October 15, 2019

1964 words 10 mins read

Paper Group NANR 50

Paper Group NANR 50

A Bayesian Nonparametric View on Count-Min Sketch. Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search. 300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes. Japanese Dialogue Corpus of Information Navigation and Attentive Listening Annotated with Extended ISO-24617-2 Dialogue Act Tags. …

A Bayesian Nonparametric View on Count-Min Sketch

Title A Bayesian Nonparametric View on Count-Min Sketch
Authors Diana Cai, Michael Mitzenmacher, Ryan P. Adams
Abstract The count-min sketch is a time- and memory-efficient randomized data structure that provides a point estimate of the number of times an item has appeared in a data stream. The count-min sketch and related hash-based data structures are ubiquitous in systems that must track frequencies of data such as URLs, IP addresses, and language n-grams. We present a Bayesian view on the count-min sketch, using the same data structure, but providing a posterior distribution over the frequencies that characterizes the uncertainty arising from the hash-based approximation. In particular, we take a nonparametric approach and consider tokens generated from a Dirichlet process (DP) random measure, which allows for an unbounded number of unique tokens. Using properties of the DP, we show that it is possible to straightforwardly compute posterior marginals of the unknown true counts and that the modes of these marginals recover the count-min sketch estimator, inheriting the associated probabilistic guarantees. Using simulated data with known ground truth, we investigate the properties of these estimators. Lastly, we also study a modified problem in which the observation stream consists of collections of tokens (i.e., documents) arising from a random measure drawn from a stable beta process, which allows for power law scaling behavior in the number of unique tokens.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/8093-a-bayesian-nonparametric-view-on-count-min-sketch
PDF http://papers.nips.cc/paper/8093-a-bayesian-nonparametric-view-on-count-min-sketch.pdf
PWC https://paperswithcode.com/paper/a-bayesian-nonparametric-view-on-count-min
Repo
Framework
Title Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search
Authors Jamie Kiros, William Chan, Geoffrey Hinton
Abstract We introduce Picturebook, a large-scale lookup operation to ground language via {`}snapshots{'} of our physical world accessed through image search. For each word in a vocabulary, we extract the top-$k$ images from Google image search and feed the images through a convolutional network to extract a word embedding. We introduce a multimodal gating function to fuse our Picturebook embeddings with other word representations. We also introduce Inverse Picturebook, a mechanism to map a Picturebook embedding back into words. We experiment and report results across a wide range of tasks: word similarity, natural language inference, semantic relatedness, sentiment/topic classification, image-sentence ranking and machine translation. We also show that gate activations corresponding to Picturebook embeddings are highly correlated to human judgments of concreteness ratings. |
Tasks Image Retrieval, Machine Translation, Natural Language Inference, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-1085/
PDF https://www.aclweb.org/anthology/P18-1085
PWC https://paperswithcode.com/paper/illustrative-language-understanding-large
Repo
Framework

300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes

Title 300-sparsans at SemEval-2018 Task 9: Hypernymy as interaction of sparse attributes
Authors G{'a}bor Berend, M{'a}rton Makrai, P{'e}ter F{"o}ldi{'a}k
Abstract This paper describes 300-sparsians{'}s participation in SemEval-2018 Task 9: Hypernym Discovery, with a system based on sparse coding and a formal concept hierarchy obtained from word embeddings. Our system took first place in subtasks (1B) Italian (all and entities), (1C) Spanish entities, and (2B) music entities.
Tasks Hypernym Discovery, Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1152/
PDF https://www.aclweb.org/anthology/S18-1152
PWC https://paperswithcode.com/paper/300-sparsans-at-semeval-2018-task-9-hypernymy
Repo
Framework

Japanese Dialogue Corpus of Information Navigation and Attentive Listening Annotated with Extended ISO-24617-2 Dialogue Act Tags

Title Japanese Dialogue Corpus of Information Navigation and Attentive Listening Annotated with Extended ISO-24617-2 Dialogue Act Tags
Authors Koichiro Yoshino, Hiroki Tanaka, Kyoshiro Sugiyama, Makoto Kondo, Satoshi Nakamura
Abstract
Tasks Slot Filling, Spoken Dialogue Systems, Task-Oriented Dialogue Systems
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1462/
PDF https://www.aclweb.org/anthology/L18-1462
PWC https://paperswithcode.com/paper/japanese-dialogue-corpus-of-information
Repo
Framework

Proceedings of the 1st Workshop on Automatic Text Adaptation (ATA)

Title Proceedings of the 1st Workshop on Automatic Text Adaptation (ATA)
Authors Arne J{"o}nsson, Evelina Rennes, Horacio Saggion, Sanja Stajner, Victoria Yaneva
Abstract
Tasks
Published 2018-11-01
URL https://www.aclweb.org/anthology/papers/W/W18/W18-7000/
PDF https://www.aclweb.org/anthology/W18-7000
PWC https://paperswithcode.com/paper/proceedings-of-the-1st-workshop-on-automatic
Repo
Framework

Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse

Title Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse
Authors Sheng Xu, Peifeng Li, Guodong Zhou, Qiaoming Zhu
Abstract The task of nuclearity recognition in Chinese discourse remains challenging due to the demand for more deep semantic information. In this paper, we propose a novel text matching network (TMN) that encodes the discourse units and the paragraphs by combining Bi-LSTM and CNN to capture both global dependency information and local n-gram information. Moreover, it introduces three components of text matching, the Cosine, Bilinear and Single Layer Network, to incorporate various similarities and interactions among the discourse units. Experimental results on the Chinese Discourse TreeBank show that our proposed TMN model significantly outperforms various strong baselines in both micro-F1 and macro-F1.
Tasks Question Answering, Text Matching
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1044/
PDF https://www.aclweb.org/anthology/C18-1044
PWC https://paperswithcode.com/paper/employing-text-matching-network-to-recognise
Repo
Framework

ABDN at SemEval-2018 Task 10: Recognising Discriminative Attributes using Context Embeddings and WordNet

Title ABDN at SemEval-2018 Task 10: Recognising Discriminative Attributes using Context Embeddings and WordNet
Authors Rui Mao, Guanyi Chen, Ruizhe Li, Chenghua Lin
Abstract This paper describes the system that we submitted for SemEval-2018 task 10: capturing discriminative attributes. Our system is built upon a simple idea of measuring the attribute word{'}s similarity with each of the two semantically similar words, based on an extended word embedding method and WordNet. Instead of computing the similarities between the attribute and semantically similar words by using standard word embeddings, we propose a novel method that combines word and context embeddings which can better measure similarities. Our model is simple and effective, which achieves an average F1 score of 0.62 on the test set.
Tasks Semantic Textual Similarity, Word Embeddings
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1169/
PDF https://www.aclweb.org/anthology/S18-1169
PWC https://paperswithcode.com/paper/abdn-at-semeval-2018-task-10-recognising
Repo
Framework

YNU_Deep at SemEval-2018 Task 11: An Ensemble of Attention-based BiLSTM Models for Machine Comprehension

Title YNU_Deep at SemEval-2018 Task 11: An Ensemble of Attention-based BiLSTM Models for Machine Comprehension
Authors Peng Ding, Xiaobing Zhou
Abstract We firstly use GloVe to learn the distributed representations automatically from the instance, question and answer triples. Then an attentionbased Bidirectional LSTM (BiLSTM) model is used to encode the triples. We also perform a simple ensemble method to improve the effectiveness of our model. The system we developed obtains an encouraging result on this task. It achieves the accuracy 0.7472 on the test set. We rank 5th according to the official ranking.
Tasks Machine Translation, Reading Comprehension, Text Summarization
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1174/
PDF https://www.aclweb.org/anthology/S18-1174
PWC https://paperswithcode.com/paper/ynu_deep-at-semeval-2018-task-11-an-ensemble
Repo
Framework

ITNLP-ARC at SemEval-2018 Task 12: Argument Reasoning Comprehension with Attention

Title ITNLP-ARC at SemEval-2018 Task 12: Argument Reasoning Comprehension with Attention
Authors Wenjie Liu, Chengjie Sun, Lei Lin, Bingquan Liu
Abstract Reasoning is a very important topic and has many important applications in the field of natural language processing. Semantic Evaluation (SemEval) 2018 Task 12 {``}The Argument Reasoning Comprehension{''} committed to research natural language reasoning. In this task, we proposed a novel argument reasoning comprehension system, ITNLP-ARC, which use Neural Networks technology to solve this problem. In our system, the LSTM model is involved to encode both the premise sentences and the warrant sentences. The attention model is used to merge the two premise sentence vectors. Through comparing the similarity between the attention vector and each of the two warrant vectors, we choose the one with higher similarity as our system{'}s final answer. |
Tasks Information Retrieval, Machine Translation, Natural Language Inference, Relation Extraction, Semantic Textual Similarity, Text Summarization
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1183/
PDF https://www.aclweb.org/anthology/S18-1183
PWC https://paperswithcode.com/paper/itnlp-arc-at-semeval-2018-task-12-argument
Repo
Framework

Semantic Parsing for Technical Support Questions

Title Semantic Parsing for Technical Support Questions
Authors Abhirut Gupta, Anupama Ray, Gargi Dasgupta, Gautam Singh, Pooja Aggarwal, Prateeti Mohapatra
Abstract Technical support problems are very complex. In contrast to regular web queries (that contain few keywords) or factoid questions (which are a few sentences), these problems usually include attributes like a detailed description of what is failing (symptom), steps taken in an effort to remediate the failure (activity), and sometimes a specific request or ask (intent). Automating support is the task of automatically providing answers to these problems given a corpus of solution documents. Traditional approaches to this task rely on information retrieval and are keyword based; looking for keyword overlap between the question and solution documents and ignoring these attributes. We present an approach for semantic parsing of technical questions that uses grammatical structure to extract these attributes as a baseline, and a CRF based model that can improve performance considerably in the presence of annotated data for training. We also demonstrate that combined with reasoning, these attributes help outperform retrieval baselines.
Tasks Information Retrieval, Semantic Parsing
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1275/
PDF https://www.aclweb.org/anthology/C18-1275
PWC https://paperswithcode.com/paper/semantic-parsing-for-technical-support
Repo
Framework

