October 15, 2019

2662 words 13 mins read

Paper Group NANR 187

Paper Group NANR 187

“Zero-Shot” Super-Resolution Using Deep Internal Learning. Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data. Cluster Labeling by Word Embeddings and WordNet’s Hypernymy. Comparing Theories of Speaker Choice Using a Model of Classifier Production in Mandarin Chinese. The Timing of Lexical Memory Retrievals in Langu …

“Zero-Shot” Super-Resolution Using Deep Internal Learning

Title “Zero-Shot” Super-Resolution Using Deep Internal Learning
Authors Assaf Shocher, Nadav Cohen, Michal Irani
Abstract Deep Learning has led to a dramatic leap in Super-Resolution (SR) performance in the past few years. However, being supervised, these SR methods are restricted to specific training data, where the acquisition of the low-resolution (LR) images from their high-resolution (HR) counterparts is predetermined (e.g., bicubic downscaling), without any distracting artifacts (e.g., sensor noise, image compression, non-ideal PSF, etc). Real LR images, however, rarely obey these restrictions, resulting in poor SR results by SotA (State of the Art) methods. In this paper we introduce ``Zero-Shot’’ SR, which exploits the power of Deep Learning, but does not rely on prior training. We exploit the internal recurrence of information inside a single image, and train a small image-specific CNN at test time, on examples extracted solely from the input image itself. As such, it can adapt itself to different settings per image. This allows to perform SR of real old photos, noisy images, biological data, and other images where the acquisition process is unknown or non-ideal. On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods. To the best of our knowledge, this is the first unsupervised CNN-based SR method. |
Tasks Image Compression, Super-Resolution
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Shocher_Zero-Shot_Super-Resolution_Using_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Shocher_Zero-Shot_Super-Resolution_Using_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/azero-shota-super-resolution-using-deep
Repo
Framework

Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data

Title Urban Zoning Using Higher-Order Markov Random Fields on Multi-View Imagery Data
Authors Tian Feng, Quang-Trung Truong, Duc Thanh Nguyen, Jing Yu Koh, Lap-Fai Yu, Alexander Binder, Sai-Kit Yeung
Abstract Urban zoning enables various applications in land use analysis and urban planning. As cities evolve, it is important to constantly update the zoning maps of cities to reflect urban pattern changes. This paper proposes a method for automatic urban zoning using higher-order Markov random fields (HO-MRF) built on multi-view imagery data including street-view photos and top-view satellite images. In the proposed HO-MRF, top-view satellite data is segmented via a multi-scale deep convolutional neural network (MS-CNN) and used in lower-order potentials. Street-view data with geo-tagged information is augmented in higher-order potentials. Various feature types for classifying street-view images were also investigated in our work. We evaluated the proposed method on a number of famous metropolises and provided in-depth analysis on technical issues.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Tian_Feng_Urban_Zoning_Using_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Tian_Feng_Urban_Zoning_Using_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/urban-zoning-using-higher-order-markov-random
Repo
Framework

Cluster Labeling by Word Embeddings and WordNet’s Hypernymy

Title Cluster Labeling by Word Embeddings and WordNet’s Hypernymy
Authors Hanieh Poostchi, Massimo Piccardi
Abstract Cluster labeling is the assignment of representative labels to clusters obtained from the organization of a document collection. Once assigned, the labels can play an important role in applications such as navigation, search and document classification. However, finding appropriately descriptive labels is still a challenging task. In this paper, we propose various approaches for assigning labels to word clusters by leveraging word embeddings and the synonymity and hypernymy relations in the WordNet lexical ontology. Experiments carried out using the WebAP document dataset have shown that one of the approaches stand out in the comparison and is capable of selecting labels that are reasonably aligned with those chosen by a pool of four human annotators.
Tasks Document Classification, Learning Word Embeddings, Word Embeddings
Published 2018-12-01
URL https://www.aclweb.org/anthology/U18-1008/
PDF https://www.aclweb.org/anthology/U18-1008
PWC https://paperswithcode.com/paper/cluster-labeling-by-word-embeddings-and
Repo
Framework

Comparing Theories of Speaker Choice Using a Model of Classifier Production in Mandarin Chinese

