Paper Group NAWR 16
Findings of the Third Shared Task on Multimodal Machine Translation. Crowdsourcing StoryLines: Harnessing the Crowd for Causal Relation Annotation. Legal Judgment Prediction via Topological Learning. Auto-Encoding Dictionary Definitions into Consistent Word Embeddings. SeriesNet:A Generative Time Series Forecasting Model. Using active learning to e …
Findings of the Third Shared Task on Multimodal Machine Translation
| Title | Findings of the Third Shared Task on Multimodal Machine Translation |
| Authors | Lo{"\i}c Barrault, Fethi Bougares, Lucia Specia, Chiraag Lala, Desmond Elliott, Stella Frank |
| Abstract | We present the results from the third shared task on multimodal machine translation. In this task a source sentence in English is supplemented by an image and participating systems are required to generate a translation for such a sentence into German, French or Czech. The image can be used in addition to (or instead of) the source sentence. This year the task was extended with a third target language (Czech) and a new test set. In addition, a variant of this task was introduced with its own test set where the source sentence is given in multiple languages: English, French and German, and participating systems are required to generate a translation in Czech. Seven teams submitted 45 different systems to the two variants of the task. Compared to last year, the performance of the multimodal submissions improved, but text-only systems remain competitive. |
| Tasks | Machine Translation, Multimodal Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6402/ |
| https://www.aclweb.org/anthology/W18-6402 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-third-shared-task-on |
| Repo | https://github.com/multi30k/dataset |
| Framework | none |
Crowdsourcing StoryLines: Harnessing the Crowd for Causal Relation Annotation
| Title | Crowdsourcing StoryLines: Harnessing the Crowd for Causal Relation Annotation |
| Authors | Tommaso Caselli, Oana Inel |
| Abstract | This paper describes a crowdsourcing experiment on the annotation of plot-like structures in English news articles. CrowdThruth methodology and metrics have been applied to select valid annotations from the crowd. We further run an in-depth analysis of the annotated data by comparing them with available expert data. Our results show a valuable use of crowdsourcing annotations for such complex semantic tasks, and suggest a new annotation approach which combine crowd and experts. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4306/ |
| https://www.aclweb.org/anthology/W18-4306 | |
| PWC | https://paperswithcode.com/paper/crowdsourcing-storylines-harnessing-the-crowd |
| Repo | https://github.com/CrowdTruth/Crowdsourcing-StoryLines |
| Framework | none |
Legal Judgment Prediction via Topological Learning
| Title | Legal Judgment Prediction via Topological Learning |
| Authors | Haoxi Zhong, Zhipeng Guo, Cunchao Tu, Chaojun Xiao, Zhiyuan Liu, Maosong Sun |
| Abstract | Legal Judgment Prediction (LJP) aims to predict the judgment result based on the facts of a case and becomes a promising application of artificial intelligence techniques in the legal field. In real-world scenarios, legal judgment usually consists of multiple subtasks, such as the decisions of applicable law articles, charges, fines, and the term of penalty. Moreover, there exist topological dependencies among these subtasks. While most existing works only focus on a specific subtask of judgment prediction and ignore the dependencies among subtasks, we formalize the dependencies among subtasks as a Directed Acyclic Graph (DAG) and propose a topological multi-task learning framework, TopJudge, which incorporates multiple subtasks and DAG dependencies into judgment prediction. We conduct experiments on several real-world large-scale datasets of criminal cases in the civil law system. Experimental results show that our model achieves consistent and significant improvements over baselines on all judgment prediction tasks. The source code can be obtained from \url{https://github.com/thunlp/TopJudge}. |
| Tasks | Multi-Task Learning, Text Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1390/ |
| https://www.aclweb.org/anthology/D18-1390 | |
| PWC | https://paperswithcode.com/paper/legal-judgment-prediction-via-topological |
| Repo | https://github.com/thunlp/TopJudge |
| Framework | pytorch |
Auto-Encoding Dictionary Definitions into Consistent Word Embeddings
| Title | Auto-Encoding Dictionary Definitions into Consistent Word Embeddings |
| Authors | Tom Bosc, Pascal Vincent |
