Paper Group NANR 182
Using Images to Improve Machine-Translating E-Commerce Product Listings.. Natural Language Descriptions for Human Activities in Video Streams. Superpixels and Polygons Using Simple Non-Iterative Clustering. On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning. Cross view link prediction by learning noise-resilient r …
Using Images to Improve Machine-Translating E-Commerce Product Listings.
| Title | Using Images to Improve Machine-Translating E-Commerce Product Listings. |
| Authors | Iacer Calixto, Daniel Stein, Evgeny Matusov, Pintu Lohar, Sheila Castilho, Andy Way |
| Abstract | In this paper we study the impact of using images to machine-translate user-generated e-commerce product listings. We study how a multi-modal Neural Machine Translation (NMT) model compares to two text-only approaches: a conventional state-of-the-art attentional NMT and a Statistical Machine Translation (SMT) model. User-generated product listings often do not constitute grammatical or well-formed sentences. More often than not, they consist of the juxtaposition of short phrases or keywords. We train our models end-to-end as well as use text-only and multi-modal NMT models for re-ranking $n$-best lists generated by an SMT model. We qualitatively evaluate our user-generated training data also analyse how adding synthetic data impacts the results. We evaluate our models quantitatively using BLEU and TER and find that (i) additional synthetic data has a general positive impact on text-only and multi-modal NMT models, and that (ii) using a multi-modal NMT model for re-ranking n-best lists improves TER significantly across different n-best list sizes. |
| Tasks | Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2101/ |
| https://www.aclweb.org/anthology/E17-2101 | |
| PWC | https://paperswithcode.com/paper/using-images-to-improve-machine-translating-e |
| Repo | |
| Framework | |
Natural Language Descriptions for Human Activities in Video Streams
| Title | Natural Language Descriptions for Human Activities in Video Streams |
| Authors | Nouf Alharbi, Yoshihiko Gotoh |
| Abstract | There has been continuous growth in the volume and ubiquity of video material. It has become essential to define video semantics in order to aid the searchability and retrieval of this data. We present a framework that produces textual descriptions of video, based on the visual semantic content. Detected action classes rendered as verbs, participant objects converted to noun phrases, visual properties of detected objects rendered as adjectives and spatial relations between objects rendered as prepositions. Further, in cases of zero-shot action recognition, a language model is used to infer a missing verb, aided by the detection of objects and scene settings. These extracted features are converted into textual descriptions using a template-based approach. The proposed video descriptions framework evaluated on the NLDHA dataset using ROUGE scores and human judgment evaluation. |
| Tasks | Language Modelling, Temporal Action Localization, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3512/ |
| https://www.aclweb.org/anthology/W17-3512 | |
| PWC | https://paperswithcode.com/paper/natural-language-descriptions-for-human |
| Repo | |
| Framework | |
Superpixels and Polygons Using Simple Non-Iterative Clustering
| Title | Superpixels and Polygons Using Simple Non-Iterative Clustering |
| Authors | Radhakrishna Achanta, Sabine Susstrunk |
| Abstract | We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we also present a polygonal partitioning algorithm. We demonstrate that our superpixels as well as the polygonal partitioning are superior to the respective state-of-the-art algorithms on quantitative benchmarks. |
| Tasks | |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Achanta_Superpixels_and_Polygons_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Achanta_Superpixels_and_Polygons_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/superpixels-and-polygons-using-simple-non |
| Repo | |
| Framework | |
On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning
| Title | On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning |
| Authors | Xingguo Li, Lin Yang, Jason Ge, Jarvis Haupt, Tong Zhang, Tuo Zhao |
| Abstract | We propose a DC proximal Newton algorithm for solving nonconvex regularized sparse learning problems in high dimensions. Our proposed algorithm integrates the proximal newton algorithm with multi-stage convex relaxation based on the difference of convex (DC) programming, and enjoys both strong computational and statistical guarantees. Specifically, by leveraging a sophisticated characterization of sparse modeling structures (i.e., local restricted strong convexity and Hessian smoothness), we prove that within each stage of convex relaxation, our proposed algorithm achieves (local) quadratic convergence, and eventually obtains a sparse approximate local optimum with optimal statistical properties after only a few convex relaxations. Numerical experiments are provided to support our theory. |
| Tasks | Sparse Learning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6867-on-quadratic-convergence-of-dc-proximal-newton-algorithm-in-nonconvex-sparse-learning |
| http://papers.nips.cc/paper/6867-on-quadratic-convergence-of-dc-proximal-newton-algorithm-in-nonconvex-sparse-learning.pdf | |
| PWC | https://paperswithcode.com/paper/on-quadratic-convergence-of-dc-proximal |
| Repo | |
| Framework | |
Cross view link prediction by learning noise-resilient representation consensus
| Title | Cross view link prediction by learning noise-resilient representation consensus |
| Authors | Xiaokai Wei, Linchuan Xu, Bokai Cao and Philip S. Yu |
