Paper Group NANR 107
Automatic identification of unknown names with specific roles. Combining Information-Weighted Sequence Alignment and Sound Correspondence Models for Improved Cognate Detection. Associative Multichannel Autoencoder for Multimodal Word Representation. Neural Procedural Reconstruction for Residential Buildings. Cross-Document, Cross-Language Event Cor …
Automatic identification of unknown names with specific roles
| Title | Automatic identification of unknown names with specific roles |
| Authors | Samia Touileb, Truls Pedersen, Helle Sj{\o}vaag |
| Abstract | Automatically identifying persons in a particular role within a large corpus can be a difficult task, especially if you don{'}t know who you are actually looking for. Resources compiling names of persons can be available, but no exhaustive lists exist. However, such lists usually contain known names that are {}visible{''} in the national public sphere, and tend to ignore the marginal and international ones. In this article we propose a method for automatically generating suggestions of names found in a corpus of Norwegian news articles, and which {}naturally{''} belong to a given initial list of members, and that were not known (compiled in a list) beforehand. The approach is based, in part, on the assumption that surface level syntactic features reveal parts of the underlying semantic content and can help uncover the structure of the language. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4517/ |
| https://www.aclweb.org/anthology/W18-4517 | |
| PWC | https://paperswithcode.com/paper/automatic-identification-of-unknown-names |
| Repo | |
| Framework | |
Combining Information-Weighted Sequence Alignment and Sound Correspondence Models for Improved Cognate Detection
| Title | Combining Information-Weighted Sequence Alignment and Sound Correspondence Models for Improved Cognate Detection |
| Authors | Johannes Dellert |
| Abstract | Methods for automated cognate detection in historical linguistics invariably build on some measure of form similarity which is designed to capture the remaining systematic similarities between cognate word forms after thousands of years of divergence. A wide range of clustering and classification algorithms has been explored for the purpose, whereas possible improvements on the level of pairwise form similarity measures have not been the main focus of research. The approach presented in this paper improves on this core component of cognate detection systems by a novel combination of information weighting, a technique for putting less weight on reoccurring morphological material, with sound correspondence modeling by means of pointwise mutual information. In evaluations on expert cognacy judgments over a subset of the IPA-encoded NorthEuraLex database, the combination of both techniques is shown to lead to considerable improvements in average precision for binary cognate detection, and modest improvements for distance-based cognate clustering. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1264/ |
| https://www.aclweb.org/anthology/C18-1264 | |
| PWC | https://paperswithcode.com/paper/combining-information-weighted-sequence |
| Repo | |
| Framework | |
Associative Multichannel Autoencoder for Multimodal Word Representation
| Title | Associative Multichannel Autoencoder for Multimodal Word Representation |
| Authors | Shaonan Wang, Jiajun Zhang, Chengqing Zong |
| Abstract | In this paper we address the problem of learning multimodal word representations by integrating textual, visual and auditory inputs. Inspired by the re-constructive and associative nature of human memory, we propose a novel associative multichannel autoencoder (AMA). Our model first learns the associations between textual and perceptual modalities, so as to predict the missing perceptual information of concepts. Then the textual and predicted perceptual representations are fused through reconstructing their original and associated embeddings. Using a gating mechanism our model assigns different weights to each modality according to the different concepts. Results on six benchmark concept similarity tests show that the proposed method significantly outperforms strong unimodal baselines and state-of-the-art multimodal models. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1011/ |
| https://www.aclweb.org/anthology/D18-1011 | |
| PWC | https://paperswithcode.com/paper/associative-multichannel-autoencoder-for |
| Repo | |
| Framework | |
Neural Procedural Reconstruction for Residential Buildings
| Title | Neural Procedural Reconstruction for Residential Buildings |
| Authors | Huayi Zeng, Jiaye Wu, Yasutaka Furukawa |