| Abstract | Monolingual dictionaries are widespread and semantically rich resources. This paper presents a simple model that learns to compute word embeddings by processing dictionary definitions and trying to reconstruct them. It exploits the inherent recursivity of dictionaries by encouraging consistency between the representations it uses as inputs and the representations it produces as outputs. The resulting embeddings are shown to capture semantic similarity better than regular distributional methods and other dictionary-based methods. In addition, our method shows strong performance when trained exclusively on dictionary data and generalizes in one shot. |
| Tasks | Document Classification, Machine Translation, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1181/ |
| https://www.aclweb.org/anthology/D18-1181 | |
| PWC | https://paperswithcode.com/paper/auto-encoding-dictionary-definitions-into |
| Repo | https://github.com/tombosc/cpae |
| Framework | none |
SeriesNet:A Generative Time Series Forecasting Model
| Title | SeriesNet:A Generative Time Series Forecasting Model |
| Authors | Zhipeng Shen, Yuanming Zhang ∗, Jiawei Lu, Jun Xu, Gang Xiao |
| Abstract | Time series forecasting is emerging as one of the most important branches of big data analysis. However, traditional time series forecasting models can not effectively extract good enough sequence data features and often result in poor forecasting accuracy. In this paper, a novel time series forecasting model, named SeriesNet, which can fully learn features of time series data in different interval lengths. The SeriesNet consists of two networks. The LSTM network aims to learn holistic features and to reduce dimensionality of multi-conditional data, and the dilated causal convolution network aims to learn different time interval. This model can learn multi-range and multi-level features from time series data, and has higher predictive accuracy compared those models using fixed time intervals. Moreover, this model adopts residual learning and batch normalization to improve generalization. Experimental results show our model has higher forecasting accuracy and has greater stableness on several typical time series data sets. |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2018-08-23 |
| URL | https://www.researchgate.net/deref/http%3A%2F%2Fdx.doi.org%2F10.1109%2FIJCNN.2018.8489522 |
| https://www.researchgate.net/deref/http%3A%2F%2Fdx.doi.org%2F10.1109%2FIJCNN.2018.8489522 | |
| PWC | https://paperswithcode.com/paper/seriesneta-generative-time-series-forecasting |
| Repo | https://github.com/kristpapadopoulos/seriesnet |
| Framework | none |
Using active learning to expand training data for implicit discourse relation recognition
| Title | Using active learning to expand training data for implicit discourse relation recognition |
| Authors | Yang Xu, Yu Hong, Huibin Ruan, Jianmin Yao, Min Zhang, Guodong Zhou |
| Abstract | We tackle discourse-level relation recognition, a problem of determining semantic relations between text spans. Implicit relation recognition is challenging due to the lack of explicit relational clues. The increasingly popular neural network techniques have been proven effective for semantic encoding, whereby widely employed to boost semantic relation discrimination. However, learning to predict semantic relations at a deep level heavily relies on a great deal of training data, but the scale of the publicly available data in this field is limited. In this paper, we follow Rutherford and Xue (2015) to expand the training data set using the corpus of explicitly-related arguments, by arbitrarily dropping the overtly presented discourse connectives. On the basis, we carry out an experiment of sampling, in which a simple active learning approach is used, so as to take the informative instances for data expansion. The goal is to verify whether the selective use of external data not only reduces the time consumption of retraining but also ensures a better system performance. Using the expanded training data, we retrain a convolutional neural network (CNN) based classifer which is a simplified version of Qin et al. (2016){'}s stacking gated relation recognizer. Experimental results show that expanding the training set with small-scale carefully-selected external data yields substantial performance gain, with the improvements of about 4{%} for accuracy and 3.6{%} for F-score. This allows a weak classifier to achieve a comparable performance against the state-of-the-art systems. |
| Tasks | Active Learning, Relation Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1079/ |
| https://www.aclweb.org/anthology/D18-1079 | |
| PWC | https://paperswithcode.com/paper/using-active-learning-to-expand-training-data |
| Repo | https://github.com/AndreaXu0401/ALIDRC |
| Framework | tf |
Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior
| Title | Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior |
| Authors | Sijia Cai, Wangmeng Zuo, Larry S. Davis, Lei Zhang |
