Paper Group NANR 113
Fast Query Expansion on an Accounting Corpus using Sub-Word Embeddings. The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation. Very Large-Scale Lexical Resources to Enhance Chinese and Japanese Machine Translation. Inference in Higher Order MRF-MAP Problems With Small and Large Cliques. Parallel Form …
Fast Query Expansion on an Accounting Corpus using Sub-Word Embeddings
| Title | Fast Query Expansion on an Accounting Corpus using Sub-Word Embeddings |
| Authors | Hrishikesh Ganu, Viswa Datha P. |
| Abstract | We present early results from a system under development which uses sub-word embeddings for query expansion in presence of mis-spelled words and other aberrations. We work for a company which creates accounting software and the end goal is to improve customer experience when they search for help on our {``}Customer Care{''} portal. Our customers use colloquial language, non-standard acronyms and sometimes mis-spell words when they use our Search portal or interact over other channels. However, our Knowledge Base has curated content which leverages technical terms and is in language which is quite formal. This results in the answer not being retrieved even though the answer might actually be present in the documentation (as assessed by a human). We address this problem by creating equivalence classes of words with similar meanings (with the additional property that the mappings to these equivalence classes are robust to mis-spellings) using sub-word embeddings and then use them to fine tune an Elasticsearch index to improve recall. We demonstrate through an end-end system that using sub-word embeddings leads to a significant lift in correct answers retrieved for an accounting corpus available in the public domain. | |
| Tasks | Information Retrieval, Lemmatization, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1208/ |
| https://www.aclweb.org/anthology/W18-1208 | |
| PWC | https://paperswithcode.com/paper/fast-query-expansion-on-an-accounting-corpus |
| Repo | |
| Framework | |
The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation
| Title | The Best of Both Worlds: Combining CNNs and Geometric Constraints for Hierarchical Motion Segmentation |
| Authors | Pia Bideau, Aruni RoyChowdhury, Rakesh R. Menon, Erik Learned-Miller |
| Abstract | Traditional methods of motion segmentation use powerful geometric constraints to understand motion, but fail to leverage the semantics of high-level image understanding. Modern CNN methods of motion analysis, on the other hand, excel at identifying well-known structures, but may not precisely characterize well-known geometric constraints. In this work, we build a new statistical model of rigid motion flow based on classical perspective projection constraints. We then combine piecewise rigid motions into complex deformable and articulated objects, guided by semantic segmentation from CNNs and a second ``object-level” statistical model. This combination of classical geometric knowledge combined with the pattern recognition abilities of CNNs yields excellent performance on a wide range of motion segmentation benchmarks, from complex geometric scenes to camouflaged animals. | |
| Tasks | Motion Segmentation, Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Bideau_The_Best_of_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Bideau_The_Best_of_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/the-best-of-both-worlds-combining-cnns-and |
| Repo | |
| Framework | |
Very Large-Scale Lexical Resources to Enhance Chinese and Japanese Machine Translation
| Title | Very Large-Scale Lexical Resources to Enhance Chinese and Japanese Machine Translation |
| Authors | Jack Halpern |
| Abstract | |
| Tasks | Lemmatization, Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1137/ |
| https://www.aclweb.org/anthology/L18-1137 | |
| PWC | https://paperswithcode.com/paper/very-large-scale-lexical-resources-to-enhance |
| Repo | |
| Framework | |
Inference in Higher Order MRF-MAP Problems With Small and Large Cliques
| Title | Inference in Higher Order MRF-MAP Problems With Small and Large Cliques |
| Authors | Ishant Shanu, Chetan Arora, S.N. Maheshwari |
| Abstract | Higher Order MRF-MAP formulation has been a popular technique for solving many problems in computer vision. Inference in a general MRF-MAP problem is NP Hard, but can be performed in polynomial time for the special case when potential functions are submodular. Two popular combinatorial approaches for solving such formulations are flow based and polyhedral approaches. Flow based approaches work well with small cliques and in that mode can handle problems with millions of variables. Polyhedral approaches can handle large cliques but in small numbers. We show in this paper that the variables in these seemingly disparate techniques can be mapped to each other. This allows us to combine the two styles in a joint framework exploiting the strength of both of them. Using the proposed joint framework, we are able to perform tractable inference in MRF-MAP problems with millions of variables and a mix of small and large cliques, a formulation which can not be solved by either of the two styles individually. We show applicability of this hybrid framework on object segmentation problem as an example of a situation where quality of results is significantly better than systems which are based only on the use of small or large cliques. |
| Tasks | Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Shanu_Inference_in_Higher_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Shanu_Inference_in_Higher_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/inference-in-higher-order-mrf-map-problems |
| Repo | |
| Framework | |
Parallel Forms in Estonian Finite State Morphology
| Title | Parallel Forms in Estonian Finite State Morphology |