| Abstract | Link Prediction has been an important task for social and information networks. Existing approaches usually assume the completeness of network structure. However, in many real-world networks, the links and node attributes can usually be partially observable. In this paper, we study the problem of Cross View Link Prediction (CVLP) on partially observable networks, where the focus is to recommend nodes with only links to nodes with only attributes (or vice versa). We aim to bridge the information gap by learning a robust consensus for link-based and attribute-based representations so that nodes become comparable in the latent space. Also, the link-based and attribute-based representations can lend strength to each other via this consensus learning. Moreover, attribute selection is performed jointly with the representation learning to alleviate the effect of noisy high-dimensional attributes. We present two instantiations of this framework with different loss functions and develop an alternating optimization framework to solve the problem. Experimental results on four real-world datasets show the proposed algorithm outperforms the baseline methods significantly for crossview link prediction. |
| Tasks | Link Prediction, Representation Learning |
| Published | 2017-04-03 |
| URL | https://dl.acm.org/citation.cfm?id=3038912.3052575 |
| http://papers.www2017.com.au.s3-website-ap-southeast-2.amazonaws.com/proceedings/p1611.pdf | |
| PWC | https://paperswithcode.com/paper/cross-view-link-prediction-by-learning-noise |
| Repo | |
| Framework | |
Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks
| Title | Representations of Time Expressions for Temporal Relation Extraction with Convolutional Neural Networks |
| Authors | Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard, Guergana Savova |
| Abstract | Token sequences are often used as the input for Convolutional Neural Networks (CNNs) in natural language processing. However, they might not be an ideal representation for time expressions, which are long, highly varied, and semantically complex. We describe a method for representing time expressions with single pseudo-tokens for CNNs. With this method, we establish a new state-of-the-art result for a clinical temporal relation extraction task. |
| Tasks | Relation Extraction, Semantic Parsing, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2341/ |
| https://www.aclweb.org/anthology/W17-2341 | |
| PWC | https://paperswithcode.com/paper/representations-of-time-expressions-for |
| Repo | |
| Framework | |
Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables
| Title | Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables |
| Authors | Bryant Chen, Daniel Kumor, Elias Bareinboim |
| Abstract | We developed a novel approach to identification and model testing in linear structural equation models (SEMs) based on auxiliary variables (AVs), which generalizes a widely-used family of methods known as instrumental variables. The identification problem is concerned with the conditions under which causal parameters can be uniquely estimated from an observational, non-causal covariance matrix. In this paper, we provide an algorithm for the identification of causal parameters in linear structural models that subsumes previous state-of-the-art methods. In other words, our algorithm identifies strictly more coefficients and models than methods previously known in the literature. Our algorithm builds on a graph-theoretic characterization of conditional independence relations between auxiliary and model variables, which is developed in this paper. Further, we leverage this new characterization for allowing identification when limited experimental data or new substantive knowledge about the domain is available. Lastly, we develop a new procedure for model testing using AVs. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=783 |
| http://proceedings.mlr.press/v70/chen17f/chen17f.pdf | |
| PWC | https://paperswithcode.com/paper/identification-and-model-testing-in-linear |
| Repo | |
| Framework | |
A Fast and Lightweight System for Multilingual Dependency Parsing
| Title | A Fast and Lightweight System for Multilingual Dependency Parsing |
| Authors | Tao Ji, Yuanbin Wu, Man Lan |
| Abstract | We present a multilingual dependency parser with a bidirectional-LSTM (BiLSTM) feature extractor and a multi-layer perceptron (MLP) classifier. We trained our transition-based projective parser in UD version 2.0 datasets without any additional data. The parser is fast, lightweight and effective on big treebanks. In the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, the official results show that the macro-averaged LAS F1 score of our system Mengest is 61.33{%}. |
| Tasks | Dependency Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3025/ |
| https://www.aclweb.org/anthology/K17-3025 | |
| PWC | https://paperswithcode.com/paper/a-fast-and-lightweight-system-for |
| Repo | |
| Framework | |
Automatically Generating Rhythmic Verse with Neural Networks
| Title | Automatically Generating Rhythmic Verse with Neural Networks |
| Authors | Jack Hopkins, Douwe Kiela |
| Abstract | We propose two novel methodologies for the automatic generation of rhythmic poetry in a variety of forms. The first approach uses a neural language model trained on a phonetic encoding to learn an implicit representation of both the form and content of English poetry. This model can effectively learn common poetic devices such as rhyme, rhythm and alliteration. The second approach considers poetry generation as a constraint satisfaction problem where a generative neural language model is tasked with learning a representation of content, and a discriminative weighted finite state machine constrains it on the basis of form. By manipulating the constraints of the latter model, we can generate coherent poetry with arbitrary forms and themes. A large-scale extrinsic evaluation demonstrated that participants consider machine-generated poems to be written by humans 54{%} of the time. In addition, participants rated a machine-generated poem to be the best amongst all evaluated. |