| Abstract | Video summarization is a challenging under-constrained problem because the underlying summary of a single video strongly depends on users’ subjective understandings. Data-driven approaches, such as deep neural networks, can deal with the ambiguity inherent in this task to some extent, but it is extremely expensive to acquire the temporal annotations of a large-scale video dataset. To leverage the plentiful web-crawled videos to improve the performance of video summarization, we present a generative modelling framework to learn the latent semantic video representations to bridge the benchmark data and web data. Specifically, our framework couples two important components: a variational autoencoder for learning the latent semantics from web videos, and an encoder-attention-decoder for saliency estimation of raw video and summary generation. A loss term to learn the semantic matching between the generated summaries and web videos is presented, and the overall framework is further formulated into a unified conditional variational encoder-decoder, called variational encoder-summarizer-decoder (VESD). Experiments conducted on the challenging datasets CoSum and TVSum demonstrate the superior performance of the proposed VESD to existing state-of-the-art methods. The source code of this work can be found at https://github.com/cssjcai/vesd. |
| Tasks | Saliency Prediction, Supervised Video Summarization, Video Summarization |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Sijia_Cai_Weakly-supervised_Video_Summarization_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Sijia_Cai_Weakly-supervised_Video_Summarization_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-video-summarization-using |
| Repo | https://github.com/cssjcai/vesd |
| Framework | none |
BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization
| Title | BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization |
| Authors | Yue Wu, Wael Abd-Almageed, Prem Natarajan |
| Abstract | We introduce a novel deep neural architecture for image copy-move forgery detection (CMFD), code-named BusterNet. Unlike previous eorts, BusterNet is a pure, end-to-end trainable, deep neural network solution. It features a two-branch architecture followed by a fu- sion module. The two branches localize potential manipulation regions (by looking for visual artifacts) and copy-move regions (by assessing vi- sual similarities), respectively. To the best of our knowledge, this is the rst CMFD algorithm with discernibility to localize source/target re- gions.We also propose simple schemes for synthesizing large-scale CMFD samples using out-of-domain datasets, and stage-wise strategies for eec- tive BusterNet training. Our extensive studies demonstrate that Buster- Net outperforms state-of-the-art copy-move detection algorithms by a large margin on the two publicly available datasets, CASIA and CoMo- FoD, and that it is robust against various known attacks. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Rex_Yue_Wu_BusterNet_Detecting_Copy-Move_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Rex_Yue_Wu_BusterNet_Detecting_Copy-Move_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/busternet-detecting-copy-move-image-forgery |
| Repo | https://github.com/isi-vista/BusterNet |
| Framework | tf |
Modular Latent Spaces for Shape Correspondences
| Title | Modular Latent Spaces for Shape Correspondences |
| Authors | Vignesh Ganapathi-Subramanian, Olga Diamanti, Leonidas J. Guibas |
| Abstract | We consider the problem of transporting shape descriptors across shapes in a collection in a modular fashion, in order to establish correspondences between them. A common goal when mapping between multiple shapes is consistency, namely that compositions of maps along a cycle of shapes should be approximately an identity map. Existing attempts to enforce consistency typically require recomputing correspondences whenever a new shape is added to the collection, which can quickly become intractable. Instead, we propose an approach that is fully modular, where the bulk of the computation is done on each shape independently. To achieve this, we use intermediate nonlinear embedding spaces, computed individually on every shape; the embedding functions use ideas from diffusion geometry and capture how different descriptors on the same shape inter‐relate. We then establish linear mappings between the different embedding spaces, via a shared latent space. The introduction of nonlinear embeddings allows for more nuanced correspondences, while the modularity of the construction allows for parallelizable calculation and efficient addition of new shapes. We compare the performance of our framework to standard functional correspondence techniques and showcase the use of this framework to simple interpolation and extrapolation tasks. |
| Tasks | |