| Abstract | This paper proposes a novel 3D reconstruction approach, dubbed Neural Procedural Reconstruction (NPR), which trains deep neural networks to procedurally apply shape grammar rules and reconstruct CAD-quality models from 3D points. In contrast to Procedural Modeling (PM), which randomly applies shape grammar rules to synthesize 3D models, NPR classifies a rule branch to explore and regresses geometric parameters at each rule application. We demonstrate the proposed system for residential buildings with aerial LiDAR as the input. Our 3D models boast extremely compact geometry and semantically segmented architectural components. Qualitative and quantitative evaluations on hundreds of houses show that our approach robustly generates CAD-quality 3D models from raw sensor data, making significant improvements over the existing state-of-the-art. |
| Tasks | 3D Reconstruction |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Huayi_Zeng_Neural_Procedural_Reconstruction_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Huayi_Zeng_Neural_Procedural_Reconstruction_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/neural-procedural-reconstruction-for |
| Repo | |
| Framework | |
Cross-Document, Cross-Language Event Coreference Annotation Using Event Hoppers
| Title | Cross-Document, Cross-Language Event Coreference Annotation Using Event Hoppers |
| Authors | Zhiyi Song, Ann Bies, Justin Mott, Xuansong Li, Stephanie Strassel, Christopher Caruso |
| Abstract | |
| Tasks | Knowledge Base Population |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1558/ |
| https://www.aclweb.org/anthology/L18-1558 | |
| PWC | https://paperswithcode.com/paper/cross-document-cross-language-event |
| Repo | |
| Framework | |
Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties
| Title | Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties |
| Authors | Yi Zhou, Yingbin Liang |
| Abstract | Due to the success of deep learning to solving a variety of challenging machine learning tasks, there is a rising interest in understanding loss functions for training neural networks from a theoretical aspect. Particularly, the properties of critical points and the landscape around them are of importance to determine the convergence performance of optimization algorithms. In this paper, we provide a necessary and sufficient characterization of the analytical forms for the critical points (as well as global minimizers) of the square loss functions for linear neural networks. We show that the analytical forms of the critical points characterize the values of the corresponding loss functions as well as the necessary and sufficient conditions to achieve global minimum. Furthermore, we exploit the analytical forms of the critical points to characterize the landscape properties for the loss functions of linear neural networks and shallow ReLU networks. One particular conclusion is that: While the loss function of linear networks has no spurious local minimum, the loss function of one-hidden-layer nonlinear networks with ReLU activation function does have local minimum that is not global minimum. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SysEexbRb |
| https://openreview.net/pdf?id=SysEexbRb | |
| PWC | https://paperswithcode.com/paper/critical-points-of-linear-neural-networks |
| Repo | |
| Framework | |
The Use of Text Alignment in Semi-Automatic Error Analysis: Use Case in the Development of the Corpus of the Latvian Language Learners
| Title | The Use of Text Alignment in Semi-Automatic Error Analysis: Use Case in the Development of the Corpus of the Latvian Language Learners |
| Authors | Roberts Dar{\c{g}}is, Ilze Auzi{\c{n}}a, Krist{=\i}ne Lev{=a}ne-Petrova |
| Abstract | |
| Tasks | Language Acquisition, Lemmatization, Morphological Analysis, Part-Of-Speech Tagging, Tokenization, Word Alignment |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1648/ |
| https://www.aclweb.org/anthology/L18-1648 | |
| PWC | https://paperswithcode.com/paper/the-use-of-text-alignment-in-semi-automatic |
| Repo | |
| Framework | |
Sparse Regularized Deep Neural Networks For Efficient Embedded Learning
| Title | Sparse Regularized Deep Neural Networks For Efficient Embedded Learning |
| Authors | Jia Bi |
| Abstract | Deep learning is becoming more widespread in its application due to its power in solving complex classification problems. However, deep learning models often require large memory and energy consumption, which may prevent them from being deployed effectively on embedded platforms, limiting their applications. This work addresses the problem by proposing methods {\em Weight Reduction Quantisation} for compressing the memory footprint of the models, including reducing the number of weights and the number of bits to store each weight. Beside, applying with sparsity-inducing regularization, our work focuses on speeding up stochastic variance reduced gradients (SVRG) optimization on non-convex problem. Our method that mini-batch SVRG with $\ell$1 regularization on non-convex problem has faster and smoother convergence rates than SGD by using adaptive learning rates. Experimental evaluation of our approach uses MNIST and CIFAR-10 datasets on LeNet-300-100 and LeNet-5 models, showing our approach can reduce the memory requirements both in the convolutional and fully connected layers by up to 60$\times$ without affecting their test accuracy. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Sk0pHeZAW |
