Paper Group NANR 24
Phonetically Balanced Code-Mixed Speech Corpus for Hindi-English Automatic Speech Recognition. Introducing the CLARIN Knowledge Centre for Linguistic Diversity and Language Documentation. CAS: French Corpus with Clinical Cases. Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification. RelocNet: Con …
Phonetically Balanced Code-Mixed Speech Corpus for Hindi-English Automatic Speech Recognition
| Title | Phonetically Balanced Code-Mixed Speech Corpus for Hindi-English Automatic Speech Recognition |
| Authors | P, Ayushi ey, Brij Mohan Lal Srivastava, Rohit Kumar, Bhanu Teja Nellore, Kasi Sai Teja, Suryakanth V. Gangashetty |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1235/ |
| https://www.aclweb.org/anthology/L18-1235 | |
| PWC | https://paperswithcode.com/paper/phonetically-balanced-code-mixed-speech |
| Repo | |
| Framework | |
Introducing the CLARIN Knowledge Centre for Linguistic Diversity and Language Documentation
| Title | Introducing the CLARIN Knowledge Centre for Linguistic Diversity and Language Documentation |
| Authors | Hanna Hedeland, Timm Lehmberg, Felix Rau, Sophie Salffner, Mandana Seyfeddinipur, Andreas Witt |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/papers/L18-1370/l18-1370 |
| https://www.aclweb.org/anthology/L18-1370 | |
| PWC | https://paperswithcode.com/paper/introducing-the-clarin-knowledge-centre-for |
| Repo | |
| Framework | |
CAS: French Corpus with Clinical Cases
| Title | CAS: French Corpus with Clinical Cases |
| Authors | Natalia Grabar, Vincent Claveau, Cl{'e}ment Dalloux |
| Abstract | Textual corpora are extremely important for various NLP applications as they provide information necessary for creating, setting and testing these applications and the corresponding tools. They are also crucial for designing reliable methods and reproducible results. Yet, in some areas, such as the medical area, due to confidentiality or to ethical reasons, it is complicated and even impossible to access textual data representative of those produced in these areas. We propose the CAS corpus built with clinical cases, such as they are reported in the published scientific literature in French. We describe this corpus, currently containing over 397,000 word occurrences, and the existing linguistic and semantic annotations. |
| Tasks | Information Retrieval |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5614/ |
| https://www.aclweb.org/anthology/W18-5614 | |
| PWC | https://paperswithcode.com/paper/cas-french-corpus-with-clinical-cases |
| Repo | |
| Framework | |
Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification
| Title | Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification |
| Authors | Mingkuan Liu, Musen Wen, Selcuk Kopru, Xianjing Liu, Alan Lu |
| Abstract | The lack of high-quality labeled training data has been one of the critical challenges facing many industrial machine learning tasks. To tackle this challenge, in this paper, we propose a semi-supervised learning method to utilize unlabeled data and user feedback signals to improve the performance of ML models. The method employs a primary model Main and an auxiliary evaluation model Eval, where Main and Eval models are trained iteratively by automatically generating labeled data from unlabeled data and/or users{'} feedback signals. The proposed approach is applied to different text classification tasks. We report results on both the publicly available Yahoo! Answers dataset and our e-commerce product classification dataset. The experimental results show that the proposed method reduces the classification error rate by 4{%} and up to 15{%} across various experimental setups and datasets. A detailed comparison with other semi-supervised learning approaches is also presented later in the paper. The results from various text classification tasks demonstrate that our method outperforms those developed in previous related studies. |
| Tasks | Machine Translation, Text Classification |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3409/ |
| https://www.aclweb.org/anthology/W18-3409 | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-with-auxiliary |
| Repo | |
| Framework | |
RelocNet: Continuous Metric Learning Relocalisation using Neural Nets
| Title | RelocNet: Continuous Metric Learning Relocalisation using Neural Nets |
| Authors | Vassileios Balntas, Shuda Li, Victor Prisacariu |
| Abstract | We propose a method of learning suitable convolutional representations for camera pose retrieval based on nearest neighbour matching and continuous metric learning-based feature descriptors. We introduce information from camera frusta overlaps between pairs of images to optimise our feature embedding network. Thus, the final camera pose descriptor differences represent camera pose changes. In addition, we build a pose regressor that is trained with a geometric loss to infer finer relative poses between a query and nearest neighbour images. Experiments show that our method is able to generalise in a meaningful way, and outperforms related methods across several experiments. |