| Published | 2018-06-30 |
| URL | https://onlinelibrary.wiley.com/doi/full/10.1111/cgf.13502 |
| https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.13502 | |
| PWC | https://paperswithcode.com/paper/modular-latent-spaces-for-shape |
| Repo | https://github.com/vigansub/Modular-Latent-Spaces |
| Framework | none |
TALEN: Tool for Annotation of Low-resource ENtities
| Title | TALEN: Tool for Annotation of Low-resource ENtities |
| Authors | Stephen Mayhew, Dan Roth |
| Abstract | We present a new web-based interface, TALEN, designed for named entity annotation in low-resource settings where the annotators do not speak the language. To address this non-traditional scenario, TALEN includes such features as in-place lexicon integration, TF-IDF token statistics, Internet search, and entity propagation, all implemented so as to make this difficult task efficient and frictionless. We conduct a small user study to compare against a popular annotation tool, showing that TALEN achieves higher precision and recall against ground-truth annotations, and that users strongly prefer it over the alternative. TALEN is available at: \url{github.com/CogComp/talen}. |
| Tasks | Named Entity Recognition |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-4014/ |
| https://www.aclweb.org/anthology/P18-4014 | |
| PWC | https://paperswithcode.com/paper/talen-tool-for-annotation-of-low-resource |
| Repo | https://github.com/CogComp/talen |
| Framework | none |
Enhanced Network Embedding with Text Information
| Title | Enhanced Network Embedding with Text Information |
| Authors | Shuang Yang, Bo Yang |
| Abstract | Network embedding aims at learning the low-dimensional and continuous vector representation for each node in networks, which is useful in many real applications. While most existing network embedding methods only focus on the network structure, the rich text information associated with nodes, which is often closely related to network structure, is widely neglected. Thus, how to effectively incorporate text information into network embedding is a problem worth studying. To solve the problem, we propose a Text Enhanced Network Embedding (TENE) method under the framework of non-negative matrix factorization to integrate network structure and text information together. We explore the consistent relationship between node representations and text cluster structure to make the network embedding more informative and discriminative. TENE learns the representations of nodes under the guidance of both proximity matrix which captures the network structure and text cluster membership matrix derived from clustering for text information. We evaluate the quality of network embedding on the task of multi-class classification of nodes. Experimental results on all three real-world datasets show the superior performance of TENE compared with baselines. |
| Tasks | Network Embedding, Node Classification |
| Published | 2018-11-29 |
| URL | https://ieeexplore.ieee.org/document/8545577 |
| https://github.com/benedekrozemberczki/TENE/blob/master/tene_paper.pdf | |
| PWC | https://paperswithcode.com/paper/enhanced-network-embedding-with-text |
| Repo | https://github.com/benedekrozemberczki/karateclub |
| Framework | none |
FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchronized GANs
| Title | FrankenGAN: Guided Detail Synthesis for Building Mass-Models Using Style-Synchronized GANs |
| Authors | Tom Kelly, Paul Guerrero, Anthony Steed, Peter Wonka, Niloy J. Mitra |
| Abstract | Coarse building mass models are now routinely generated at scales ranging from individual buildings through to whole cities. For example, they can be abstracted from raw measurements, generated procedurally, or created manually. However, these models typically lack any meaningful semantic or texture details, making them unsuitable for direct display. We introduce the problem of automatically and realistically decorating such models by adding semantically consistent geometric details and textures. Building on the recent success of generative adversarial networks (GANs), we propose FrankenGAN, a cascade of GANs to create plausible details across multiple scales over large neighborhoods. The various GANs are synchronized to produce consistent style distributions over buildings and neighborhoods. We provide the user with direct control over the variability of the output. We allow her to interactively specify style via images and manipulate style-adapted sliders to control style variability. We demonstrate our system on several large-scale examples. The generated outputs are qualitatively evaluated via a set of user studies and are found to be realistic, semantically-plausible, and style-consistent. |
| Tasks | Texture Synthesis |
| Published | 2018-11-01 |
| URL | https://geometry.cs.ucl.ac.uk/projects/2018/frankengan/ |
