Paper Group NANR 80
Batch Weight for Domain Adaptation With Mass Shift. Cross-Corpus Data Augmentation for Acoustic Addressee Detection. The Impact of Semantic Linguistic Features in Relation Extraction: A Logical Relational Learning Approach. Hierarchical Multi-label Classification of Text with Capsule Networks. Evaluation of Semantic Change of Harm-Related Concepts …
Batch Weight for Domain Adaptation With Mass Shift
Title | Batch Weight for Domain Adaptation With Mass Shift |
Authors | Mikolaj Binkowski, Devon Hjelm, Aaron Courville |
Abstract | Unsupervised domain transfer is the task of transferring or translating samples from a source distribution to a different target distribution. Current solutions unsupervised domain transfer often operate on data on which the modes of the distribution are well-matched, for instance have the same frequencies of classes between source and target distributions. However, these models do not perform well when the modes are not well-matched, as would be the case when samples are drawn independently from two different, but related, domains. This mode imbalance is problematic as generative adversarial networks (GANs), a successful approach in this setting, are sensitive to mode frequency, which results in a mismatch of semantics between source samples and generated samples of the target distribution. We propose a principled method of re-weighting training samples to correct for such mass shift between the transferred distributions, which we call batch weight. We also provide rigorous probabilistic setting for domain transfer and new simplified objective for training transfer networks, an alternative to complex, multi-component loss functions used in the current state-of-the art image-to-image translation models. The new objective stems from the discrimination of joint distributions and enforces cycle-consistency in an abstract, high-level, rather than pixel-wise, sense. Lastly, we experimentally show the effectiveness of the proposed methods in several image-to-image translation tasks. |
Tasks | Domain Adaptation, Image-to-Image Translation |
Published | 2019-10-01 |
URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Binkowski_Batch_Weight_for_Domain_Adaptation_With_Mass_Shift_ICCV_2019_paper.html |
http://openaccess.thecvf.com/content_ICCV_2019/papers/Binkowski_Batch_Weight_for_Domain_Adaptation_With_Mass_Shift_ICCV_2019_paper.pdf | |
PWC | https://paperswithcode.com/paper/batch-weight-for-domain-adaptation-with-mass-1 |
Repo | |
Framework | |
Cross-Corpus Data Augmentation for Acoustic Addressee Detection
Title | Cross-Corpus Data Augmentation for Acoustic Addressee Detection |
Authors | Oleg Akhtiamov, Ingo Siegert, Alexey Karpov, Wolfgang Minker |
Abstract | Acoustic addressee detection (AD) is a modern paralinguistic and dialogue challenge that especially arises in voice assistants. In the present study, we distinguish addressees in two settings (a conversation between several people and a spoken dialogue system, and a conversation between several adults and a child) and introduce the first competitive baseline (unweighted average recall equals 0.891) for the Voice Assistant Conversation Corpus that models the first setting. We jointly solve both classification problems, using three models: a linear support vector machine dealing with acoustic functionals and two neural networks utilising raw waveforms alongside with acoustic low-level descriptors. We investigate how different corpora influence each other, applying the mixup approach to data augmentation. We also study the influence of various acoustic context lengths on AD. Two-second speech fragments turn out to be sufficient for reliable AD. Mixup is shown to be beneficial for merging acoustic data (extracted features but not raw waveforms) from different domains that allows us to reach a higher classification performance on human-machine AD and also for training a multipurpose neural network that is capable of solving both human-machine and adult-child AD problems. |
Tasks | Data Augmentation |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/W19-5933/ |
https://www.aclweb.org/anthology/W19-5933 | |
PWC | https://paperswithcode.com/paper/cross-corpus-data-augmentation-for-acoustic |
Repo | |
Framework | |
The Impact of Semantic Linguistic Features in Relation Extraction: A Logical Relational Learning Approach
Title | The Impact of Semantic Linguistic Features in Relation Extraction: A Logical Relational Learning Approach |
Authors | Rinaldo Lima, Bernard Espinasse, Frederico Freitas |
Abstract | Relation Extraction (RE) consists in detecting and classifying semantic relations between entities in a sentence. The vast majority of the state-of-the-art RE systems relies on morphosyntactic features and supervised machine learning algorithms. This paper tries to answer important questions concerning both the impact of semantic based features, and the integration of external linguistic knowledge resources on RE performance. For that, a RE system based on a logical and relational learning algorithm was used and evaluated on three reference datasets from two distinct domains. The yielded results confirm that the classifiers induced using the proposed richer feature set outperformed the classifiers built with morphosyntactic features in average 4{%} (F1-measure). |
