October 15, 2019

2339 words 11 mins read

Paper Group NANR 199

Paper Group NANR 199

Towards an Automatic Assessment of Crowdsourced Data for NLU. Incremental Natural Language Processing: Challenges, Strategies, and Evaluation. Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018) …

Towards an Automatic Assessment of Crowdsourced Data for NLU

Title Towards an Automatic Assessment of Crowdsourced Data for NLU
Authors Patricia Braunger, Wolfgang Maier, Jan Wessling, Maria Schmidt
Abstract
Tasks Language Modelling, Speech Recognition, Text Generation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1315/
PDF https://www.aclweb.org/anthology/L18-1315
PWC https://paperswithcode.com/paper/towards-an-automatic-assessment-of
Repo
Framework

Incremental Natural Language Processing: Challenges, Strategies, and Evaluation

Title Incremental Natural Language Processing: Challenges, Strategies, and Evaluation
Authors Arne K{"o}hn
Abstract Incrementality is ubiquitous in human-human interaction and beneficial for human-computer interaction. It has been a topic of research in different parts of the NLP community, mostly with focus on the specific topic at hand even though incremental systems have to deal with similar challenges regardless of domain. In this survey, I consolidate and categorize the approaches, identifying similarities and differences in the computation and data, and show trade-offs that have to be considered. A focus lies on evaluating incremental systems because the standard metrics often fail to capture the incremental properties of a system and coming up with a suitable evaluation scheme is non-trivial.
Tasks Dialogue Understanding
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1253/
PDF https://www.aclweb.org/anthology/C18-1253
PWC https://paperswithcode.com/paper/incremental-natural-language-processing
Repo
Framework

Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction

Title Learning from limited datasets: Implications for Natural Language Generation and Human-Robot Interaction
Authors Jekaterina Belakova, Dimitra Gkatzia
Abstract One of the most natural ways for human robot communication is through spoken language. Training human-robot interaction systems require access to large datasets which are expensive to obtain and labour intensive. In this paper, we describe an approach for learning from minimal data, using as a toy example language understanding in spoken dialogue systems. Understanding of spoken language is crucial because it has implications for natural language generation, i.e. correctly understanding a user{'}s utterance will lead to choosing the right response/action. Finally, we discuss implications for Natural Language Generation in Human-Robot Interaction.
Tasks One-Shot Learning, Spoken Dialogue Systems, Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6902/
PDF https://www.aclweb.org/anthology/W18-6902
PWC https://paperswithcode.com/paper/learning-from-limited-datasets-implications
Repo
Framework

Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)

Title Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC-2018)
Authors Nicoletta Calzolari, Khalid Choukri, Christopher Cieri, Thierry Declerck, Koiti Hasida, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis, Takenobu Tokunaga, Sara Goggi, H{'e}l{`e}ne Mazo
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/papers/L/L18/L18-1000/
PDF https://www.aclweb.org/anthology/L18-1000
PWC https://paperswithcode.com/paper/proceedings-of-the-eleventh-international
Repo
Framework

Unsupervised CNN-based Co-Saliency Detection with Graphical Optimization

Title Unsupervised CNN-based Co-Saliency Detection with Graphical Optimization
Authors Kuang-Jui Hsu, Chung-Chi Tsai, Yen-Yu Lin, Xiaoning Qian, Yung-Yu Chuang
Abstract In this paper, we address co-saliency detection in a set of images jointly covering objects of a specific class by an unsupervised convolutional neural network (CNN). Our method does not require any additional training data in the form of object masks. We decompose co-saliency detection into two sub-tasks, single-image saliency detection and cross-image co-occurrence region discovery corresponding to two novel unsupervised losses, the single-image saliency (SIS) loss and the co-occurrence (COOC) loss. The two losses are modeled on a graphical model where the former and the latter act as the unary and pairwise terms, respectively. These two tasks can be jointly optimized for generating co-saliency maps of high quality. Furthermore, the quality of the generated co-saliency maps can be enhanced via two extensions: map sharpening by self-paced learning and boundary preserving by fully connected conditional random fields. Experiments show that our method achieves superior results, even outperforming many supervised methods.
Tasks Co-Saliency Detection, Saliency Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Kuang-Jui_Hsu_Unsupervised_CNN-based_co-saliency_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Kuang-Jui_Hsu_Unsupervised_CNN-based_co-saliency_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/unsupervised-cnn-based-co-saliency-detection
Repo
Framework

Tailoring Neural Architectures for Translating from Morphologically Rich Languages

Title Tailoring Neural Architectures for Translating from Morphologically Rich Languages
Authors Peyman Passban, Andy Way, Qun Liu
Abstract A morphologically complex word (MCW) is a hierarchical constituent with meaning-preserving subunits, so word-based models which rely on surface forms might not be powerful enough to translate such structures. When translating from morphologically rich languages (MRLs), a source word could be mapped to several words or even a full sentence on the target side, which means an MCW should not be treated as an atomic unit. In order to provide better translations for MRLs, we boost the existing neural machine translation (NMT) architecture with a double- channel encoder and a double-attentive decoder. The main goal targeted in this research is to provide richer information on the encoder side and redesign the decoder accordingly to benefit from such information. Our experimental results demonstrate that we could achieve our goal as the proposed model outperforms existing subword- and character-based architectures and showed significant improvements on translating from German, Russian, and Turkish into English.
Tasks Machine Translation
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1265/
PDF https://www.aclweb.org/anthology/C18-1265
PWC https://paperswithcode.com/paper/tailoring-neural-architectures-for
Repo
Framework

