Paper Group NANR 86
Cohen Welling bases & SO(2)-Equivariant classifiers using Tensor nonlinearity.. Machine Learning Approach for Reliability Assessment of Open Source Software. Contributions to Clinical Named Entity Recognition in Portuguese. Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog. Multi-Agent Dual Learning. Cross-Atlas Convolution for Para …
Cohen Welling bases & SO(2)-Equivariant classifiers using Tensor nonlinearity.
| Title | Cohen Welling bases & SO(2)-Equivariant classifiers using Tensor nonlinearity. |
| Authors | Muthuvel Murugan, K Venkata Subrahmanyam |
| Abstract | In this paper we propose autoencoder architectures for learning a Cohen-Welling (CW)-basis for images and their rotations. We use the learned CW-basis to build a rotation equivariant classifier to classify images. The autoencoder and classi- fier architectures use only tensor product nonlinearity. The model proposed by Cohen & Welling (2014) uses ideas from group representation theory, and extracts a basis exposing irreducible representations for images and their rotations. We give several architectures to learn CW-bases including a novel coupling AE archi- tecture to learn a coupled CW-bases for images in different scales simultaneously. Our use of tensor product nonlinearity is inspired from recent work of Kondor (2018a). Our classifier has very good accuracy and we use fewer parameters. Even when the sample complexity to learn a good CW-basis is low we learn clas- sifiers which perform impressively. We show that a coupled CW-bases in one scale can be deployed to classify images in a classifier trained and tested on images in a different scale with only a marginal dip in performance. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SyxXhsAcFQ |
| https://openreview.net/pdf?id=SyxXhsAcFQ | |
| PWC | https://paperswithcode.com/paper/cohen-welling-bases-so2-equivariant |
| Repo | |
| Framework | |
Machine Learning Approach for Reliability Assessment of Open Source Software
| Title | Machine Learning Approach for Reliability Assessment of Open Source Software |
| Authors | Ranjan Kumar Behera, Santanu Kumar Rath, Sanjay Misra, Marcelo Leon, Adewole Adewumi( |
| Abstract | Some of the quality parameters for any successful open source software may be attributed to affordability, availability of source code, re-distributability, and modifiability etc. Quality of software can be further improvised subsequently by either users or associated developers by constantly monitoring some of the reliability aspects. Since multiple users are allowed to modify the code there is a potential threat for security, which might degrade the reliability of software. Bug tracking systems are often considered to monitor various software faults, detected mostly in open source software projects. Various authors have made research in this direction by applying different techniques in order to improve the reliability of open source software projects. In this work, an various machine learning models have been implemented to examine the reliability of the software. An extensive numerical illustration has also been presented for bug data recorded on bug tracking system. The effectiveness of machine learning models for estimating the level of faults associated with the systems has been verified by comparing it with similar approaches as available in the literature. |
| Tasks | |
| Published | 2019-06-29 |
| URL | https://doi.org/10.1007/978-3-030-24305-0_35 |
| https://doi.org/10.1007/978-3-030-24305-0_35 | |
| PWC | https://paperswithcode.com/paper/machine-learning-approach-for-reliability |
| Repo | |
| Framework | |
Contributions to Clinical Named Entity Recognition in Portuguese
| Title | Contributions to Clinical Named Entity Recognition in Portuguese |
| Authors | F{'a}bio Lopes, C{'e}sar Teixeira, Hugo Gon{\c{c}}alo Oliveira |
| Abstract | Having in mind that different languages might present different challenges, this paper presents the following contributions to the area of Information Extraction from clinical text, targeting the Portuguese language: a collection of 281 clinical texts in this language, with manually-annotated named entities; word embeddings trained in a larger collection of similar texts; results of using BiLSTM-CRF neural networks for named entity recognition on the annotated collection, including a comparison of using in-domain or out-of-domain word embeddings in this task. Although learned with much less data, performance is higher when using in-domain embeddings. When tested in 20 independent clinical texts, this model achieved better results than a model using larger out-of-domain embeddings. |
| Tasks | Named Entity Recognition, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5024/ |
| https://www.aclweb.org/anthology/W19-5024 | |
| PWC | https://paperswithcode.com/paper/contributions-to-clinical-named-entity |
| Repo | |
| Framework | |
Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog
| Title | Span-based Hierarchical Semantic Parsing for Task-Oriented Dialog |
| Authors | Panupong Pasupat, Sonal Gupta, M, Karishma yam, Rushin Shah, Mike Lewis, Luke Zettlemoyer |
