Paper Group NANR 176
Enhancing Universal Dependency Treebanks: A Case Study. LMU Munich’s Neural Machine Translation Systems at WMT 2018. A Bayesian Nonparametric Topic Model with Variational Auto-Encoders. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask. Rolling Shutter Pose and Ego-motion Estimation using Shape-from-Template. …
Enhancing Universal Dependency Treebanks: A Case Study
| Title | Enhancing Universal Dependency Treebanks: A Case Study |
| Authors | Joakim Nivre, Paola Marongiu, Filip Ginter, Jenna Kanerva, Simonetta Montemagni, Sebastian Schuster, Maria Simi |
| Abstract | We evaluate two cross-lingual techniques for adding enhanced dependencies to existing treebanks in Universal Dependencies. We apply a rule-based system developed for English and a data-driven system trained on Finnish to Swedish and Italian. We find that both systems are accurate enough to bootstrap enhanced dependencies in existing UD treebanks. In the case of Italian, results are even on par with those of a prototype language-specific system. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6012/ |
| https://www.aclweb.org/anthology/W18-6012 | |
| PWC | https://paperswithcode.com/paper/enhancing-universal-dependency-treebanks-a |
| Repo | |
| Framework | |
LMU Munich’s Neural Machine Translation Systems at WMT 2018
| Title | LMU Munich’s Neural Machine Translation Systems at WMT 2018 |
| Authors | Matthias Huck, Dario Stojanovski, Viktor Hangya, Alex Fraser, er |
| Abstract | We present the LMU Munich machine translation systems for the English{–}German language pair. We have built neural machine translation systems for both translation directions (English→German and German→English) and for two different domains (the biomedical domain and the news domain). The systems were used for our participation in the WMT18 biomedical translation task and in the shared task on machine translation of news. The main focus of our recent system development efforts has been on achieving improvements in the biomedical domain over last year{'}s strong biomedical translation engine for English→German (Huck et al., 2017a). Considerable progress has been made in the latter task, which we report on in this paper. |
| Tasks | Domain Adaptation, Machine Translation, Unsupervised Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6446/ |
| https://www.aclweb.org/anthology/W18-6446 | |
| PWC | https://paperswithcode.com/paper/lmu-munichas-neural-machine-translation |
| Repo | |
| Framework | |
A Bayesian Nonparametric Topic Model with Variational Auto-Encoders
| Title | A Bayesian Nonparametric Topic Model with Variational Auto-Encoders |
| Authors | Xuefei Ning, Yin Zheng, Zhuxi Jiang, Yu Wang, Huazhong Yang, Junzhou Huang |
| Abstract | Topic modeling of text documents is one of the most important tasks in representation learning. In this work, we propose iTM-VAE, which is a Bayesian nonparametric (BNP) topic model with variational auto-encoders. On one hand, as a BNP topic model, iTM-VAE potentially has infinite topics and can adapt the topic number to data automatically. On the other hand, different with the other BNP topic models, the inference of iTM-VAE is modeled by neural networks, which has rich representation capacity and can be computed in a simple feed-forward manner. Two variants of iTM-VAE are also proposed in this paper, where iTM-VAE-Prod models the generative process in products-of-experts fashion for better performance and iTM-VAE-G places a prior over the concentration parameter such that the model can adapt a suitable concentration parameter to data automatically. Experimental results on 20News and Reuters RCV1-V2 datasets show that the proposed models outperform the state-of-the-arts in terms of perplexity, topic coherence and document retrieval tasks. Moreover, the ability of adjusting the concentration parameter to data is also confirmed by experiments. |
| Tasks | Representation Learning, Topic Models |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SkxqZngC- |
| https://openreview.net/pdf?id=SkxqZngC- | |
| PWC | https://paperswithcode.com/paper/a-bayesian-nonparametric-topic-model-with |
| Repo | |
| Framework | |
100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask
| Title | 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask |
| Authors | Emily M. Bender |
| Abstract | Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that{'}s accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh. |
| Tasks | Recommendation Systems |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-5001/ |
| https://www.aclweb.org/anthology/P18-5001 | |
| PWC | https://paperswithcode.com/paper/100-things-you-always-wanted-to-know-about-1 |
| Repo | |
| Framework | |
Rolling Shutter Pose and Ego-motion Estimation using Shape-from-Template
| Title | Rolling Shutter Pose and Ego-motion Estimation using Shape-from-Template |
| Authors | Yizhen Lao, Omar Ait-Aider, Adrien Bartoli |