Word Relation Autoencoder for Unseen Hypernym Extraction Using Word Embeddings

Title Word Relation Autoencoder for Unseen Hypernym Extraction Using Word Embeddings
Authors Hong-You Chen, Cheng-Syuan Lee, Keng-Te Liao, Shou-De Lin
Abstract Lexicon relation extraction given distributional representation of words is an important topic in NLP. We observe that the state-of-the-art projection-based methods cannot be generalized to handle unseen hypernyms. We propose to analyze it in the perspective of pollution and construct the corresponding indicator to measure it. We propose a word relation autoencoder (WRAE) model to address the challenge. Experiments on several hypernym-like lexicon datasets show that our model outperforms the competitors significantly.
Tasks Relation Extraction, Word Embeddings
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1519/
PDF https://www.aclweb.org/anthology/D18-1519
PWC https://paperswithcode.com/paper/word-relation-autoencoder-for-unseen-hypernym
Repo
Framework

TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights

Title TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights
Authors Diwen Wan, Fumin Shen, Li Liu, Fan Zhu, Jie Qin, Ling Shao, Heng Tao Shen
Abstract Despite the remarkable success of Convolutional Neural Networks (CNNs) on generalized visual tasks, high computational and memory costs restrict their comprehensive applications on consumer electronics (e.g., portable or smart wearable devices). Recent advancements in binarized networks have demonstrated progress on reducing computational and memory costs, however, they suffer from significant performance degradation comparing to their full-precision counterparts. Thus, a highly-economical yet effective CNN that is authentically applicable to consumer electronics is at urgent need. In this work, we propose a Ternary-Binary Network (TBN), which provides an efficient approximation to standard CNNs. Based on an accelerated ternary-binary matrix multiplication, TBN replaces the arithmetical operations in standard CNNs with efficient XOR, AND and bitcount operations, and thus provides an optimal tradeoff between memory, efficiency and performance. TBN demonstrates its consistent effectiveness when applied to various CNN architectures (e.g., AlexNet and ResNet) on multiple datasets of different scales, and provides ~32x memory savings and 40x faster convolutional operations. Meanwhile, TBN can outperform XNOR-Network by up to 5.5% (top-1 accuracy) on the ImageNet classification task, and up to 4.4% (mAP score) on the PASCAL VOC object detection task.
Tasks Object Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Diwen_Wan_TBN_Convolutional_Neural_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Diwen_Wan_TBN_Convolutional_Neural_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/tbn-convolutional-neural-network-with-ternary
Repo
Framework

ALANIS at SemEval-2018 Task 3: A Feature Engineering Approach to Irony Detection in English Tweets

Title ALANIS at SemEval-2018 Task 3: A Feature Engineering Approach to Irony Detection in English Tweets
Authors Kevin Swanberg, Madiha Mirza, Ted Pedersen, Zhenduo Wang
Abstract This paper describes the ALANIS system that participated in Task 3 of SemEval-2018. We develop a system for detection of irony, as well as the detection of three types of irony: verbal polar irony, other verbal irony, and situational irony. The system uses a logistic regression model in subtask A and a voted classifier system with manually developed features to identify ironic tweets. This model improves on a naive bayes baseline by about 8 percent on training set.
Tasks Feature Engineering, Feature Selection, Semantic Textual Similarity
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1082/
PDF https://www.aclweb.org/anthology/S18-1082
PWC https://paperswithcode.com/paper/alanis-at-semeval-2018-task-3-a-feature
Repo
Framework

uOttawa at SemEval-2018 Task 1: Self-Attentive Hybrid GRU-Based Network

Title uOttawa at SemEval-2018 Task 1: Self-Attentive Hybrid GRU-Based Network
Authors Ahmed Husseini Orabi, Mahmoud Husseini Orabi, Diana Inkpen, David Van Bruwaene
Abstract We propose a novel attentive hybrid GRU-based network (SAHGN), which we used at SemEval-2018 Task 1: Affect in Tweets. Our network has two main characteristics, 1) has the ability to internally optimize its feature representation using attention mechanisms, and 2) provides a hybrid representation using a character level Convolutional Neural Network (CNN), as well as a self-attentive word-level encoder. The key advantage of our model is its ability to signify the relevant and important information that enables self-optimization. Results are reported on the valence intensity regression task.
Tasks Tokenization
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1027/
PDF https://www.aclweb.org/anthology/S18-1027
PWC https://paperswithcode.com/paper/uottawa-at-semeval-2018-task-1-self-attentive
Repo
Framework

