Paper Group NANR 64
Proceedings of the Third Workshop on Semantic Deep Learning. Visual Supervision in Bootstrapped Information Extraction. An Interactive Web-Interface for Visualizing the Inner Workings of the Question Answering LSTM. CEFR-based Lexical Simplification Dataset. Polarimetric Three-View Geometry. MemoReader: Large-Scale Reading Comprehension through Neu …
Proceedings of the Third Workshop on Semantic Deep Learning
| Title | Proceedings of the Third Workshop on Semantic Deep Learning |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4000/ |
| https://www.aclweb.org/anthology/W18-4000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-third-workshop-on-semantic |
| Repo | |
| Framework | |
Visual Supervision in Bootstrapped Information Extraction
| Title | Visual Supervision in Bootstrapped Information Extraction |
| Authors | Matthew Berger, Ajay Nagesh, Joshua Levine, Mihai Surdeanu, Helen Zhang |
| Abstract | We challenge a common assumption in active learning, that a list-based interface populated by informative samples provides for efficient and effective data annotation. We show how a 2D scatterplot populated with diverse and representative samples can yield improved models given the same time budget. We consider this for bootstrapping-based information extraction, in particular named entity classification, where human and machine jointly label data. To enable effective data annotation in a scatterplot, we have developed an embedding-based bootstrapping model that learns the distributional similarity of entities through the patterns that match them in a large data corpus, while being discriminative with respect to human-labeled and machine-promoted entities. We conducted a user study to assess the effectiveness of these different interfaces, and analyze bootstrapping performance in terms of human labeling accuracy, label quantity, and labeling consensus across multiple users. Our results suggest that supervision acquired from the scatterplot interface, despite being noisier, yields improvements in classification performance compared with the list interface, due to a larger quantity of supervision acquired. |
| Tasks | Active Learning |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1229/ |
| https://www.aclweb.org/anthology/D18-1229 | |
| PWC | https://paperswithcode.com/paper/visual-supervision-in-bootstrapped |
| Repo | |
| Framework | |
An Interactive Web-Interface for Visualizing the Inner Workings of the Question Answering LSTM
| Title | An Interactive Web-Interface for Visualizing the Inner Workings of the Question Answering LSTM |
| Authors | Ekaterina Loginova, G{"u}nter Neumann |
| Abstract | We present a visualisation tool which aims to illuminate the inner workings of an LSTM model for question answering. It plots heatmaps of neurons{'} firings and allows a user to check the dependency between neurons and manual features. The system possesses an interactive web-interface and can be adapted to other models and domains. |
| Tasks | Feature Engineering, Machine Translation, Question Answering |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2006/ |
| https://www.aclweb.org/anthology/D18-2006 | |
| PWC | https://paperswithcode.com/paper/an-interactive-web-interface-for-visualizing |
| Repo | |
| Framework | |
CEFR-based Lexical Simplification Dataset
| Title | CEFR-based Lexical Simplification Dataset |
| Authors | Satoru Uchida, Shohei Takada, Yuki Arase |
| Abstract | |
| Tasks | Lexical Simplification, Text Simplification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1514/ |
| https://www.aclweb.org/anthology/L18-1514 | |
| PWC | https://paperswithcode.com/paper/cefr-based-lexical-simplification-dataset |
| Repo | |
| Framework | |
Polarimetric Three-View Geometry
| Title | Polarimetric Three-View Geometry |
| Authors | Lixiong Chen, Yinqiang Zheng, Art Subpa-asa, Imari Sato |
| Abstract | This paper theorizes the connection between polarization and three-view geometry. It presents a ubiquitous polarization-induced constraint that regulates the relative pose of a system of three cameras. We demonstrate that, in a multi-view system, the polarization phase obtained for a surface point is induced from one of the two pencils of planes: one by specular reflections with its axis aligned with the incident light; one by diffusive reflections with its axis aligned with the surface normal. Differing from the traditional three-view geometry, we show that this constraint directly encodes camera rotation and projection, and is independent of camera translation. In theory, six polarized diffusive point-point-point correspondences suffice to determine the camera rotations. In practise, a cross-validation mechanism using correspondences of specularites can effectively resolve the ambiguities caused by mixed polarization. The experiments on real world scenes validate our proposed theory. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Lixiong_Chen_Polarimetric_Three-View_Geometry_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Lixiong_Chen_Polarimetric_Three-View_Geometry_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/polarimetric-three-view-geometry |