| Abstract | We propose a new method for the absolute camera pose problem (PnP) which handles Rolling Shutter (RS) effects. Unlike all existing methods which perform 3D-2D registration after augmenting the Global Shutter (GS) projection model with the velocity parameters under various kinematic models, we propose to use local differential constraints. These are established by drawing an analogy with Shape-from-Template (SfT). The main idea consists in considering that RS distortions due to camera ego-motion during image acquisition can be interpreted as virtual deformations of a template captured by a GS camera. Once the virtual deformations have been recovered using SfT, the camera pose and ego-motion are computed by registering the deformed scene on the original template. This 3D-3D registration involves a 3D cost function based on the Euclidean point distance, more physically meaningful than the re-projection error or the algebraic distance based cost functions used in previous work. Results on both synthetic and real data show that the proposed method outperforms existing RS pose estimation techniques in terms of accuracy and stability of performance in various configurations. |
| Tasks | Motion Estimation, Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yizhen_Lao_Rolling_Shutter_Pose_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yizhen_Lao_Rolling_Shutter_Pose_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/rolling-shutter-pose-and-ego-motion |
| Repo | |
| Framework | |
Extended and Enhanced Polish Dependency Bank in Universal Dependencies Format
| Title | Extended and Enhanced Polish Dependency Bank in Universal Dependencies Format |
| Authors | Alina Wr{'o}blewska |
| Abstract | The paper presents the largest Polish Dependency Bank in Universal Dependencies format {–} PDBUD {–} with 22K trees and 352K tokens. PDBUD builds on its previous version, i.e. the Polish UD treebank (PL-SZ), and contains all 8K PL-SZ trees. The PL-SZ trees are checked and possibly corrected in the current edition of PDBUD. Further 14K trees are automatically converted from a new version of Polish Dependency Bank. The PDBUD trees are expanded with the enhanced edges encoding the shared dependents and the shared governors of the coordinated conjuncts and with the semantic roles of some dependents. The conducted evaluation experiments show that PDBUD is large enough for training a high-quality graph-based dependency parser for Polish. |
| Tasks | Dependency Parsing |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6020/ |
| https://www.aclweb.org/anthology/W18-6020 | |
| PWC | https://paperswithcode.com/paper/extended-and-enhanced-polish-dependency-bank |
| Repo | |
| Framework | |
Cross-Domain Sentiment Classification with Target Domain Specific Information
| Title | Cross-Domain Sentiment Classification with Target Domain Specific Information |
| Authors | Minlong Peng, Qi Zhang, Yu-gang Jiang, Xuanjing Huang |
| Abstract | The task of adopting a model with good performance to a target domain that is different from the source domain used for training has received considerable attention in sentiment analysis. Most existing approaches mainly focus on learning representations that are domain-invariant in both the source and target domains. Few of them pay attention to domain-specific information, which should also be informative. In this work, we propose a method to simultaneously extract domain specific and invariant representations and train a classifier on each of the representation, respectively. And we introduce a few target domain labeled data for learning domain-specific information. To effectively utilize the target domain labeled data, we train the domain invariant representation based classifier with both the source and target domain labeled data and train the domain-specific representation based classifier with only the target domain labeled data. These two classifiers then boost each other in a co-training style. Extensive sentiment analysis experiments demonstrated that the proposed method could achieve better performance than state-of-the-art methods. |
| Tasks | Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1233/ |
| https://www.aclweb.org/anthology/P18-1233 | |
| PWC | https://paperswithcode.com/paper/cross-domain-sentiment-classification-with |
| Repo | |
| Framework | |
Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance
| Title | Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance |
| Authors | M, Soumil al, Karthick Nanmaran |
| Abstract | Building tools for code-mixed data is rapidly gaining popularity in the NLP research community as such data is exponentially rising on social media. Working with code-mixed data contains several challenges, especially due to grammatical inconsistencies and spelling variations in addition to all the previous known challenges for social media scenarios. In this article, we present a novel architecture focusing on normalizing phonetic typing variations, which is commonly seen in code-mixed data. One of the main features of our architecture is that in addition to normalizing, it can also be utilized for back-transliteration and word identification in some cases. Our model achieved an accuracy of 90.27{%} on the test data. |