Title Comparing Theories of Speaker Choice Using a Model of Classifier Production in Mandarin Chinese
Authors Meilin Zhan, Roger Levy
Abstract Speakers often have more than one way to express the same meaning. What general principles govern speaker choice in the face of optionality when near semantically invariant alternation exists? Studies have shown that optional reduction in language is sensitive to contextual predictability, such that more predictable a linguistic unit is, the more likely it is to get reduced. Yet it is unclear whether these cases of speaker choice are driven by audience design versus toward facilitating production. Here we argue that for a different optionality phenomenon, namely classifier choice in Mandarin Chinese, Uniform Information Density and at least one plausible variant of availability-based production make opposite predictions regarding the relationship between the predictability of the upcoming material and speaker choices. In a corpus analysis of Mandarin Chinese, we show that the distribution of speaker choices supports the availability-based production account and not the Uniform Information Density.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1181/
PDF https://www.aclweb.org/anthology/N18-1181
PWC https://paperswithcode.com/paper/comparing-theories-of-speaker-choice-using-a
Repo
Framework

The Timing of Lexical Memory Retrievals in Language Production

Title The Timing of Lexical Memory Retrievals in Language Production
Authors Jeremy Cole, David Reitter
Abstract This paper explores the time course of lexical memory retrieval by modeling fluent language production. The duration of retrievals is predicted using the ACT-R cognitive architecture. In a large-scale observational study of a spoken corpus, we find that language production at a time point preceding a word is sped up or slowed down depending on activation of that word. This computational analysis has consequences for the theoretical model of language production. The results point to interference between lexical and phonological stages as well as a quantifiable buffer for lexical information that opens up the possibility of non-sequential retrievals.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1183/
PDF https://www.aclweb.org/anthology/N18-1183
PWC https://paperswithcode.com/paper/the-timing-of-lexical-memory-retrievals-in
Repo
Framework

Global-Locally Self-Attentive Encoder for Dialogue State Tracking

Title Global-Locally Self-Attentive Encoder for Dialogue State Tracking
Authors Victor Zhong, Caiming Xiong, Richard Socher
Abstract Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems. In this paper, we propose the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules. Our model uses global modules to shares parameters between estimators for different types (called slots) of dialogue states, and uses local modules to learn slot-specific features. We show that this significantly improves tracking of rare states. GLAD obtains 88.3{%} joint goal accuracy and 96.4{%} request accuracy on the WoZ state tracking task, outperforming prior work by 3.9{%} and 4.8{%}. On the DSTC2 task, our model obtains 74.7{%} joint goal accuracy and 97.3{%} request accuracy, outperforming prior work by 1.3{%} and 0.8{%}
Tasks Dialogue State Tracking, Representation Learning, Speech Recognition, Spoken Language Understanding, Task-Oriented Dialogue Systems
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1135/
PDF https://www.aclweb.org/anthology/P18-1135
PWC https://paperswithcode.com/paper/global-locally-self-attentive-encoder-for
Repo
Framework

Pivot Correlational Neural Network for Multimodal Video Categorization

Title Pivot Correlational Neural Network for Multimodal Video Categorization
Authors Sunghun Kang, Junyeong Kim, Hyunsoo Choi, Sungjin Kim, Chang D. Yoo
Abstract This paper considers an architecture for multimodal video categorization referred to as Pivot Correlational Neural Network (Pivot CorrNN). The architecture is trained to maximizes the correlation between the hidden states as well as the predictions of the modal-agnostic pivot stream and modal-specific stream in the network. Here, the modal-agnostic pivot hidden state considers all modal inputs without distinction while the modal-specific hidden state is dedicated exclusively to one specific modal input. The Pivot CorrNN consists of three modules: (1) maximizing pivot-correlation module that attempts to maximally correlate the modal-agnostic and a modal-specific hidden-state as well as their predictions, (2) contextual Gated Recurrent Unit (cGRU) module which extends the capability of a generic GRU to take multimodal inputs in updating the pivot hidden-state, and (3) adaptive aggregation module that aggregates all modal-specific predictions as well as the modal-agnostic pivot predictions into one final prediction. We evaluate the Pivot CorrNN on two publicly available large-scale multimodal video categorization datasets, FCVID and YouTube-8M. From the experimental results, Pivot CorrNN achieves the best performance on the FCVID database and performance comparable to the state-of-the-art on YouTube-8M database.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Sunghun_Kang_Pivot_Correlational_Neural_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Sunghun_Kang_Pivot_Correlational_Neural_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/pivot-correlational-neural-network-for
Repo
Framework