Matics Software Suite: New Tools for Evaluation and Data Exploration

Title Matics Software Suite: New Tools for Evaluation and Data Exploration
Authors Olivier Galibert, Guillaume Bernard, Agnes Delaborde, Sabrina Lecadre, Juliette Kahn
Abstract
Tasks Optical Character Recognition, Speaker Diarization, Speaker Identification, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1319/
PDF https://www.aclweb.org/anthology/L18-1319
PWC https://paperswithcode.com/paper/matics-software-suite-new-tools-for
Repo
Framework

Frequency-Domain Dynamic Pruning for Convolutional Neural Networks

Title Frequency-Domain Dynamic Pruning for Convolutional Neural Networks
Authors Zhenhua Liu, Jizheng Xu, Xiulian Peng, Ruiqin Xiong
Abstract Deep convolutional neural networks have demonstrated their powerfulness in a variety of applications. However, the storage and computational requirements have largely restricted their further extensions on mobile devices. Recently, pruning of unimportant parameters has been used for both network compression and acceleration. Considering that there are spatial redundancy within most filters in a CNN, we propose a frequency-domain dynamic pruning scheme to exploit the spatial correlations. The frequency-domain coefficients are pruned dynamically in each iteration and different frequency bands are pruned discriminatively, given their different importance on accuracy. Experimental results demonstrate that the proposed scheme can outperform previous spatial-domain counterparts by a large margin. Specifically, it can achieve a compression ratio of 8.4x and a theoretical inference speed-up of 9.2x for ResNet-110, while the accuracy is even better than the reference model on CIFAR-110.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7382-frequency-domain-dynamic-pruning-for-convolutional-neural-networks
PDF http://papers.nips.cc/paper/7382-frequency-domain-dynamic-pruning-for-convolutional-neural-networks.pdf
PWC https://paperswithcode.com/paper/frequency-domain-dynamic-pruning-for
Repo
Framework

MirasVoice: A bilingual (English-Persian) speech corpus

Title MirasVoice: A bilingual (English-Persian) speech corpus
Authors Amir Vaheb, Ali Janalizadeh Choobbasti, S.H.E. Mortazavi Najafabadi, Saeid Safavi, Behnam Sabeti
Abstract
Tasks Speaker Recognition, Speaker Verification, Speech Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1459/
PDF https://www.aclweb.org/anthology/L18-1459
PWC https://paperswithcode.com/paper/mirasvoice-a-bilingual-english-persian-speech
Repo
Framework

Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds

Title Content-Sensitive Supervoxels via Uniform Tessellations on Video Manifolds
Authors Ran Yi, Yong-Jin Liu, Yu-Kun Lai
Abstract Supervoxels are perceptually meaningful atomic regions in videos, obtained by grouping voxels that exhibit coherence in both appearance and motion. In this paper, we propose content-sensitive supervoxels (CSS), which are regularly-shaped 3D primitive volumes that possess the following characteristic: they are typically larger and longer in content-sparse regions (i.e., with homogeneous appearance and motion), and smaller and shorter in content-dense regions (i.e., with high variation of appearance and/or motion). To compute CSS, we map a video X to a 3-dimensional manifold M embedded in R^6, whose volume elements give a good measure of the content density in X. We propose an efficient Lloyd-like method with a splitting-merging scheme to compute a uniform tessellation on M, which induces the CSS in X. Theoretically our method has a good competitive ratio O(1). We also present a simple extension of CSS to stream CSS for processing long videos that cannot be loaded into main memory at once. We evaluate CSS, stream CSS and seven representative supervoxel methods on four video datasets. The results show that our method outperforms existing supervoxel methods.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Yi_Content-Sensitive_Supervoxels_via_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Yi_Content-Sensitive_Supervoxels_via_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/content-sensitive-supervoxels-via-uniform
Repo
Framework

The AnnCor CHILDES Treebank

Title The AnnCor CHILDES Treebank
Authors Jan Odijk, Alexis Dimitriadis, Martijn van der Klis, Marjo van Koppen, Meie Otten, Remco van der Veen
Abstract
Tasks Language Acquisition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1360/
PDF https://www.aclweb.org/anthology/L18-1360
PWC https://paperswithcode.com/paper/the-anncor-childes-treebank
Repo
Framework
comments powered by Disqus