| Repo | |
| Framework | |
MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller
| Title | MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller |
| Authors | Seohyun Back, Seunghak Yu, Sathish Reddy Indurthi, Jihie Kim, Jaegul Choo |
| Abstract | Machine reading comprehension helps machines learn to utilize most of the human knowledge written in the form of text. Existing approaches made a significant progress comparable to human-level performance, but they are still limited in understanding, up to a few paragraphs, failing to properly comprehend lengthy document. In this paper, we propose a novel deep neural network architecture to handle a long-range dependency in RC tasks. In detail, our method has two novel aspects: (1) an advanced memory-augmented architecture and (2) an expanded gated recurrent unit with dense connections that mitigate potential information distortion occurring in the memory. Our proposed architecture is widely applicable to other models. We have performed extensive experiments with well-known benchmark datasets such as TriviaQA, QUASAR-T, and SQuAD. The experimental results demonstrate that the proposed method outperforms existing methods, especially for lengthy documents. |
| Tasks | Machine Reading Comprehension, Question Answering, Reading Comprehension |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1237/ |
| https://www.aclweb.org/anthology/D18-1237 | |
| PWC | https://paperswithcode.com/paper/memoreader-large-scale-reading-comprehension |
| Repo | |
| Framework | |
Compact Encoding of Words for Efficient Character-level Convolutional Neural Networks Text Classification
| Title | Compact Encoding of Words for Efficient Character-level Convolutional Neural Networks Text Classification |
| Authors | Wemerson Marinho, Luis Marti, Nayat Sanchez-pi |
| Abstract | This paper puts forward a new text to tensor representation that relies on information compression techniques to assign shorter codes to the most frequently used characters. This representation is language-independent with no need of pretraining and produces an encoding with no information loss. It provides an adequate description of the morphology of text, as it is able to represent prefixes, declensions, and inflections with similar vectors and are able to represent even unseen words on the training dataset. Similarly, as it is compact yet sparse, is ideal for speed up training times using tensor processing libraries. As part of this paper, we show that this technique is especially effective when coupled with convolutional neural networks (CNNs) for text classification at character-level. We apply two variants of CNN coupled with it. Experimental results show that it drastically reduces the number of parameters to be optimized, resulting in competitive classification accuracy values in only a fraction of the time spent by one-hot encoding representations, thus enabling training in commodity hardware. |
| Tasks | Text Classification |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SkYXvCR6W |
| https://openreview.net/pdf?id=SkYXvCR6W | |
| PWC | https://paperswithcode.com/paper/compact-encoding-of-words-for-efficient |
| Repo | |
| Framework | |
Continuous Convolutional Neural Networks for Image Classification
| Title | Continuous Convolutional Neural Networks for Image Classification |
| Authors | Vitor Guizilini, Fabio Ramos |
| Abstract | This paper introduces the concept of continuous convolution to neural networks and deep learning applications in general. Rather than directly using discretized information, input data is first projected into a high-dimensional Reproducing Kernel Hilbert Space (RKHS), where it can be modeled as a continuous function using a series of kernel bases. We then proceed to derive a closed-form solution to the continuous convolution operation between two arbitrary functions operating in different RKHS. Within this framework, convolutional filters also take the form of continuous functions, and the training procedure involves learning the RKHS to which each of these filters is projected, alongside their weight parameters. This results in much more expressive filters, that do not require spatial discretization and benefit from properties such as adaptive support and non-stationarity. Experiments on image classification are performed, using classical datasets, with results indicating that the proposed continuous convolutional neural network is able to achieve competitive accuracy rates with far fewer parameters and a faster convergence rate. |
| Tasks | Image Classification |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BJjBnN9a- |
| https://openreview.net/pdf?id=BJjBnN9a- | |
| PWC | https://paperswithcode.com/paper/continuous-convolutional-neural-networks-for |
| Repo | |
| Framework | |
Video searching and fingerprint detection by using the image query and PlaceNet-based shot boundary detection method
| Title | Video searching and fingerprint detection by using the image query and PlaceNet-based shot boundary detection method |