Challenging Reading Comprehension on Daily Conversation: Passage Completion on Multiparty Dialog

Title Challenging Reading Comprehension on Daily Conversation: Passage Completion on Multiparty Dialog
Authors Kaixin Ma, Tomasz Jurczyk, Jinho D. Choi
Abstract This paper presents a new corpus and a robust deep learning architecture for a task in reading comprehension, passage completion, on multiparty dialog. Given a dialog in text and a passage containing factual descriptions about the dialog where mentions of the characters are replaced by blanks, the task is to fill the blanks with the most appropriate character names that reflect the contexts in the dialog. Since there is no dataset that challenges the task of passage completion in this genre, we create a corpus by selecting transcripts from a TV show that comprise 1,681 dialogs, generating passages for each dialog through crowdsourcing, and annotating mentions of characters in both the dialog and the passages. Given this dataset, we build a deep neural model that integrates rich feature extraction from convolutional neural networks into sequence modeling in recurrent neural networks, optimized by utterance and dialog level attentions. Our model outperforms the previous state-of-the-art model on this task in a different genre using bidirectional LSTM, showing a 13.0+{%} improvement for longer dialogs. Our analysis shows the effectiveness of the attention mechanisms and suggests a direction to machine comprehension on multiparty dialog.
Tasks Question Answering, Reading Comprehension
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1185/
PDF https://www.aclweb.org/anthology/N18-1185
PWC https://paperswithcode.com/paper/challenging-reading-comprehension-on-daily
Repo
Framework

Probabilistic Boolean Tensor Decomposition

Title Probabilistic Boolean Tensor Decomposition
Authors Tammo Rukat, Chris Holmes, Christopher Yau
Abstract Boolean tensor decomposition approximates data of multi-way binary relationships as product of interpretable low-rank binary factors, following the rules Boolean algebra. Here, we present its first probabilistic treatment. We facilitate scalable sampling-based posterior inference by exploitation of the combinatorial structure of the factor conditionals. Maximum a posteriori estimates consistently outperform existing non-probabilistic approaches. We show that our performance gains can partially be explained by convergence to solutions that occupy relatively large regions of the parameter space, as well as by implicit model averaging. Moreover, the Bayesian treatment facilitates model selection with much greater accuracy than the previously suggested minimum description length based approach. We investigate three real-world data sets. First, temporal interaction networks and behavioural data of university students demonstrate the inference of instructive latent patterns. Next, we decompose a tensor with more than 10 Billion data points, indicating relations of gene expression in cancer patients. Not only does this demonstrate scalability, it also provides an entirely novel perspective on relational properties of continuous data and, in the present example, on the molecular heterogeneity of cancer. Our implementation is available on GitHub: https://github.com/TammoR/LogicalFactorisationMachines
Tasks Model Selection
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=1988
PDF http://proceedings.mlr.press/v80/rukat18a/rukat18a.pdf
PWC https://paperswithcode.com/paper/probabilistic-boolean-tensor-decomposition
Repo
Framework

Fast and Effective Robustness Certification

Title Fast and Effective Robustness Certification
Authors Gagandeep Singh, Timon Gehr, Matthew Mirman, Markus Püschel, Martin Vechev
Abstract We present a new method and system, called DeepZ, for certifying neural network robustness based on abstract interpretation. Compared to state-of-the-art automated verifiers for neural networks, DeepZ: (i) handles ReLU, Tanh and Sigmoid activation functions, (ii) supports feedforward and convolutional architectures, (iii) is significantly more scalable and precise, and (iv) and is sound with respect to floating point arithmetic. These benefits are due to carefully designed approximations tailored to the setting of neural networks. As an example, DeepZ achieves a verification accuracy of 97% on a large network with 88,500 hidden units under $L_{\infty}$ attack with $\epsilon = 0.1$ with an average runtime of 133 seconds.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8278-fast-and-effective-robustness-certification
PDF http://papers.nips.cc/paper/8278-fast-and-effective-robustness-certification.pdf
PWC https://paperswithcode.com/paper/fast-and-effective-robustness-certification
Repo
Framework