Tasks | Relational Reasoning, Relation Extraction |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/R19-1076/ |
https://www.aclweb.org/anthology/R19-1076 | |
PWC | https://paperswithcode.com/paper/the-impact-of-semantic-linguistic-features-in |
Repo | |
Framework | |
Hierarchical Multi-label Classification of Text with Capsule Networks
Title | Hierarchical Multi-label Classification of Text with Capsule Networks |
Authors | Rami Aly, Steffen Remus, Chris Biemann |
Abstract | Capsule networks have been shown to demonstrate good performance on structured data in the area of visual inference. In this paper we apply and compare simple shallow capsule networks for hierarchical multi-label text classification and show that they can perform superior to other neural networks, such as CNNs and LSTMs, and non-neural network architectures such as SVMs. For our experiments, we use the established Web of Science (WOS) dataset and introduce a new real-world scenario dataset, the BlurbGenreCollection (BGC). Our results confirm the hypothesis that capsule networks are especially advantageous for rare events and structurally diverse categories, which we attribute to their ability to combine latent encoded information. |
Tasks | Multi-Label Classification, Multi-Label Text Classification, Text Classification |
Published | 2019-07-01 |
URL | https://www.aclweb.org/anthology/P19-2045/ |
https://www.aclweb.org/anthology/P19-2045 | |
PWC | https://paperswithcode.com/paper/hierarchical-multi-label-classification-of |
Repo | |
Framework | |
Evaluation of Semantic Change of Harm-Related Concepts in Psychology
Title | Evaluation of Semantic Change of Harm-Related Concepts in Psychology |
Authors | Ekaterina Vylomova, Sean Murphy, Nicholas Haslam |
Abstract | The paper focuses on diachronic evaluation of semantic changes of harm-related concepts in psychology. More specifically, we investigate a hypothesis that certain concepts such as {}addiction{''}, { }bullying{''}, {}harassment{''}, { }prejudice{''}, and {}trauma{''} became broader during the last four decades. We evaluate semantic changes using two models: an LSA-based model from Sagi et al. (2009) and a diachronic adaptation of word2vec from Hamilton et al. (2016), that are trained on a large corpus of journal abstracts covering the period of 1980{--} 2019. Several concepts showed evidence of broadening. { }Addiction{''} moved from physiological dependency on a substance to include psychological dependency on gaming and the Internet. Similarly, {}harassment{''} and { }trauma{''} shifted towards more psychological meanings. On the other hand, {``}bullying{''} has transformed into a more victim-related concept and expanded to new areas such as workplaces. | |
Tasks | |
Published | 2019-08-01 |
URL | https://www.aclweb.org/anthology/W19-4704/ |
https://www.aclweb.org/anthology/W19-4704 | |
PWC | https://paperswithcode.com/paper/evaluation-of-semantic-change-of-harm-related |
Repo | |
Framework | |
Hiding Video in Audio via Reversible Generative Models
Title | Hiding Video in Audio via Reversible Generative Models |
Authors | Hyukryul Yang, Hao Ouyang, Vladlen Koltun, Qifeng Chen |
Abstract | We present a method for hiding video content inside audio files while preserving the perceptual fidelity of the cover audio. This is a form of cross-modal steganography and is particularly challenging due to the high bitrate of video. Our scheme uses recent advances in flow-based generative models, which enable mapping audio to latent codes such that nearby codes correspond to perceptually similar signals. We show that compressed video data can be concealed in the latent codes of audio sequences while preserving the fidelity of both the hidden video and the cover audio. We can embed 128x128 video inside same-duration audio, or higher-resolution video inside longer audio sequences. Quantitative experiments show that our approach outperforms relevant baselines in steganographic capacity and fidelity. |
Tasks | |
Published | 2019-10-01 |
URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yang_Hiding_Video_in_Audio_via_Reversible_Generative_Models_ICCV_2019_paper.html |
http://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_Hiding_Video_in_Audio_via_Reversible_Generative_Models_ICCV_2019_paper.pdf | |
PWC | https://paperswithcode.com/paper/hiding-video-in-audio-via-reversible |
Repo | |
Framework | |
What You Say and How You Say It Matters: Predicting Stock Volatility Using Verbal and Vocal Cues
Title | What You Say and How You Say It Matters: Predicting Stock Volatility Using Verbal and Vocal Cues |
Authors | Yu Qin, Yi Yang |