| Authors | Heiki-Jaan Kaalep |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0212/ |
| https://www.aclweb.org/anthology/W18-0212 | |
| PWC | https://paperswithcode.com/paper/parallel-forms-in-estonian-finite-state |
| Repo | |
| Framework | |
ASR for Documenting Acutely Under-Resourced Indigenous Languages
| Title | ASR for Documenting Acutely Under-Resourced Indigenous Languages |
| Authors | Robbie Jimerson, Emily Prud{'}hommeaux |
| Abstract | |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1657/ |
| https://www.aclweb.org/anthology/L18-1657 | |
| PWC | https://paperswithcode.com/paper/asr-for-documenting-acutely-under-resourced |
| Repo | |
| Framework | |
An SLA Corpus Annotated with Pedagogically Relevant Grammatical Structures
| Title | An SLA Corpus Annotated with Pedagogically Relevant Grammatical Structures |
| Authors | Leonardo Zilio, Rodrigo Wilkens, C{'e}drick Fairon |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1650/ |
| https://www.aclweb.org/anthology/L18-1650 | |
| PWC | https://paperswithcode.com/paper/an-sla-corpus-annotated-with-pedagogically |
| Repo | |
| Framework | |
Improving Crowdsourcing-Based Annotation of Japanese Discourse Relations
| Title | Improving Crowdsourcing-Based Annotation of Japanese Discourse Relations |
| Authors | Yudai Kishimoto, Shinnosuke Sawada, Yugo Murawaki, Daisuke Kawahara, Sadao Kurohashi |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1637/ |
| https://www.aclweb.org/anthology/L18-1637 | |
| PWC | https://paperswithcode.com/paper/improving-crowdsourcing-based-annotation-of |
| Repo | |
| Framework | |
Point-to-Point Regression PointNet for 3D Hand Pose Estimation
| Title | Point-to-Point Regression PointNet for 3D Hand Pose Estimation |
| Authors | Liuhao Ge, Zhou Ren, Junsong Yuan |
| Abstract | Convolutional Neural Networks (CNNs)-based methods for 3D hand pose estimation with depth cameras usually take 2D depth images as input and directly regress holistic 3D hand pose. Different from these methods, our proposed Point-to-Point Regression PointNet directly takes the 3D point cloud as input and outputs point-wise estimations, i.e., heat-maps and unit vector fields on the point cloud, representing the closeness and direction from every point in the point cloud to the hand joint. The point-wise estimations are used to infer 3D joint locations with weighted fusion. To better capture 3D spatial information in the point cloud, we apply a stacked network architecture for PointNet with intermediate supervision, which is trained end-to-end. Experiments show that our method can achieve outstanding results when compared with state-of-the-art methods on three challenging hand pose datasets. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Liuhao_Ge_Point-to-Point_Regression_PointNet_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Liuhao_Ge_Point-to-Point_Regression_PointNet_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/point-to-point-regression-pointnet-for-3d |
| Repo | |
| Framework | |
Not that much power: Linguistic alignment is influenced more by low-level linguistic features rather than social power
| Title | Not that much power: Linguistic alignment is influenced more by low-level linguistic features rather than social power |
| Authors | Yang Xu, Jeremy Cole, David Reitter |
| Abstract | Linguistic alignment between dialogue partners has been claimed to be affected by their relative social power. A common finding has been that interlocutors of higher power tend to receive more alignment than those of lower power. However, these studies overlook some low-level linguistic features that can also affect alignment, which casts doubts on these findings. This work characterizes the effect of power on alignment with logistic regression models in two datasets, finding that the effect vanishes or is reversed after controlling for low-level features such as utterance length. Thus, linguistic alignment is explained better by low-level features than by social power. We argue that a wider range of factors, especially cognitive factors, need to be taken into account for future studies on observational data when social factors of language use are in question. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1056/ |
| https://www.aclweb.org/anthology/P18-1056 | |
| PWC | https://paperswithcode.com/paper/not-that-much-power-linguistic-alignment-is |
| Repo | |
| Framework | |
Learning Data Terms for Non-blind Deblurring
| Title | Learning Data Terms for Non-blind Deblurring |
| Authors | Jiangxin Dong, Jinshan Pan, Deqing Sun, Zhixun Su, Ming-Hsuan Yang |
| Abstract | Existing deblurring methods mainly focus on developing effective image priors and assume that blurred images contain insignificant amounts of noise. However, state-of-the-art deblurring methods do not perform well on real-world images degraded with significant noise or outliers. To address these issues, we show that it is critical to learn data fitting terms beyond the commonly used L1 or L2 norm. We propose a simple and effective discriminative framework to learn data terms that can adaptively handle blurred images in the presence of severe noise and outliers. Instead of learning the distribution of the data fitting errors, we directly learn the associated shrinkage function for the data term using a cascaded architecture, which is more flexible and efficient. Our analysis shows that the shrinkage functions learned at the intermediate stages can effectively suppress noise and preserve image structures. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods. |
| Tasks | Deblurring |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jiangxin_Dong_Learning_Data_Terms_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Jiangxin_Dong_Learning_Data_Terms_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-data-terms-for-non-blind-deblurring |