Incorporating Background Knowledge into Video Description Generation

Title Incorporating Background Knowledge into Video Description Generation
Authors Spencer Whitehead, Heng Ji, Mohit Bansal, Shih-Fu Chang, Clare Voss
Abstract Most previous efforts toward video captioning focus on generating generic descriptions, such as, {``}A man is talking.{''} We collect a news video dataset to generate enriched descriptions that include important background knowledge, such as named entities and related events, which allows the user to fully understand the video content. We develop an approach that uses video meta-data to retrieve topically related news documents for a video and extracts the events and named entities from these documents. Then, given the video as well as the extracted events and entities, we generate a description using a Knowledge-aware Video Description network. The model learns to incorporate entities found in the topically related documents into the description via an entity pointer network and the generation procedure is guided by the event and entity types from the topically related documents through a knowledge gate, which is a gating mechanism added to the model{'}s decoder that takes a one-hot vector of these types. We evaluate our approach on the new dataset of news videos we have collected, establishing the first benchmark for this dataset as well as proposing a new metric to evaluate these descriptions. |
Tasks Text Generation, Video Captioning, Video Description
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1433/
PDF https://www.aclweb.org/anthology/D18-1433
PWC https://paperswithcode.com/paper/incorporating-background-knowledge-into-video
Repo
Framework

A Deep Learning Based Approach to Transliteration

Title A Deep Learning Based Approach to Transliteration
Authors Soumyadeep Kundu, Sayantan Paul, Santanu Pal
Abstract In this paper, we propose different architectures for language independent machine transliteration which is extremely important for natural language processing (NLP) applications. Though a number of statistical models for transliteration have already been proposed in the past few decades, we proposed some neural network based deep learning architectures for the transliteration of named entities. Our transliteration systems adapt two different neural machine translation (NMT) frameworks: recurrent neural network and convolutional sequence to sequence based NMT. It is shown that our method provides quite satisfactory results when it comes to multi lingual machine transliteration. Our submitted runs are an ensemble of different transliteration systems for all the language pairs. In the NEWS 2018 Shared Task on Transliteration, our method achieves top performance for the En{–}Pe and Pe{–}En language pairs and comparable results for other cases.
Tasks Information Retrieval, Machine Translation, Transliteration
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2411/
PDF https://www.aclweb.org/anthology/W18-2411
PWC https://paperswithcode.com/paper/a-deep-learning-based-approach-to
Repo
Framework

Mining Evidences for Concept Stock Recommendation

Title Mining Evidences for Concept Stock Recommendation
Authors Qi Liu, Yue Zhang
Abstract We investigate the task of mining relevant stocks given a topic of concern on emerging capital markets, for which there is lack of structural understanding. Deep learning is leveraged to mine evidences from large scale textual data, which contain valuable market information. In particular, distributed word similarities trained over large scale raw texts are taken as a basis of relevance measuring, and deep reinforcement learning is leveraged to learn a strategy of topic expansion, given a small amount of manually labeled data from financial analysts. Results on two Chinese stock market datasets show that our method outperforms a strong baseline using information retrieval techniques.
Tasks Information Retrieval
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1191/
PDF https://www.aclweb.org/anthology/N18-1191
PWC https://paperswithcode.com/paper/mining-evidences-for-concept-stock
Repo
Framework

Proceedings of the First International Workshop on Language Cognition and Computational Models

Title Proceedings of the First International Workshop on Language Cognition and Computational Models
Authors
Abstract
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4100/
PDF https://www.aclweb.org/anthology/W18-4100
PWC https://paperswithcode.com/paper/proceedings-of-the-first-international
Repo
Framework

Natural Answer Generation with Heterogeneous Memory

Title Natural Answer Generation with Heterogeneous Memory
Authors Yao Fu, Yansong Feng
Abstract Memory augmented encoder-decoder framework has achieved promising progress for natural language generation tasks. Such frameworks enable a decoder to retrieve from a memory during generation. However, less research has been done to take care of the memory contents from different sources, which are often of heterogeneous formats. In this work, we propose a novel attention mechanism to encourage the decoder to actively interact with the memory by taking its heterogeneity into account. Our solution attends across the generated history and memory to explicitly avoid repetition, and introduce related knowledge to enrich our generated sentences. Experiments on the answer sentence generation task show that our method can effectively explore heterogeneous memory to produce readable and meaningful answer sentences while maintaining high coverage for given answer information.
Tasks Question Answering, Text Generation
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1017/
PDF https://www.aclweb.org/anthology/N18-1017
PWC https://paperswithcode.com/paper/natural-answer-generation-with-heterogeneous
Repo
Framework
comments powered by Disqus