| Tasks | Language Modelling, Text Generation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1016/ |
| https://www.aclweb.org/anthology/P17-1016 | |
| PWC | https://paperswithcode.com/paper/automatically-generating-rhythmic-verse-with |
| Repo | |
| Framework | |
PJIIT’s systems for WMT 2017 Conference
| Title | PJIIT’s systems for WMT 2017 Conference |
| Authors | Krzysztof Wolk, Krzysztof Marasek |
| Abstract | |
| Tasks | Domain Adaptation, Language Modelling, Machine Translation, Transliteration, Word Alignment |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4743/ |
| https://www.aclweb.org/anthology/W17-4743 | |
| PWC | https://paperswithcode.com/paper/pjiitas-systems-for-wmt-2017-conference |
| Repo | |
| Framework | |
Text-based Speaker Identification on Multiparty Dialogues Using Multi-document Convolutional Neural Networks
| Title | Text-based Speaker Identification on Multiparty Dialogues Using Multi-document Convolutional Neural Networks |
| Authors | Kaixin Ma, Catherine Xiao, Jinho D. Choi |
| Abstract | |
| Tasks | Speaker Identification, Speech Recognition, Structured Prediction |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3009/ |
| https://www.aclweb.org/anthology/P17-3009 | |
| PWC | https://paperswithcode.com/paper/text-based-speaker-identification-on |
| Repo | |
| Framework | |
Dialog for Language to Code
| Title | Dialog for Language to Code |
| Authors | Shobhit Chaurasia, Raymond J. Mooney |
| Abstract | Generating computer code from natural language descriptions has been a long-standing problem. Prior work in this domain has restricted itself to generating code in one shot from a single description. To overcome this limitation, we propose a system that can engage users in a dialog to clarify their intent until it has all the information to produce correct code. To evaluate the efficacy of dialog in code generation, we focus on synthesizing conditional statements in the form of IFTTT recipes. |
| Tasks | Code Generation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2030/ |
| https://www.aclweb.org/anthology/I17-2030 | |
| PWC | https://paperswithcode.com/paper/dialog-for-language-to-code |
| Repo | |
| Framework | |
Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization
| Title | Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization |
| Authors | Pan Xu, Jian Ma, Quanquan Gu |
| Abstract | We study the estimation of the latent variable Gaussian graphical model (LVGGM), where the precision matrix is the superposition of a sparse matrix and a low-rank matrix. In order to speed up the estimation of the sparse plus low-rank components, we propose a sparsity constrained maximum likelihood estimator based on matrix factorization and an efficient alternating gradient descent algorithm with hard thresholding to solve it. Our algorithm is orders of magnitude faster than the convex relaxation based methods for LVGGM. In addition, we prove that our algorithm is guaranteed to linearly converge to the unknown sparse and low-rank components up to the optimal statistical precision. Experiments on both synthetic and genomic data demonstrate the superiority of our algorithm over the state-of-the-art algorithms and corroborate our theory. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6789-speeding-up-latent-variable-gaussian-graphical-model-estimation-via-nonconvex-optimization |
| http://papers.nips.cc/paper/6789-speeding-up-latent-variable-gaussian-graphical-model-estimation-via-nonconvex-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/speeding-up-latent-variable-gaussian-1 |
| Repo | |
| Framework | |
zNLP: Identifying Parallel Sentences in Chinese-English Comparable Corpora
| Title | zNLP: Identifying Parallel Sentences in Chinese-English Comparable Corpora |
| Authors | Zheng Zhang, Pierre Zweigenbaum |
| Abstract | This paper describes the zNLP system for the BUCC 2017 shared task. Our system identifies parallel sentence pairs in Chinese-English comparable corpora by translating word-by-word Chinese sentences into English, using the search engine Solr to select near-parallel sentences and then by using an SVM classifier to identify true parallel sentences from the previous results. It obtains an F1-score of 45{%} (resp. 32{%}) on the test (training) set. |
| Tasks | Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2510/ |
| https://www.aclweb.org/anthology/W17-2510 | |
| PWC | https://paperswithcode.com/paper/znlp-identifying-parallel-sentences-in |
| Repo | |
| Framework | |
Dimensions of Abusive Language on Twitter
| Title | Dimensions of Abusive Language on Twitter |
| Authors | Isobelle Clarke, Jack Grieve |
| Abstract | In this paper, we use a new categorical form of multidimensional register analysis to identify the main dimensions of functional linguistic variation in a corpus of abusive language, consisting of racist and sexist Tweets. By analysing the use of a wide variety of parts-of-speech and grammatical constructions, as well as various features related to Twitter and computer-mediated communication, we discover three dimensions of linguistic variation in this corpus, which we interpret as being related to the degree of interactive, antagonistic and attitudinal language exhibited by individual Tweets. We then demonstrate that there is a significant functional difference between racist and sexist Tweets, with sexists Tweets tending to be more interactive and attitudinal than racist Tweets. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3001/ |
| https://www.aclweb.org/anthology/W17-3001 | |
| PWC | https://paperswithcode.com/paper/dimensions-of-abusive-language-on-twitter |
| Repo | |
| Framework | |