| https://arxiv.org/pdf/1806.07179 | |
| PWC | https://paperswithcode.com/paper/frankengan-guided-detail-synthesis-for-1 |
| Repo | https://github.com/twak/chordatlas |
| Framework | none |
Clubmark: a Parallel Isolation Framework for Benchmarking and Profiling Clustering Algorithms on NUMA Architectures
| Title | Clubmark: a Parallel Isolation Framework for Benchmarking and Profiling Clustering Algorithms on NUMA Architectures |
| Authors | Artem Lutov, Mourad Khayati, Philippe Cudré-Mauroux |
| Abstract | There is a great diversity of clustering and community detection algorithms, which are key components of many data analysis and exploration systems. To the best of our knowledge, however, there does not exist yet any uniform benchmarking framework, which is publicly available and suitable for the parallel benchmarking of diverse clustering algorithms on a wide range of synthetic and real-world datasets. In this paper, we introduce Clubmark, a new extensible framework that aims to fill this gap by providing a parallel isolation benchmarking platform for clustering algorithms and their evaluation on NUMA servers. Clubmark allows for fine-grained control over various execution variables (timeouts, memory consumption, CPU affinity and cache policy) and supports the evaluation of a wide range of clustering algorithms including multi-level, hierarchical and overlapping clustering techniques on both weighted and unweighted input networks with built-in evaluation of several extrinsic and intrinsic measures. Our framework is open-source and provides a consistent and systematic way to execute, evaluate and profile clustering techniques considering a number of aspects that are often missing in state-of-the-art frameworks and benchmarking systems. |
| Tasks | Clustering Algorithms Evaluation, Community Detection |
| Published | 2018-11-17 |
| URL | https://arxiv.org/abs/1902.00475 |
| https://arxiv.org/pdf/1902.00475 | |
| PWC | https://paperswithcode.com/paper/clubmark-a-parallel-isolation-framework-for |
| Repo | https://github.com/eXascaleInfolab/clubmark |
| Framework | none |
Few-Shot Charge Prediction with Discriminative Legal Attributes
| Title | Few-Shot Charge Prediction with Discriminative Legal Attributes |
| Authors | Zikun Hu, Xiang Li, Cunchao Tu, Zhiyuan Liu, Maosong Sun |
| Abstract | Automatic charge prediction aims to predict the final charges according to the fact descriptions in criminal cases and plays a crucial role in legal assistant systems. Existing works on charge prediction perform adequately on those high-frequency charges but are not yet capable of predicting few-shot charges with limited cases. Moreover, these exist many confusing charge pairs, whose fact descriptions are fairly similar to each other. To address these issues, we introduce several discriminative attributes of charges as the internal mapping between fact descriptions and charges. These attributes provide additional information for few-shot charges, as well as effective signals for distinguishing confusing charges. More specifically, we propose an attribute-attentive charge prediction model to infer the attributes and charges simultaneously. Experimental results on real-work datasets demonstrate that our proposed model achieves significant and consistent improvements than other state-of-the-art baselines. Specifically, our model outperforms other baselines by more than 50{%} in the few-shot scenario. Our codes and datasets can be obtained from https://github.com/thunlp/attribute{_}charge. |
| Tasks | Text Classification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1041/ |
| https://www.aclweb.org/anthology/C18-1041 | |
| PWC | https://paperswithcode.com/paper/few-shot-charge-prediction-with |
| Repo | https://github.com/thunlp/attribute_charge |
| Framework | tf |
Towards a unified framework for bilingual terminology extraction of single-word and multi-word terms
| Title | Towards a unified framework for bilingual terminology extraction of single-word and multi-word terms |
| Authors | Jingshu Liu, Emmanuel Morin, Pe{~n}a Saldarriaga |
| Abstract | Extracting a bilingual terminology for multi-word terms from comparable corpora has not been widely researched. In this work we propose a unified framework for aligning bilingual terms independently of the term lengths. We also introduce some enhancements to the context-based and the neural network based approaches. Our experiments show the effectiveness of our enhancements of previous works and the system can be adapted in specialized domains. |
| Tasks | Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1242/ |
| https://www.aclweb.org/anthology/C18-1242 | |
| PWC | https://paperswithcode.com/paper/towards-a-unified-framework-for-bilingual |
| Repo | https://github.com/Dictanova/term-eval |
| Framework | none |