| Tasks | Metric Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Vassileios_Balntas_RelocNet_Continous_Metric_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Vassileios_Balntas_RelocNet_Continous_Metric_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/relocnet-continuous-metric-learning |
| Repo | |
| Framework | |
Hierarchical Dirichlet Gaussian Marked Hawkes Process for Narrative Reconstruction in Continuous Time Domain
| Title | Hierarchical Dirichlet Gaussian Marked Hawkes Process for Narrative Reconstruction in Continuous Time Domain |
| Authors | Yeon Seonwoo, Alice Oh, Sungjoon Park |
| Abstract | In news and discussions, many articles and posts are provided without their related previous articles or posts. Hence, it is difficult to understand the context from which the articles and posts have occurred. In this paper, we propose the Hierarchical Dirichlet Gaussian Marked Hawkes process (HD-GMHP) for reconstructing the narratives and thread structures of news articles and discussion posts. HD-GMHP unifies three modeling strategies in previous research: temporal characteristics, triggering event relations, and meta information of text in news articles and discussion threads. To show the effectiveness of the model, we perform experiments in narrative reconstruction and thread reconstruction with real world datasets: articles from the New York Times and a corpus of Wikipedia conversations. The experimental results show that HD-GMHP outperforms the baselines of LDA, HDP, and HDHP for both tasks. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1369/ |
| https://www.aclweb.org/anthology/D18-1369 | |
| PWC | https://paperswithcode.com/paper/hierarchical-dirichlet-gaussian-marked-hawkes |
| Repo | |
| Framework | |
The Power of Ensembles for Active Learning in Image Classification
| Title | The Power of Ensembles for Active Learning in Image Classification |
| Authors | William H. Beluch, Tim Genewein, Andreas Nürnberger, Jan M. Köhler |
| Abstract | Deep learning methods have become the de-facto standard for challenging image processing tasks such as image classification. One major hurdle of deep learning approaches is that large sets of labeled data are necessary, which can be prohibitively costly to obtain, particularly in medical image diagnosis applications. Active learning techniques can alleviate this labeling effort. In this paper we investigate some recently proposed methods for active learning with high-dimensional data and convolutional neural network classifiers. We compare ensemble-based methods against Monte-Carlo Dropout and geometric approaches. We find that ensembles perform better and lead to more calibrated predictive uncertainties, which are the basis for many active learning algorithms. To investigate why Monte-Carlo Dropout uncertainties perform worse, we explore potential differences in isolation in a series of experiments. We show results for MNIST and CIFAR-10, on which we achieve a test set accuracy of $90 %$ with roughly 12,200 labeled images, and initial results on ImageNet. Additionally, we show results on a large, highly class-imbalanced diabetic retinopathy dataset. We observe that the ensemble-based active learning effectively counteracts this imbalance during acquisition. |
| Tasks | Active Learning, Image Classification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Beluch_The_Power_of_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Beluch_The_Power_of_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/the-power-of-ensembles-for-active-learning-in |
| Repo | |
| Framework | |
Neural Storyline Extraction Model for Storyline Generation from News Articles
| Title | Neural Storyline Extraction Model for Storyline Generation from News Articles |
| Authors | Deyu Zhou, Linsen Guo, Yulan He |
| Abstract | Storyline generation aims to extract events described on news articles under a certain news topic and reveal how those events evolve over time. Most approaches to storyline generation first train supervised models to extract events from news articles published in different time periods and then link relevant extracted events into coherent stories. They are domain dependent and cannot deal with unseen event types. To tackle this problem, approaches based on probabilistic graphic models jointly model the generations of events and storylines without the use of annotated data. However, the parameter inference procedure is too complex and models often require long time to converge. In this paper, we propose a novel neural network based approach to extract structured representations and evolution patterns of storylines without using annotated data. In this model, title and main body of a news article are assumed to share the similar storyline distribution. Moreover, similar documents described in neighboring time periods are assumed to share similar storyline distributions. Based on these assumptions, structured representations and evolution patterns of storylines can be extracted. The proposed model has been evaluated on three news corpora and the experimental results show that it outperforms state-of-the-art approaches for storyline generation on both accuracy and efficiency. |
| Tasks | Topic Models |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1156/ |