| https://openreview.net/pdf?id=Sk0pHeZAW | |
| PWC | https://paperswithcode.com/paper/sparse-regularized-deep-neural-networks-for |
| Repo | |
| Framework | |
Syntactical Analysis of the Weaknesses of Sentiment Analyzers
| Title | Syntactical Analysis of the Weaknesses of Sentiment Analyzers |
| Authors | Rohil Verma, Samuel Kim, David Walter |
| Abstract | We carry out a syntactic analysis of two state-of-the-art sentiment analyzers, Google Cloud Natural Language and Stanford CoreNLP, to assess their classification accuracy on sentences with negative polarity items. We were motivated by the absence of studies investigating sentiment analyzer performance on sentences with polarity items, a common construct in human language. Our analysis focuses on two sentential structures: downward entailment and non-monotone quantifiers; and demonstrates weaknesses of Google Natural Language and CoreNLP in capturing polarity item information. We describe the particular syntactic phenomenon that these analyzers fail to understand that any ideal sentiment analyzer must. We also provide a set of 150 test sentences that any ideal sentiment analyzer must be able to understand. |
| Tasks | Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1141/ |
| https://www.aclweb.org/anthology/D18-1141 | |
| PWC | https://paperswithcode.com/paper/syntactical-analysis-of-the-weaknesses-of |
| Repo | |
| Framework | |
Unsupervised Counselor Dialogue Clustering for Positive Emotion Elicitation in Neural Dialogue System
| Title | Unsupervised Counselor Dialogue Clustering for Positive Emotion Elicitation in Neural Dialogue System |
| Authors | Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, Satoshi Nakamura |
| Abstract | Positive emotion elicitation seeks to improve user{'}s emotional state through dialogue system interaction, where a chat-based scenario is layered with an implicit goal to address user{'}s emotional needs. Standard neural dialogue system approaches still fall short in this situation as they tend to generate only short, generic responses. Learning from expert actions is critical, as these potentially differ from standard dialogue acts. In this paper, we propose using a hierarchical neural network for response generation that is conditioned on 1) expert{'}s action, 2) dialogue context, and 3) user emotion, encoded from user input. We construct a corpus of interactions between a counselor and 30 participants following a negative emotional exposure to learn expert actions and responses in a positive emotion elicitation scenario. Instead of relying on the expensive, labor intensive, and often ambiguous human annotations, we unsupervisedly cluster the expert{'}s responses and use the resulting labels to train the network. Our experiments and evaluation show that the proposed approach yields lower perplexity and generates a larger variety of responses. |
| Tasks | Emotion Recognition, Goal-Oriented Dialogue Systems |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5017/ |
| https://www.aclweb.org/anthology/W18-5017 | |
| PWC | https://paperswithcode.com/paper/unsupervised-counselor-dialogue-clustering |
| Repo | |
| Framework | |
EICA Team at SemEval-2018 Task 2: Semantic and Metadata-based Features for Multilingual Emoji Prediction
| Title | EICA Team at SemEval-2018 Task 2: Semantic and Metadata-based Features for Multilingual Emoji Prediction |
| Authors | Yufei Xie, Qingqing Song |
| Abstract | The advent of social media has brought along a novel way of communication where meaning is composed by combining short text messages and visual enhancements, the so-called emojis. We describe our system for participating in SemEval-2018 Task 2 on Multilingual Emoji Prediction. Our approach relies on combining a rich set of various types of features: semantic and metadata. The most important types turned out to be the metadata feature. In subtask 1: Emoji Prediction in English, our primary submission obtain a MAP of 16.45, Precision of 31.557, Recall of 16.771 and Accuracy of 30.992. |
| Tasks | Information Retrieval, Sentiment Analysis, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1065/ |
| https://www.aclweb.org/anthology/S18-1065 | |
| PWC | https://paperswithcode.com/paper/eica-team-at-semeval-2018-task-2-semantic-and |
| Repo | |
| Framework | |
LIS at SemEval-2018 Task 2: Mixing Word Embeddings and Bag of Features for Multilingual Emoji Prediction
| Title | LIS at SemEval-2018 Task 2: Mixing Word Embeddings and Bag of Features for Multilingual Emoji Prediction |
| Authors | Ga{"e}l Guibon, Magalie Ochs, Patrice Bellot |