| Abstract | We propose a semantic parser for parsing compositional utterances into Task Oriented Parse (TOP), a tree representation that has intents and slots as labels of nesting tree nodes. Our parser is span-based: it scores labels of the tree nodes covering each token span independently, but then decodes a valid tree globally. In contrast to previous sequence decoding approaches and other span-based parsers, we (1) improve the training speed by removing the need to run the decoder at training time; and (2) introduce edge scores, which model relations between parent and child labels, to mitigate the independence assumption between node labels and improve accuracy. Our best parser outperforms previous methods on the TOP dataset of mixed-domain task-oriented utterances in both accuracy and training speed. |
| Tasks | Semantic Parsing |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1163/ |
| https://www.aclweb.org/anthology/D19-1163 | |
| PWC | https://paperswithcode.com/paper/span-based-hierarchical-semantic-parsing-for |
| Repo | |
| Framework | |
Multi-Agent Dual Learning
| Title | Multi-Agent Dual Learning |
| Authors | Yiren Wang, Yingce Xia, Tianyu He, Fei Tian, Tao Qin, ChengXiang Zhai, Tie-Yan Liu |
| Abstract | Dual learning has attracted much attention in machine learning, computer vision and natural language processing communities. The core idea of dual learning is to leverage the duality between the primal task (mapping from domain X to domain Y) and dual task (mapping from domain Y to X) to boost the performances of both tasks. Existing dual learning framework forms a system with two agents (one primal model and one dual model) to utilize such duality. In this paper, we extend this framework by introducing multiple primal and dual models, and propose the multi-agent dual learning framework. Experiments on neural machine translation and image translation tasks demonstrate the effectiveness of the new framework. In particular, we set a new record on IWSLT 2014 German-to-English translation with a 35.44 BLEU score, achieve a 31.03 BLEU score on WMT 2014 English-to-German translation with over 2.6 BLEU improvement over the strong Transformer baseline, and set a new record of 49.61 BLEU score on the recent WMT 2018 English-to-German translation. |
| Tasks | Machine Translation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyGhN2A5tm |
| https://openreview.net/pdf?id=HyGhN2A5tm | |
| PWC | https://paperswithcode.com/paper/multi-agent-dual-learning |
| Repo | |
| Framework | |
Cross-Atlas Convolution for Parameterization Invariant Learning on Textured Mesh Surface
| Title | Cross-Atlas Convolution for Parameterization Invariant Learning on Textured Mesh Surface |
| Authors | Shiwei Li, Zixin Luo, Mingmin Zhen, Yao Yao, Tianwei Shen, Tian Fang, Long Quan |
| Abstract | We present a convolutional network architecture for direct feature learning on mesh surfaces through their atlases of texture maps. The texture map encodes the parameterization from 3D to 2D domain, rendering not only RGB values but also rasterized geometric features if necessary. Since the parameterization of texture map is not pre-determined, and depends on the surface topologies, we therefore introduce a novel cross-atlas convolution to recover the original mesh geodesic neighborhood, so as to achieve the invariance property to arbitrary parameterization. The proposed module is integrated into classification and segmentation architectures, which takes the input texture map of a mesh, and infers the output predictions. Our method not only shows competitive performances on classification and segmentation public benchmarks, but also paves the way for the broad mesh surfaces learning. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Cross-Atlas_Convolution_for_Parameterization_Invariant_Learning_on_Textured_Mesh_Surface_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Cross-Atlas_Convolution_for_Parameterization_Invariant_Learning_on_Textured_Mesh_Surface_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/cross-atlas-convolution-for-parameterization |
| Repo | |
| Framework | |
Soft Representation Learning for Sparse Transfer
| Title | Soft Representation Learning for Sparse Transfer |
| Authors | Haeju Park, Jinyoung Yeo, Gengyu Wang, Seung-won Hwang |
| Abstract | Transfer learning is effective for improving the performance of tasks that are related, and Multi-task learning (MTL) and Cross-lingual learning (CLL) are important instances. This paper argues that hard-parameter sharing, of hard-coding layers shared across different tasks or languages, cannot generalize well, when sharing with a loosely related task. Such case, which we call sparse transfer, might actually hurt performance, a phenomenon known as negative transfer. Our contribution is using adversarial training across tasks, to {``}soft-code{''} shared and private spaces, to avoid the shared space gets too sparse. In CLL, our proposed architecture considers another challenge of dealing with low-quality input. | |
| Tasks | Multi-Task Learning, Representation Learning, Transfer Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1151/ |
| https://www.aclweb.org/anthology/P19-1151 | |
| PWC | https://paperswithcode.com/paper/soft-representation-learning-for-sparse |
| Repo | |
| Framework | |
HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation
| Title | HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation |
| Authors | Brian Thompson, Rebecca Knowles, Xuan Zhang, Huda Khayrallah, Kevin Duh, Philipp Koehn |