| https://www.aclweb.org/anthology/N18-1156 | |
| PWC | https://paperswithcode.com/paper/neural-storyline-extraction-model-for |
| Repo | |
| Framework | |
TRAC-1 Shared Task on Aggression Identification: IIT(ISM)@COLING’18
| Title | TRAC-1 Shared Task on Aggression Identification: IIT(ISM)@COLING’18 |
| Authors | Ritesh Kumar, Guggilla Bhanodai, Rajendra Pamula, Maheshwar Reddy Chennuru |
| Abstract | This paper describes the work that our team bhanodaig did at Indian Institute of Technology (ISM) towards TRAC-1 Shared Task on Aggression Identification in Social Media for COLING 2018. In this paper we label aggression identification into three categories: Overtly Aggressive, Covertly Aggressive and Non-aggressive. We train a model to differentiate between these categories and then analyze the results in order to better understand how we can distinguish between them. We participated in two different tasks named as English (Facebook) task and English (Social Media) task. For English (Facebook) task System 05 was our best run (i.e. 0.3572) above the Random Baseline (i.e. 0.3535). For English (Social Media) task our system 02 got the value (i.e. 0.1960) below the Random Bseline (i.e. 0.3477). For all of our runs we used Long Short-Term Memory model. Overall, our performance is not satisfactory. However, as new entrant to the field, our scores are encouraging enough to work for better results in future. |
| Tasks | Transfer Learning, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4407/ |
| https://www.aclweb.org/anthology/W18-4407 | |
| PWC | https://paperswithcode.com/paper/trac-1-shared-task-on-aggression |
| Repo | |
| Framework | |
MAJE Submission to the WMT2018 Shared Task on Parallel Corpus Filtering
| Title | MAJE Submission to the WMT2018 Shared Task on Parallel Corpus Filtering |
| Authors | Marina Fomicheva, Jes{'u}s Gonz{'a}lez-Rubio |
| Abstract | This paper describes the participation of Webinterpret in the shared task on parallel corpus filtering at the Third Conference on Machine Translation (WMT 2018). The paper describes the main characteristics of our approach and discusses the results obtained on the data sets published for the shared task. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6476/ |
| https://www.aclweb.org/anthology/W18-6476 | |
| PWC | https://paperswithcode.com/paper/maje-submission-to-the-wmt2018-shared-task-on |
| Repo | |
| Framework | |
MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models
| Title | MPLP++: Fast, Parallel Dual Block-Coordinate Ascent for Dense Graphical Models |
| Authors | Siddharth Tourani, Alexander Shekhovtsov, Carsten Rother, Bogdan Savchynskyy |
| Abstract | Dense, discrete Graphical Models with pairwise potentials are a powerful class of models which are employed in state-of-the-art computer vision and bio-imaging applications. This work introduces a new MAP-solver, based on the popular Dual Block-Coordinate Ascent principle. Surprisingly, by making a small change to a low-performing solver, the Max Product Linear Programming (MPLP) algorithm, we derive the new solver MPLP++ that significantly outperforms all existing solvers by a large margin, including the state-of-the-art solver Tree-Reweighted Sequential (TRW-S) message-passing algorithm. Additionally, our solver is highly parallel, in contrast to TRW-S, which gives a further boost in performance with the proposed GPU and multi-thread CPU implementations. We verify the superiority of our algorithm on dense problems from publicly available benchmarks, as well, as a new benchmark for 6D Object Pose estimation. We also provide an ablation study with respect to graph density. |
| Tasks | 6D Pose Estimation using RGB, Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Siddharth_Tourani_MPLP_Fast_Parallel_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Siddharth_Tourani_MPLP_Fast_Parallel_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mplp-fast-parallel-dual-block-coordinate |
| Repo | |
| Framework | |
Benefits of Depth for Long-Term Memory of Recurrent Networks
| Title | Benefits of Depth for Long-Term Memory of Recurrent Networks |
| Authors | Yoav Levine, Or Sharir, Amnon Shashua |
| Abstract | The key attribute that drives the unprecedented success of modern Recurrent Neural Networks (RNNs) on learning tasks which involve sequential data, is their ever-improving ability to model intricate long-term temporal dependencies. However, a well established measure of RNNs’ long-term memory capacity is lacking, and thus formal understanding of their ability to correlate data throughout time is limited. Though depth efficiency in convolutional networks is well established by now, it does not suffice in order to account for the success of deep RNNs on inputs of varying lengths, and the need to address their ‘time-series expressive power’ arises. In this paper, we analyze the effect of depth on the ability of recurrent networks to express correlations ranging over long time-scales. To meet the above need, we introduce a measure of the information flow across time that can be supported by the network, referred to as the Start-End separation rank. Essentially, this