Universal Growth in Production Economies

Title Universal Growth in Production Economies
Authors Simina Branzei, Ruta Mehta, Noam Nisan
Abstract We study a simple variant of the von Neumann model of an expanding economy, in which multiple producers make goods according to their production function. The players trade their goods at the market and then use the bundles received as inputs for the production in the next round. The decision that players have to make is how to invest their money (i.e. bids) in each round. We show that a simple decentralized dynamic, where players update their bids on the goods in the market proportionally to how useful the investments were, leads to growth of the economy in the long term (whenever growth is possible) but also creates unbounded inequality, i.e. very rich and very poor players emerge. We analyze several other phenomena, such as how the relation of a player with others influences its development and the Gini index of the system.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7467-universal-growth-in-production-economies
PDF http://papers.nips.cc/paper/7467-universal-growth-in-production-economies.pdf
PWC https://paperswithcode.com/paper/universal-growth-in-production-economies
Repo
Framework

Pruning Basic Elements for Better Automatic Evaluation of Summaries

Title Pruning Basic Elements for Better Automatic Evaluation of Summaries
Authors Ukyo Honda, Tsutomu Hirao, Masaaki Nagata
Abstract We propose a simple but highly effective automatic evaluation measure of summarization, pruned Basic Elements (pBE). Although the BE concept is widely used for the automated evaluation of summaries, its weakness is that it redundantly matches basic elements. To avoid this redundancy, pBE prunes basic elements by (1) disregarding frequency count of basic elements and (2) reducing semantically overlapped basic elements based on word similarity. Even though it is simple, pBE outperforms ROUGE in DUC datasets in most cases and achieves the highest rank correlation coefficient in TAC 2011 AESOP task.
Tasks Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2104/
PDF https://www.aclweb.org/anthology/N18-2104
PWC https://paperswithcode.com/paper/pruning-basic-elements-for-better-automatic
Repo
Framework

Iterative temporal differencing with fixed random feedback alignment support spike-time dependent plasticity in vanilla backpropagation for deep learning

Title Iterative temporal differencing with fixed random feedback alignment support spike-time dependent plasticity in vanilla backpropagation for deep learning
Authors Aras Dargazany, Kunal Mankodiya
Abstract In vanilla backpropagation (VBP), activation function matters considerably in terms of non-linearity and differentiability. Vanishing gradient has been an important problem related to the bad choice of activation function in deep learning (DL). This work shows that a differentiable activation function is not necessary any more for error backpropagation. The derivative of the activation function can be replaced by an iterative temporal differencing (ITD) using fixed random feedback weight alignment (FBA). Using FBA with ITD, we can transform the VBP into a more biologically plausible approach for learning deep neural network architectures. We don’t claim that ITD works completely the same as the spike-time dependent plasticity (STDP) in our brain but this work can be a step toward the integration of STDP-based error backpropagation in deep learning.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=BkpXqwUTZ
PDF https://openreview.net/pdf?id=BkpXqwUTZ
PWC https://paperswithcode.com/paper/iterative-temporal-differencing-with-fixed
Repo
Framework

Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts

Title Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts
Authors Annie Louis, Charles Sutton
Abstract An essential aspect to understanding narratives is to grasp the interaction between characters in a story and the actions they take. We examine whether computational models can capture this interaction, when both character attributes and actions are expressed as complex natural language descriptions. We propose role-playing games as a testbed for this problem, and introduce a large corpus of game transcripts collected from online discussion forums. Using neural language models which combine character and action descriptions from these stories, we show that we can learn the latent ties. Action sequences are better predicted when the character performing the action is also taken into account, and vice versa for character attributes.
Tasks Topic Models
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2111/
PDF https://www.aclweb.org/anthology/N18-2111
PWC https://paperswithcode.com/paper/deep-dungeons-and-dragons-learning-character
Repo
Framework

Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks

Title Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks
Authors Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen
Abstract Benefiting from tens of millions of hierarchically stacked learnable parameters, Deep Neural Networks (DNNs) have demonstrated overwhelming accuracy on a variety of artificial intelligence tasks. However reversely, the large size of DNN models lays a heavy burden on storage, computation and power consumption, which prohibits their deployments on the embedded and mobile systems. In this paper, we propose Explicit Loss-error-aware Quantization (ELQ), a new method that can train DNN models with very low-bit parameter values such as ternary and binary ones to approximate 32-bit floating-point counterparts without noticeable loss of predication accuracy. Unlike existing methods that usually pose the problem as a straightforward approximation of the layer-wise weights or outputs of the original full-precision model (specifically, minimizing the error of the layer-wise weights or inner products of the weights and the inputs between the original and respective quantized models), our ELQ elaborately bridges the loss perturbation from the weight quantization and an incremental quantization strategy to address DNN quantization. Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective. As validated with two mainstream convolutional neural network families (i.e., fully convolutional and non-fully convolutional), our ELQ shows better results than the state-of-the-art quantization methods on the large scale ImageNet classification dataset. Code will be made publicly available.
Tasks Quantization
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_Explicit_Loss-Error-Aware_Quantization_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Explicit_Loss-Error-Aware_Quantization_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/explicit-loss-error-aware-quantization-for
Repo
Framework
comments powered by Disqus