Abstract | Predicting financial risk is an essential task in financial market. Prior research has shown that textual information in a firm{'}s financial statement can be used to predict its stock{'}s risk level. Nowadays, firm CEOs communicate information not only verbally through press releases and financial reports, but also nonverbally through investor meetings and earnings conference calls. There are anecdotal evidences that CEO{'}s vocal features, such as emotions and voice tones, can reveal the firm{'}s performance. However, how vocal features can be used to predict risk levels, and to what extent, is still unknown. To fill the gap, we obtain earnings call audio recordings and textual transcripts for S{&}P 500 companies in recent years. We propose a multimodal deep regression model (MDRM) that jointly model CEO{'}s verbal (from text) and vocal (from audio) information in a conference call. Empirical results show that our model that jointly considers verbal and vocal features achieves significant and substantial prediction error reduction. We also discuss several interesting findings and the implications to financial markets. The processed earnings conference calls data (text and audio) are released for readers who are interested in reproducing the results or designing trading strategy. |
Tasks | |
Published | 2019-07-01 |
URL | https://www.aclweb.org/anthology/P19-1038/ |
https://www.aclweb.org/anthology/P19-1038 | |
PWC | https://paperswithcode.com/paper/what-you-say-and-how-you-say-it-matters |
Repo | |
Framework | |
Modeling Markedness with a Split-and-Merger Model of Sound Change
Title | Modeling Markedness with a Split-and-Merger Model of Sound Change |
Authors | Andrea Ceolin, Ollie Sayeed |
Abstract | The concept of {}markedness{'} has been influential in phonology for almost a century. Theoretical phonology has found it useful to describe some segments as more { }marked{'} than others, referring to a cluster of language-internal and -external properties (Jakobson 1968, Haspelmath 2006). We argue, using a simple mathematical model based on Evolutionary Phonology (Blevins 2004), that markedness is an epiphenomenon of phonetically grounded sound change. |
Tasks | |
Published | 2019-08-01 |
URL | https://www.aclweb.org/anthology/W19-4708/ |
https://www.aclweb.org/anthology/W19-4708 | |
PWC | https://paperswithcode.com/paper/modeling-markedness-with-a-split-and-merger |
Repo | |
Framework | |
A Method to Automatically Identify Diachronic Variation in Collocations.
Title | A Method to Automatically Identify Diachronic Variation in Collocations. |
Authors | Marcos Garcia, Marcos Garc{'\i}a Salido |
Abstract | This paper introduces a novel method to track collocational variations in diachronic corpora that can identify several changes undergone by these phraseological combinations and to propose alternative solutions found in later periods. The strategy consists of extracting syntactically-related candidates of collocations and ranking them using statistical association measures. Then, starting from the first period of the corpus, the system tracks each combination over time, verifying different types of historical variation such as the loss of one or both lemmas, the disappearance of the collocation, or its diachronic frequency trend. Using a distributional semantics strategy, it also proposes other linguistic structures which convey similar meanings to those extinct collocations. A case study on historical corpora of Portuguese and Spanish shows that the system speeds up and facilitates the finding of some diachronic changes and phraseological shifts that are harder to identify without using automated methods. |
Tasks | |
Published | 2019-08-01 |
URL | https://www.aclweb.org/anthology/W19-4709/ |
https://www.aclweb.org/anthology/W19-4709 | |
PWC | https://paperswithcode.com/paper/a-method-to-automatically-identify-diachronic |
Repo | |
Framework | |
Fine-Grained Propaganda Detection with Fine-Tuned BERT
Title | Fine-Grained Propaganda Detection with Fine-Tuned BERT |
Authors | Shehel Yoosuf, Yin Yang |
Abstract | This paper presents the winning solution of the Fragment Level Classification (FLC) task in the Fine Grained Propaganda Detection competition at the NLP4IF{'}19 workshop. The goal of the FLC task is to detect and classify textual segments that correspond to one of the 18 given propaganda techniques in a news articles dataset. The main idea of our solution is to perform word-level classification using fine-tuned BERT, a popular pre-trained language model. Besides presenting the model and its evaluation results, we also investigate the attention heads in the model, which provide insights into what the model learns, as well as aspects for potential improvements. |
Tasks | Language Modelling |
Published | 2019-11-01 |
URL | https://www.aclweb.org/anthology/D19-5011/ |
https://www.aclweb.org/anthology/D19-5011 | |
PWC | https://paperswithcode.com/paper/fine-grained-propaganda-detection-with-fine |
Repo | |
Framework | |
Evidence-based Trustworthiness
Title | Evidence-based Trustworthiness |
Authors | Yi Zhang, Zachary Ives, Dan Roth |