measure reflects the distance of the function realized by the recurrent network from a function that models no interaction whatsoever between the beginning and end of the input sequence. We prove that deep recurrent networks support Start-End separation ranks which are exponentially higher than those supported by their shallow counterparts. Moreover, we show that the ability of deep recurrent networks to correlate different parts of the input sequence increases exponentially as the input sequence extends, while that of vanilla shallow recurrent networks does not adapt to the sequence length at all. Thus, we establish that depth brings forth an overwhelming advantage in the ability of recurrent networks to model long-term dependencies, and provide an exemplar of quantifying this key attribute which may be readily extended to other RNN architectures of interest, e.g. variants of LSTM networks. We obtain our results by considering a class of recurrent networks referred to as Recurrent Arithmetic Circuits (RACs), which merge the hidden state with the input via the Multiplicative Integration operation. |
| Tasks | Time Series |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJ3d2Ax0- |
| https://openreview.net/pdf?id=HJ3d2Ax0- | |
| PWC | https://paperswithcode.com/paper/benefits-of-depth-for-long-term-memory-of |
| Repo | |
| Framework | |
Syntax Encoding with Application in Authorship Attribution
| Title | Syntax Encoding with Application in Authorship Attribution |
| Authors | Richong Zhang, Zhiyuan Hu, Hongyu Guo, Yongyi Mao |
| Abstract | We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation. The proposed syntax encoding scheme is provably information-lossless. In specific, an embedding vector is constructed for each word in the sentence, encoding the path in the syntax tree corresponding to the word. The one-to-one correspondence between these {``}syntax-embedding{''} vectors and the words (hence their embedding vectors) in the sentence makes it easy to integrate such a representation with all word-level NLP models. We empirically show the benefits of the syntax embeddings on the Authorship Attribution domain, where our approach improves upon the prior art and achieves new performance records on five benchmarking data sets. | |
| Tasks | Feature Engineering, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1294/ |
| https://www.aclweb.org/anthology/D18-1294 | |
| PWC | https://paperswithcode.com/paper/syntax-encoding-with-application-in |
| Repo | |
| Framework | |
BinLin: A Simple Method of Dependency Tree Linearization
| Title | BinLin: A Simple Method of Dependency Tree Linearization |
| Authors | Yevgeniy Puzikov, Iryna Gurevych |
| Abstract | Surface Realization Shared Task 2018 is a workshop on generating sentences from lemmatized sets of dependency triples. This paper describes the results of our participation in the challenge. We develop a data-driven pipeline system which first orders the lemmas and then conjugates the words to finish the surface realization process. Our contribution is a novel sequential method of ordering lemmas, which, despite its simplicity, achieves promising results. We demonstrate the effectiveness of the proposed approach, describe its limitations and outline ways to improve it. |
| Tasks | Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3602/ |
| https://www.aclweb.org/anthology/W18-3602 | |
| PWC | https://paperswithcode.com/paper/binlin-a-simple-method-of-dependency-tree |
| Repo | |
| Framework | |
Neural User Simulation for Corpus-based Policy Optimisation of Spoken Dialogue Systems
| Title | Neural User Simulation for Corpus-based Policy Optimisation of Spoken Dialogue Systems |
| Authors | Florian Kreyssig, I{~n}igo Casanueva, Pawe{\l} Budzianowski, Milica Ga{\v{s}}i{'c} |
| Abstract | User Simulators are one of the major tools that enable offline training of task-oriented dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The ABUS is based on hand-crafted rules and its output is in semantic form. Issues arise from both properties such as limited diversity and the inability to interface a text-level belief tracker. This paper introduces the Neural User Simulator (NUS) whose behaviour is learned from a corpus and which generates natural language, hence needing a less labelled dataset than simulators generating a semantic output. In comparison to much of the past work on this topic, which evaluates user simulators on corpus-based metrics, we use the NUS to train the policy of a reinforcement learning based Spoken Dialogue System. The NUS is compared to the ABUS by evaluating the policies that were trained using the simulators. Cross-model evaluation is performed i.e. training on one simulator and testing on the other. Furthermore, the trained policies are tested on real users. In both evaluation tasks the NUS outperformed the ABUS. |
| Tasks | Dialogue Management, Spoken Dialogue Systems, Task-Oriented Dialogue Systems |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5007/ |
| https://www.aclweb.org/anthology/W18-5007 | |
| PWC | https://paperswithcode.com/paper/neural-user-simulation-for-corpus-based |
| Repo | |
| Framework | |