| Tasks | Opinion Mining, Transliteration, Word Embeddings |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6107/ |
| https://www.aclweb.org/anthology/W18-6107 | |
| PWC | https://paperswithcode.com/paper/normalization-of-transliterated-words-in-code-1 |
| Repo | |
| Framework | |
Multimodal Frame Identification with Multilingual Evaluation
| Title | Multimodal Frame Identification with Multilingual Evaluation |
| Authors | Teresa Botschen, Iryna Gurevych, Jan-Christoph Klie, Hatem Mousselly-Sergieh, Stefan Roth |
| Abstract | An essential step in FrameNet Semantic Role Labeling is the Frame Identification (FrameId) task, which aims at disambiguating a situation around a predicate. Whilst current FrameId methods rely on textual representations only, we hypothesize that FrameId can profit from a richer understanding of the situational context. Such contextual information can be obtained from common sense knowledge, which is more present in images than in text. In this paper, we extend a state-of-the-art FrameId system in order to effectively leverage multimodal representations. We conduct a comprehensive evaluation on the English FrameNet and its German counterpart SALSA. Our analysis shows that for the German data, textual representations are still competitive with multimodal ones. However on the English data, our multimodal FrameId approach outperforms its unimodal counterpart, setting a new state of the art. Its benefits are particularly apparent in dealing with ambiguous and rare instances, the main source of errors of current systems. For research purposes, we release (a) the implementation of our system, (b) our evaluation splits for SALSA 2.0, and (c) the embeddings for synsets and IMAGINED words. |
| Tasks | Common Sense Reasoning, Semantic Role Labeling, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1134/ |
| https://www.aclweb.org/anthology/N18-1134 | |
| PWC | https://paperswithcode.com/paper/multimodal-frame-identification-with |
| Repo | |
| Framework | |
Towards Less Post-Editing
| Title | Towards Less Post-Editing |
| Authors | Bill Lafferty |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1916/ |
| https://www.aclweb.org/anthology/W18-1916 | |
| PWC | https://paperswithcode.com/paper/towards-less-post-editing |
| Repo | |
| Framework | |
ExplainGAN: Model Explanation via Decision Boundary Crossing Transformations
| Title | ExplainGAN: Model Explanation via Decision Boundary Crossing Transformations |
| Authors | Pouya Samangouei, Ardavan Saeedi, Liam Nakagawa, Nathan Silberman |
| Abstract | We introduce a new method for interpreting computer vision models: visually perceptible, decision-boundary crossing transformations. Our goal is to answer a simple question: why did a model classify an image as being of class A instead of class B? Existing approaches to model interpretation, including saliency and explanation-by-nearest neighbor, fail to visually illustrate examples of transformations required for a specific input to alter a model’s prediction. On the other hand, algorithms for creating decision-boundary crossing transformations (e.g., adversarial examples) produce differences that are visually imperceptible and do not enable insightful explanation. To address this we introduce ExplainGAN, a generative model that produces visually perceptible decision-boundary crossing transformations. These transformations provide high-level conceptual insights which illustrate how a model makes decisions. We validate our model using both traditional quantitative interpretation metrics and introduce a new validation scheme for our approach and generative models more generally. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Nathan_Silberman_ExplainGAN_Model_Explanation_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Nathan_Silberman_ExplainGAN_Model_Explanation_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/explaingan-model-explanation-via-decision |
| Repo | |
| Framework | |
Adversarial Examples for Natural Language Classification Problems
| Title | Adversarial Examples for Natural Language Classification Problems |
| Authors | Volodymyr Kuleshov, Shantanu Thakoor, Tingfung Lau, Stefano Ermon |
| Abstract | Modern machine learning algorithms are often susceptible to adversarial examples — maliciously crafted inputs that are undetectable by humans but that fool the algorithm into producing undesirable behavior. In this work, we show that adversarial examples exist in natural language classification: we formalize the notion of an adversarial example in this setting and describe algorithms that construct such examples. Adversarial perturbations can be crafted for a wide range of tasks — including spam filtering, fake news detection, and sentiment analysis — and affect different models — convolutional and recurrent neural networks as well as linear classifiers to a lesser degree. Constructing an adversarial example involves replacing 10-30% of words in a sentence with synonyms that don’t change its meaning. Up to 90% of input examples admit adversarial perturbations; furthermore, these perturbations retain a degree of transferability across models. Our findings demonstrate the existence of vulnerabilities in machine learning systems and hint at limitations in our understanding of classification algorithms. |