Abstract | The information revolution brought with it information pollution. Information retrieval and extraction help us cope with abundant information from diverse sources. But some sources are of anonymous authorship, and some are of uncertain accuracy, so how can we determine what we should actually believe? Not all information sources are equally trustworthy, and simply accepting the majority view is often wrong. This paper develops a general framework for estimating the trustworthiness of information sources in an environment where multiple sources provide claims and supporting evidence, and each claim can potentially be produced by multiple sources. We consider two settings: one in which information sources directly assert claims, and a more realistic and challenging one, in which claims are inferred from evidence provided by sources, via (possibly noisy) NLP techniques. Our key contribution is to develop a family of probabilistic models that jointly estimate the trustworthiness of sources, and the credibility of claims they assert. This is done while accounting for the (possibly noisy) NLP needed to infer claims from evidence supplied by sources. We evaluate our framework on several datasets, showing strong results and significant improvement over baselines. |
Tasks | Information Retrieval |
Published | 2019-07-01 |
URL | https://www.aclweb.org/anthology/P19-1040/ |
https://www.aclweb.org/anthology/P19-1040 | |
PWC | https://paperswithcode.com/paper/evidence-based-trustworthiness |
Repo | |
Framework | |
Coordinate-Free Carlsson-Weinshall Duality and Relative Multi-View Geometry
Title | Coordinate-Free Carlsson-Weinshall Duality and Relative Multi-View Geometry |
Authors | Matthew Trager, Martial Hebert, Jean Ponce |
Abstract | We present a coordinate-free description of Carlsson-Weinshall duality between scene points and camera pinholes and use it to derive a new characterization of primal/dual multi-view geometry. In the case of three views, a particular set of reduced trilinearities provide a novel parameterization of camera geometry that, unlike existing ones, is subject only to very simple internal constraints. These trilinearities lead to new “quasi-linear” algorithms for primal and dual structure from motion. We include some preliminary experiments with real and synthetic data. |
Tasks | |
Published | 2019-06-01 |
URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Trager_Coordinate-Free_Carlsson-Weinshall_Duality_and_Relative_Multi-View_Geometry_CVPR_2019_paper.html |
http://openaccess.thecvf.com/content_CVPR_2019/papers/Trager_Coordinate-Free_Carlsson-Weinshall_Duality_and_Relative_Multi-View_Geometry_CVPR_2019_paper.pdf | |
PWC | https://paperswithcode.com/paper/coordinate-free-carlsson-weinshall-duality |
Repo | |
Framework | |
Dependency Parser for Sanskrit Verses
Title | Dependency Parser for Sanskrit Verses |
Authors | Amba Kulkarni, Sanal Vikram, Sriram K |
Abstract | |
Tasks | |
Published | 2019-10-01 |
URL | https://www.aclweb.org/anthology/W19-7502/ |
https://www.aclweb.org/anthology/W19-7502 | |
PWC | https://paperswithcode.com/paper/dependency-parser-for-sanskrit-verses |
Repo | |
Framework | |
Grammatical Framework: an Interlingual Grammar Formalism
Title | Grammatical Framework: an Interlingual Grammar Formalism |
Authors | Aarne Ranta |
Abstract | |
Tasks | |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/W19-3101/ |
https://www.aclweb.org/anthology/W19-3101 | |
PWC | https://paperswithcode.com/paper/grammatical-framework-an-interlingual-grammar |
Repo | |
Framework | |
Online Unsupervised Learning of the 3D Kinematic Structure of Arbitrary Rigid Bodies
Title | Online Unsupervised Learning of the 3D Kinematic Structure of Arbitrary Rigid Bodies |
Authors | Urbano Miguel Nunes, Yiannis Demiris |
Abstract | This work addresses the problem of 3D kinematic structure learning of arbitrary articulated rigid bodies from RGB-D data sequences. Typically, this problem is addressed by offline methods that process a batch of frames, assuming that complete point trajectories are available. However, this approach is not feasible when considering scenarios that require continuity and fluidity, for instance, human-robot interaction. In contrast, we propose to tackle this problem in an online unsupervised fashion, by recursively maintaining the metric distance of the scene’s 3D structure, while achieving real-time performance. The influence of noise is mitigated by building a similarity measure based on a linear embedding representation and incorporating this representation into the original metric distance. The kinematic structure is then estimated based on a combination of implicit motion and spatial properties. The proposed approach achieves competitive performance both quantitatively and qualitatively in terms of estimation accuracy, even compared to offline methods. |
Tasks | |
Published | 2019-10-01 |
URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Nunes_Online_Unsupervised_Learning_of_the_3D_Kinematic_Structure_of_Arbitrary_ICCV_2019_paper.html |
http://openaccess.thecvf.com/content_ICCV_2019/papers/Nunes_Online_Unsupervised_Learning_of_the_3D_Kinematic_Structure_of_Arbitrary_ICCV_2019_paper.pdf | |
PWC | https://paperswithcode.com/paper/online-unsupervised-learning-of-the-3d |
Repo | |
Framework | |