| Abstract | Bilingual lexicons are valuable resources used by professional human translators. While these resources can be easily incorporated in statistical machine translation, it is unclear how to best do so in the neural framework. In this work, we present the HABLex dataset, designed to test methods for bilingual lexicon integration into neural machine translation. Our data consists of human generated alignments of words and phrases in machine translation test sets in three language pairs (Russian-English, Chinese-English, and Korean-English), resulting in clean bilingual lexicons which are well matched to the reference. We also present two simple baselines - constrained decoding and continued training - and an improvement to continued training to address overfitting. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1142/ |
| https://www.aclweb.org/anthology/D19-1142 | |
| PWC | https://paperswithcode.com/paper/hablex-human-annotated-bilingual-lexicons-for |
| Repo | |
| Framework | |
Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size
| Title | Big Generalizations with Small Data: Exploring the Role of Training Samples in Learning Adjectives of Size |
| Authors | S Pezzelle, ro, Raquel Fern{'a}ndez |
| Abstract | In this paper, we experiment with a recently proposed visual reasoning task dealing with quantities {–} modeling the multimodal, contextually-dependent meaning of size adjectives ({}big{'}, {}small{'}) {–} and explore the impact of varying the training data on the learning behavior of a state-of-art system. In previous work, models have been shown to fail in generalizing to unseen adjective-noun combinations. Here, we investigate whether, and to what extent, seeing some of these cases during training helps a model understand the rule subtending the task, i.e., that being big implies being not small, and vice versa. We show that relatively few examples are enough to understand this relationship, and that developing a specific, mutually exclusive representation of size adjectives is beneficial to the task. |
| Tasks | Visual Reasoning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6403/ |
| https://www.aclweb.org/anthology/D19-6403 | |
| PWC | https://paperswithcode.com/paper/big-generalizations-with-small-data-exploring |
| Repo | |
| Framework | |
Linguistic Analysis Improves Neural Metaphor Detection
| Title | Linguistic Analysis Improves Neural Metaphor Detection |
| Authors | Kevin Stowe, Sarah Moeller, Laura Michaelis, Martha Palmer |
| Abstract | In the field of metaphor detection, deep learning systems are the ubiquitous and achieve strong performance on many tasks. However, due to the complicated procedures for manually identifying metaphors, the datasets available are relatively small and fraught with complications. We show that using syntactic features and lexical resources can automatically provide additional high-quality training data for metaphoric language, and this data can cover gaps and inconsistencies in metaphor annotation, improving state-of-the-art word-level metaphor identification. This novel application of automatically improving training data improves classification across numerous tasks, and reconfirms the necessity of high-quality data for deep learning frameworks. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1034/ |
| https://www.aclweb.org/anthology/K19-1034 | |
| PWC | https://paperswithcode.com/paper/linguistic-analysis-improves-neural-metaphor |
| Repo | |
| Framework | |
Infra-slow brain dynamics as a marker for cognitive function and decline
| Title | Infra-slow brain dynamics as a marker for cognitive function and decline |
| Authors | Shagun Ajmera Shyam Sunder Ajmera, Shreya Rajagopal, Razi Rehman, Devarajan Sridharan |
| Abstract | Functional magnetic resonance imaging (fMRI) enables measuring human brain activity, in vivo. Yet, the fMRI hemodynamic response unfolds over very slow timescales (<0.1-1 Hz), orders of magnitude slower than millisecond timescales of neural spiking. It is unclear, therefore, if slow dynamics as measured with fMRI are relevant for cognitive function. We investigated this question with a novel application of Gaussian Process Factor Analysis (GPFA) and machine learning to fMRI data. We analyzed slowly sampled (1.4 Hz) fMRI data from 1000 healthy human participants (Human Connectome Project database), and applied GPFA to reduce dimensionality and extract smooth latent dynamics. GPFA dimensions with slow (<1 Hz) characteristic timescales identified, with high accuracy (>95%), the specific task that each subject was performing inside the fMRI scanner. Moreover, functional connectivity between slow GPFA latents accurately predicted inter-individual differences in behavioral scores across a range of cognitive tasks. Finally, infra-slow (<0.1 Hz) latent dynamics predicted CDR (Clinical Dementia Rating) scores of individual patients, and identified patients with mild cognitive impairment (MCI) who would progress to develop Alzheimer’s dementia (AD). Slow and infra-slow brain dynamics may be relevant for understanding the neural basis of cognitive function, in health and disease. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8918-infra-slow-brain-dynamics-as-a-marker-for-cognitive-function-and-decline |