| Authors | Dayou, Jiang; Jongweon, Kim |
| Abstract | This work presents a novel shot boundary detection (SBD) method based on the Place-centric deep network (PlaceNet), with the aim of using video shots and image queries for video searching (VS) and fingerprint detection. The SBD method has three stages. In the first stage, we employed Local Binary Pattern-Singular Value Decomposition (LBP-SVD) features for candidate shot boundaries selection. In the second stage, we used the PlaceNet to select the shot boundary by semantic labels. In the third stage, we used the Scale-Invariant Feature Transform (SIFT) descriptor to eliminate falsely detected boundaries. The experimental results show that our SBD method is effective on a series of SBD datasets. In addition, video searching experiments are conducted by using one query image instead of video sequences. The results under several image transitions by using shot fingerprints have shown good precision. |
| Tasks | Boundary Detection |
| Published | 2018-09-26 |
| URL | https://www.mendeley.com/catalogue/video-searching-fingerprint-detection-using-image-query-placenetbased-shot-boundary-detection-method/ |
| https://www.mdpi.com/2076-3417/8/10/1735 | |
| PWC | https://paperswithcode.com/paper/video-searching-and-fingerprint-detection-by |
| Repo | |
| Framework | |
Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension
| Title | Multi-Granular Sequence Encoding via Dilated Compositional Units for Reading Comprehension |
| Authors | Yi Tay, Anh Tuan Luu, Siu Cheung Hui |
| Abstract | Sequence encoders are crucial components in many neural architectures for learning to read and comprehend. This paper presents a new compositional encoder for reading comprehension (RC). Our proposed encoder is not only aimed at being fast but also expressive. Specifically, the key novelty behind our encoder is that it explicitly models across multiple granularities using a new dilated composition mechanism. In our approach, gating functions are learned by modeling relationships and reasoning over multi-granular sequence information, enabling compositional learning that is aware of both long and short term information. We conduct experiments on three RC datasets, showing that our proposed encoder demonstrates very promising results both as a standalone encoder as well as a complementary building block. Empirical results show that simple Bi-Attentive architectures augmented with our proposed encoder not only achieves state-of-the-art / highly competitive results but is also considerably faster than other published works. |
| Tasks | Open-Domain Question Answering, Question Answering, Reading Comprehension |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1238/ |
| https://www.aclweb.org/anthology/D18-1238 | |
| PWC | https://paperswithcode.com/paper/multi-granular-sequence-encoding-via-dilated |
| Repo | |
| Framework | |
Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP
| Title | Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP |
| Authors | Edoardo Maria Ponti, Roi Reichart, Anna Korhonen, Ivan Vuli{'c} |
| Abstract | The transfer or share of knowledge between languages is a potential solution to resource scarcity in NLP. However, the effectiveness of cross-lingual transfer can be challenged by variation in syntactic structures. Frameworks such as Universal Dependencies (UD) are designed to be cross-lingually consistent, but even in carefully designed resources trees representing equivalent sentences may not always overlap. In this paper, we measure cross-lingual syntactic variation, or anisomorphism, in the UD treebank collection, considering both morphological and structural properties. We show that reducing the level of anisomorphism yields consistent gains in cross-lingual transfer tasks. We introduce a source language selection procedure that facilitates effective cross-lingual parser transfer, and propose a typologically driven method for syntactic tree processing which reduces anisomorphism. Our results show the effectiveness of this method for both machine translation and cross-lingual sentence similarity, demonstrating the importance of syntactic structure compatibility for boosting cross-lingual transfer in NLP. |
| Tasks | Cross-Lingual Transfer, Machine Translation, Representation Learning, Transfer Learning |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1142/ |
| https://www.aclweb.org/anthology/P18-1142 | |
| PWC | https://paperswithcode.com/paper/isomorphic-transfer-of-syntactic-structures |
| Repo | |
| Framework | |
Identification and Estimation of Causal Effects from Dependent Data
| Title | Identification and Estimation of Causal Effects from Dependent Data |
| Authors | Eli Sherman, Ilya Shpitser |
