality-estimation-and-translation-metrics |
| Repo | |
| Framework | |
Multi-View Image Fusion
| Title | Multi-View Image Fusion |
| Authors | Marc Comino Trinidad, Ricardo Martin Brualla, Florian Kainz, Janne Kontkanen |
| Abstract | We present an end-to-end learned system for fusing multiple misaligned photographs of the same scene into a chosen target view. We demonstrate three use cases: 1) color transfer for inferring color for a monochrome view, 2) HDR fusion for merging misaligned bracketed exposures, and 3) detail transfer for reprojecting a high definition image to the point of view of an affordable VR180-camera. While the system can be trained end-to-end, it consists of three distinct steps: feature extraction, image warping and fusion. We present a novel cascaded feature extraction method that enables us to synergetically learn optical flow at different resolution levels. We show that this significantly improves the network’s ability to learn large disparities. Finally, we demonstrate that our alignment architecture outperforms a state-of-the art optical flow network on the image warping task when both systems are trained in an identical manner. |
| Tasks | Optical Flow Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Trinidad_Multi-View_Image_Fusion_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Trinidad_Multi-View_Image_Fusion_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multi-view-image-fusion |
| Repo | |
| Framework | |