| Repo | |
| Framework | |
Scientific Discovery as Link Prediction in Influence and Citation Graphs
| Title | Scientific Discovery as Link Prediction in Influence and Citation Graphs |
| Authors | Fan Luo, Marco A. Valenzuela-Esc{'a}rcega, Gus Hahn-Powell, Mihai Surdeanu |
| Abstract | We introduce a machine learning approach for the identification of {}white spaces{''} in scientific knowledge. Our approach addresses this task as link prediction over a graph that contains over 2M influence statements such as {}CTCF activates FOXA1{''}, which were automatically extracted using open-domain machine reading. We model this prediction task using graph-based features extracted from the above influence graph, as well as from a citation graph that captures scientific communities. We evaluated the proposed approach through backtesting. Although the data is heavily unbalanced (50 times more negative examples than positives), our approach predicts which influence links will be discovered in the {``}near future{''} with a F1 score of 27 points, and a mean average precision of 68{%}. | |
| Tasks | Link Prediction, Reading Comprehension |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1701/ |
| https://www.aclweb.org/anthology/W18-1701 | |
| PWC | https://paperswithcode.com/paper/scientific-discovery-as-link-prediction-in |
| Repo | |
| Framework | |
Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues
| Title | Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues |
| Authors | Soumendu Sundar Mukherjee, Purnamrita Sarkar, Y. X. Rachel Wang, Bowei Yan |
| Abstract | Variational approximation has been widely used in large-scale Bayesian inference recently, the simplest kind of which involves imposing a mean field assumption to approximate complicated latent structures. Despite the computational scalability of mean field, theoretical studies of its loss function surface and the convergence behavior of iterative updates for optimizing the loss are far from complete. In this paper, we focus on the problem of community detection for a simple two-class Stochastic Blockmodel (SBM). Using batch co-ordinate ascent (BCAVI) for updates, we give a complete characterization of all the critical points and show different convergence behaviors with respect to initializations. When the parameters are known, we show a significant proportion of random initializations will converge to ground truth. On the other hand, when the parameters themselves need to be estimated, a random initialization will converge to an uninformative local optimum. |
| Tasks | Bayesian Inference, Community Detection |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8268-mean-field-for-the-stochastic-blockmodel-optimization-landscape-and-convergence-issues |
| http://papers.nips.cc/paper/8268-mean-field-for-the-stochastic-blockmodel-optimization-landscape-and-convergence-issues.pdf | |
| PWC | https://paperswithcode.com/paper/mean-field-for-the-stochastic-blockmodel |
| Repo | |
| Framework | |
Learning Comment Controversy Prediction in Web Discussions Using Incidentally Supervised Multi-Task CNNs
| Title | Learning Comment Controversy Prediction in Web Discussions Using Incidentally Supervised Multi-Task CNNs |
| Authors | Nils Rethmeier, Marc H{"u}bner, Leonhard Hennig |
| Abstract | Comments on web news contain controversies that manifest as inter-group agreement-conflicts. Tracking such \textit{rapidly evolving controversy} could ease conflict resolution or journalist-user interaction. However, this presupposes controversy online-prediction that scales to diverse domains using incidental supervision signals instead of manual labeling. To more deeply interpret comment-controversy model decisions we frame prediction as binary classification and evaluate baselines and multi-task CNNs that use an auxiliary news-genre-encoder. Finally, we use ablation and interpretability methods to determine the impacts of topic, discourse and sentiment indicators, contextual vs. global word influence, as well as genre-keywords vs. per-genre-controversy keywords {–} to find that the models learn plausible controversy features using only incidentally supervised signals. |
| Tasks | Language Modelling |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6246/ |
| https://www.aclweb.org/anthology/W18-6246 | |
| PWC | https://paperswithcode.com/paper/learning-comment-controversy-prediction-in |
| Repo | |
| Framework | |
Abbreviation Expander - a Web-based System for Easy Reading of Technical Documents
| Title | Abbreviation Expander - a Web-based System for Easy Reading of Technical Documents |
| Authors | Manuel R. Ciosici, Ira Assent |
| Abstract | Abbreviations and acronyms are a part of textual communication in most domains. However, abbreviations are not necessarily defined in documents that employ them. Understanding all abbreviations used in a given document often requires extensive knowledge of the target domain and the ability to disambiguate based on context. This creates considerable entry barriers to newcomers and difficulties in automated document processing. Existing abbreviation expansion systems or tools require substantial technical knowledge for set up or make strong assumptions which limit their use in practice. Here, we present Abbreviation Expander, a system that builds on state of the art methods for identification of abbreviations, acronyms and their definitions and a novel disambiguator for abbreviation expansion in an easily accessible web-based solution. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2001/ |
| https://www.aclweb.org/anthology/C18-2001 | |
| PWC | https://paperswithcode.com/paper/abbreviation-expander-a-web-based-system-for |
| Repo | |
| Framework | |