| Abstract | The assumption that data samples are independent and identically distributed (iid) is standard in many areas of statistics and machine learning. Nevertheless, in some settings, such as social networks, infectious disease modeling, and reasoning with spatial and temporal data, this assumption is false. An extensive literature exists on making causal inferences under the iid assumption [12, 8, 21, 16], but, as pointed out in [14], causal inference in non-iid contexts is challenging due to the combination of unobserved confounding bias and data dependence. In this paper we develop a general theory describing when causal inferences are possible in such scenarios. We use segregated graphs [15], a generalization of latent projection mixed graphs [23], to represent causal models of this type and provide a complete algorithm for non-parametric identification in these models. We then demonstrate how statistical inferences may be performed on causal parameters identified by this algorithm, even in cases where parts of the model exhibit full interference, meaning only a single sample is available for parts of the model [19]. We apply these techniques to a synthetic data set which considers the adoption of fake news articles given the social network structure, articles read by each person, and baseline demographics and socioeconomic covariates. |
| Tasks | Causal Inference |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8153-identification-and-estimation-of-causal-effects-from-dependent-data |
| http://papers.nips.cc/paper/8153-identification-and-estimation-of-causal-effects-from-dependent-data.pdf | |
| PWC | https://paperswithcode.com/paper/identification-and-estimation-of-causal |
| Repo | |
| Framework | |
Uncovering Code-Mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural Based Question Answering
| Title | Uncovering Code-Mixed Challenges: A Framework for Linguistically Driven Question Generation and Neural Based Question Answering |
| Authors | Deepak Gupta, Pabitra Lenka, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | Existing research on question answering (QA) and comprehension reading (RC) are mainly focused on the resource-rich language like English. In recent times, the rapid growth of multi-lingual web content has posed several challenges to the existing QA systems. Code-mixing is one such challenge that makes the task more complex. In this paper, we propose a linguistically motivated technique for code-mixed question generation (CMQG) and a neural network based architecture for code-mixed question answering (CMQA). For evaluation, we manually create the code-mixed questions for Hindi-English language pair. In order to show the effectiveness of our neural network based CMQA technique, we utilize two benchmark datasets, SQuAD and MMQA. Experiments show that our proposed model achieves encouraging performance on CMQG and CMQA. |
| Tasks | Question Answering, Question Generation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-1012/ |
| https://www.aclweb.org/anthology/K18-1012 | |
| PWC | https://paperswithcode.com/paper/uncovering-code-mixed-challenges-a-framework |
| Repo | |
| Framework | |
Possessors Change Over Time: A Case Study with Artworks
| Title | Possessors Change Over Time: A Case Study with Artworks |
| Authors | Dhivya Chinnappa, Eduardo Blanco |
| Abstract | This paper presents a corpus and experimental results to extract possession relations over time. We work with Wikipedia articles about artworks, and extract possession relations along with temporal information indicating when these relations are true. The annotation scheme yields many possessors over time for a given artwork, and experimental results show that an LSTM ensemble can automate the task. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1251/ |
| https://www.aclweb.org/anthology/D18-1251 | |
| PWC | https://paperswithcode.com/paper/possessors-change-over-time-a-case-study-with |
| Repo | |
| Framework | |
A Revised Underwater Image Formation Model
| Title | A Revised Underwater Image Formation Model |
| Authors | Derya Akkaynak, Tali Treibitz |
| Abstract | The current underwater image formation model descends from atmospheric dehazing equations where attenuation is a weak function of wavelength. We recently showed that this model introduces significant errors and dependencies in the estimation of the direct transmission signal because underwater, light attenuates in a wavelength-dependent manner. Here, we show that the backscattered signal derived from the current model also suffers from dependencies that were previously unaccounted for. In doing so, we use oceanographic measurements to derive the physically valid space of backscatter, and further show that the wideband coefficients that govern backscatter are different than those that govern direct transmission, even though the current model treats them to be the same. We propose a revised equation for underwater image formation that takes these differences into account, and validate it through in situ experiments underwater. This revised model might explain frequent instabilities of current underwater color reconstruction models, and calls for the development of new methods. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Akkaynak_A_Revised_Underwater_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Akkaynak_A_Revised_Underwater_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-revised-underwater-image-formation-model |
| Repo | |
| Framework | |