| Tasks | Fake News Detection, Sentiment Analysis |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1QZ3zbAZ |
| https://openreview.net/pdf?id=r1QZ3zbAZ | |
| PWC | https://paperswithcode.com/paper/adversarial-examples-for-natural-language |
| Repo | |
| Framework | |
Modeling Student Response Times: Towards Efficient One-on-one Tutoring Dialogues
| Title | Modeling Student Response Times: Towards Efficient One-on-one Tutoring Dialogues |
| Authors | Luciana Benotti, Jayadev Bhaskaran, Sigtryggur Kjartansson, David Lang |
| Abstract | In this paper we investigate the task of modeling how long it would take a student to respond to a tutor question during a tutoring dialogue. Solving such a task has applications in educational settings such as intelligent tutoring systems, as well as in platforms that help busy human tutors to keep students engaged. Knowing how long it would normally take a student to respond to different types of questions could help tutors optimize their own time while answering multiple dialogues concurrently, as well as deciding when to prompt a student again. We study this problem using data from a service that offers tutor support for math, chemistry and physics through an instant messaging platform. We create a dataset of 240K questions. We explore several strong baselines for this task and compare them with human performance. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6117/ |
| https://www.aclweb.org/anthology/W18-6117 | |
| PWC | https://paperswithcode.com/paper/modeling-student-response-times-towards |
| Repo | |
| Framework | |
Learning 3D Shape Completion From Laser Scan Data With Weak Supervision
| Title | Learning 3D Shape Completion From Laser Scan Data With Weak Supervision |
| Authors | David Stutz, Andreas Geiger |
| Abstract | 3D shape completion from partial point clouds is a fundamental problem in computer vision and computer graphics. Recent approaches can be characterized as either data-driven or learning-based. Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations. Learning-based approaches, in contrast, avoid the expensive optimization step and instead directly predict the complete shape from the incomplete observations using deep neural networks. However, full supervision is required which is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, i.e., learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. Tackling 3D shape completion of cars on ShapeNet and KITTI, we demonstrate that the proposed amortized maximum likelihood approach is able to compete with a fully supervised baseline and a state-of-the-art data-driven approach while being significantly faster. On ModelNet, we additionally show that the approach is able to generalize to other object categories as well. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Stutz_Learning_3D_Shape_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Stutz_Learning_3D_Shape_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-3d-shape-completion-from-laser-scan |
| Repo | |
| Framework | |
Video Action Segmentation with Hybrid Temporal Networks
| Title | Video Action Segmentation with Hybrid Temporal Networks |
| Authors | Li Ding, Chenliang Xu |
| Abstract | Action segmentation as a milestone towards building automatic systems to understand untrimmed videos has received considerable attention in the recent years. It is typically being modeled as a sequence labeling problem but contains intrinsic and sufficient differences than text parsing or speech processing. In this paper, we introduce a novel hybrid temporal convolutional and recurrent network (TricorNet), which has an encoder-decoder architecture: the encoder consists of a hierarchy of temporal convolutional kernels that capture the local motion changes of different actions; the decoder is a hierarchy of recurrent neural networks that are able to learn and memorize long-term action dependencies after the encoding stage. Our model is simple but extremely effective in terms of video sequence labeling. The experimental results on three public action segmentation datasets have shown that the proposed model achieves superior performance over the state of the art. |
| Tasks | action segmentation |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1nzLmWAb |
| https://openreview.net/pdf?id=r1nzLmWAb | |
| PWC | https://paperswithcode.com/paper/video-action-segmentation-with-hybrid |
| Repo | |
| Framework | |