| Abstract | In this paper we present the system submitted to the SemEval2018 task2 : Multilingual Emoji Prediction. Our system approaches both languages as being equal by first; considering word embeddings associated to automatically computed features of different types, then by applying bagging algorithm RandomForest to predict the emoji of a tweet. |
| Tasks | Information Retrieval, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1081/ |
| https://www.aclweb.org/anthology/S18-1081 | |
| PWC | https://paperswithcode.com/paper/lis-at-semeval-2018-task-2-mixing-word |
| Repo | |
| Framework | |
Robust parfda Statistical Machine Translation Results
| Title | Robust parfda Statistical Machine Translation Results |
| Authors | Ergun Bi{\c{c}}ici |
| Abstract | We build parallel feature decay algorithms (parfda) Moses statistical machine translation (SMT) models for language pairs in the translation task. parfda obtains results close to the top constrained phrase-based SMT with an average of 2.252 BLEU points difference on WMT 2017 datasets using significantly less computation for building SMT systems than that would be spent using all available corpora. We obtain BLEU upper bounds based on target coverage to identify which systems used additional data. We use PRO for tuning to decrease fluctuations in the results and postprocess translation outputs to decrease translation errors due to the casing of words. F1 scores on the key phrases of the English to Turkish testsuite that we prepared reveal that parfda achieves 2nd best results. Truecasing translations before scoring obtained the best results overall. |
| Tasks | Language Modelling, Machine Translation, Tokenization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6405/ |
| https://www.aclweb.org/anthology/W18-6405 | |
| PWC | https://paperswithcode.com/paper/robust-parfda-statistical-machine-translation |
| Repo | |
| Framework | |
Treat us like the sequences we are: Prepositional Paraphrasing of Noun Compounds using LSTM
| Title | Treat us like the sequences we are: Prepositional Paraphrasing of Noun Compounds using LSTM |
| Authors | Girishkumar Ponkiya, Kevin Patel, Pushpak Bhattacharyya, Girish Palshikar |
| Abstract | Interpreting noun compounds is a challenging task. It involves uncovering the underlying predicate which is dropped in the formation of the compound. In most cases, this predicate is of the form VERB+PREP. It has been observed that uncovering the preposition is a significant step towards uncovering the predicate. In this paper, we attempt to paraphrase noun compounds using prepositions. We consider noun compounds and their corresponding prepositional paraphrases as parallelly aligned sequences of words. This enables us to adapt different architectures from cross-lingual embedding literature. We choose the architecture where we create representations of both noun compound (source sequence) and its corresponding prepositional paraphrase (target sequence), such that their sim- ilarity is high. We use LSTMs to learn these representations. We use these representations to decide the correct preposition. Our experiments show that this approach performs considerably well on different datasets of noun compounds that are manually annotated with prepositions. |
| Tasks | Machine Translation, Question Answering |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1155/ |
| https://www.aclweb.org/anthology/C18-1155 | |
| PWC | https://paperswithcode.com/paper/treat-us-like-the-sequences-we-are |
| Repo | |
| Framework | |
A Papier-Mâché Approach to Learning 3D Surface Generation
| Title | A Papier-Mâché Approach to Learning 3D Surface Generation |
| Authors | Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry |
| Abstract | We introduce a method for learning to generate the surface of 3D shapes. Our approach represents a 3D shape as a collection of parametric surface elements and, in contrast to methods generating voxel grids or point clouds, naturally infers a surface representation of the shape. Beyond its novelty, our new shape generation framework, AtlasNet, comes with significant advantages, such as improved precision and generalization capabilities, and the possibility to generate a shape of arbitrary resolution without memory issues. We demonstrate these benefits and compare to strong baselines on the ShapeNet benchmark for two applications: (i) auto-encoding shapes, and (ii) single-view reconstruction from a still image. We also provide results showing its potentialfor other applications, such as morphing, parametrization, super-resolution, matching, and co-segmentation. |
| Tasks | 3D Surface Generation, Super-Resolution |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Groueix_A_Papier-Mache_Approach_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Groueix_A_Papier-Mache_Approach_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-papier-macha-approach-to-learning-3d |
| Repo | |
| Framework | |