| http://papers.nips.cc/paper/8918-infra-slow-brain-dynamics-as-a-marker-for-cognitive-function-and-decline.pdf | |
| PWC | https://paperswithcode.com/paper/infra-slow-brain-dynamics-as-a-marker-for |
| Repo | |
| Framework | |
Incorporating Linguistic Constraints into Keyphrase Generation
| Title | Incorporating Linguistic Constraints into Keyphrase Generation |
| Authors | Jing Zhao, Yuxiang Zhang |
| Abstract | Keyphrases, that concisely describe the high-level topics discussed in a document, are very useful for a wide range of natural language processing tasks. Though existing keyphrase generation methods have achieved remarkable performance on this task, they generate many overlapping phrases (including sub-phrases or super-phrases) of keyphrases. In this paper, we propose the parallel Seq2Seq network with the coverage attention to alleviate the overlapping phrase problem. Specifically, we integrate the linguistic constraints of keyphrase into the basic Seq2Seq network on the source side, and employ the multi-task learning framework on the target side. In addition, in order to prevent from generating overlapping phrases of keyphrases with correct syntax, we introduce the coverage vector to keep track of the attention history and to decide whether the parts of source text have been covered by existing generated keyphrases. Experimental results show that our method can outperform the state-of-the-art CopyRNN on scientific datasets, and is also more effective in news domain. |
| Tasks | Multi-Task Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1515/ |
| https://www.aclweb.org/anthology/P19-1515 | |
| PWC | https://paperswithcode.com/paper/incorporating-linguistic-constraints-into |
| Repo | |
| Framework | |
A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings
| Title | A Transparent Framework for Evaluating Unintended Demographic Bias in Word Embeddings |
| Authors | Chris Sweeney, Maryam Najafian |
| Abstract | Word embedding models have gained a lot of traction in the Natural Language Processing community, however, they suffer from unintended demographic biases. Most approaches to evaluate these biases rely on vector space based metrics like the Word Embedding Association Test (WEAT). While these approaches offer great geometric insights into unintended biases in the embedding vector space, they fail to offer an interpretable meaning for how the embeddings could cause discrimination in downstream NLP applications. In this work, we present a transparent framework and metric for evaluating discrimination across protected groups with respect to their word embedding bias. Our metric (Relative Negative Sentiment Bias, RNSB) measures fairness in word embeddings via the relative negative sentiment associated with demographic identity terms from various protected groups. We show that our framework and metric enable useful analysis into the bias in word embeddings. |
| Tasks | Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1162/ |
| https://www.aclweb.org/anthology/P19-1162 | |
| PWC | https://paperswithcode.com/paper/a-transparent-framework-for-evaluating |
| Repo | |
| Framework | |
Online abuse detection: the value of preprocessing and neural attention models
| Title | Online abuse detection: the value of preprocessing and neural attention models |
| Authors | Dhruv Kumar, Robin Cohen, Lukasz Golab |
| Abstract | We propose an attention-based neural network approach to detect abusive speech in online social networks. Our approach enables more effective modeling of context and the semantic relationships between words. We also empirically evaluate the value of text pre-processing techniques in addressing the challenge of out-of-vocabulary words in toxic content. Finally, we conduct extensive experiments on the Wikipedia Talk page datasets, showing improved predictive power over the previous state-of-the-art. |
| Tasks | Abuse Detection |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1303/ |
| https://www.aclweb.org/anthology/W19-1303 | |
| PWC | https://paperswithcode.com/paper/online-abuse-detection-the-value-of |
| Repo | |
| Framework | |
LIUM-MIRACL Participation in the MADAR Arabic Dialect Identification Shared Task
| Title | LIUM-MIRACL Participation in the MADAR Arabic Dialect Identification Shared Task |
| Authors | Sam{'e}h Kchaou, Fethi Bougares, Lamia Hadrich-Belguith |
| Abstract | This paper describes the joint participation of the LIUM and MIRACL Laboratories at the Arabic dialect identification challenge of the MADAR Shared Task (Bouamor et al., 2019) conducted during the Fourth Arabic Natural Language Processing Workshop (WANLP 2019). We participated to the Travel Domain Dialect Identification subtask. We built several systems and explored different techniques including conventional machine learning methods and deep learning algorithms. Deep learning approaches did not perform well on this task. We experimented several classification systems and we were able to identify the dialect of an input sentence with an F1-score of 65.41{%} on the official test set using only the training data supplied by the shared task organizers. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4625/ |
| https://www.aclweb.org/anthology/W19-4625 | |
| PWC | https://paperswithcode.com/paper/lium-miracl-participation-in-the-madar-arabic |
| Repo | |
| Framework | |
