Paper Group NANR 152
Linguistic Resources for Phrasal Verb Identification. Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification. Extracting In-domain Training Corpora for Neural Machine Translation Using Data Selection Methods. A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping. STYLUS: A Resource for Systematically Derived Language Usage …
Linguistic Resources for Phrasal Verb Identification
| Title | Linguistic Resources for Phrasal Verb Identification |
| Authors | Peter Machonis |
| Abstract | This paper shows how a Lexicon-Grammar dictionary of English phrasal verbs (PV) can be transformed into an electronic dictionary, and with the help of multiple grammars, dictionaries, and filters within the linguistic development environment, NooJ, how to accurately identify PV in large corpora. The NooJ program is an alternative to statistical methods commonly used in NLP: all PV are listed in a dictionary and then located by means of a PV grammar in both continuous and discontinuous format. Results are then refined with a series of dictionaries, disambiguating grammars, and other linguistics recourses. The main advantage of such a program is that all PV can be identified in any corpus. The only drawback is that PV not listed in the dictionary (e.g., archaic forms, recent neologisms) are not identified; however, new PV can easily be added to the electronic dictionary, which is freely available to all. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3804/ |
| https://www.aclweb.org/anthology/W18-3804 | |
| PWC | https://paperswithcode.com/paper/linguistic-resources-for-phrasal-verb |
| Repo | |
| Framework | |
Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification
| Title | Viewpoint-Aware Attentive Multi-View Inference for Vehicle Re-Identification |
| Authors | Yi Zhou, Ling Shao |
| Abstract | Vehicle re-identification (re-ID) has the huge potential to contribute to the intelligent video surveillance. However, it suffers from challenges that different vehicle identities with a similar appearance have little inter-instance discrepancy while one vehicle usually has large intra-instance differences under viewpoint and illumination variations. Previous methods address vehicle re-ID by simply using visual features from originally captured views and usually exploit the spatial-temporal information of the vehicles to refine the results. In this paper, we propose a Viewpoint-aware Attentive Multi-view Inference (VAMI) model that only requires visual information to solve the multi-view vehicle re-ID problem. Given vehicle images of arbitrary viewpoints, the VAMI extracts the single-view feature for each input image and aims to transform the features into a global multi-view feature representation so that pairwise distance metric learning can be better optimized in such a viewpoint-invariant feature space. The VAMI adopts a viewpoint-aware attention model to select core regions at different viewpoints and implement effective multi-view feature inference by an adversarial training architecture. Extensive experiments validate the effectiveness of each proposed component and illustrate that our approach achieves consistent improvements over state-of-the-art vehicle re-ID methods on two public datasets: VeRi and VehicleID. |
| Tasks | Metric Learning, Vehicle Re-Identification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhou_Viewpoint-Aware_Attentive_Multi-View_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_Viewpoint-Aware_Attentive_Multi-View_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/viewpoint-aware-attentive-multi-view |
| Repo | |
| Framework | |
Extracting In-domain Training Corpora for Neural Machine Translation Using Data Selection Methods
| Title | Extracting In-domain Training Corpora for Neural Machine Translation Using Data Selection Methods |
| Authors | Catarina Cruz Silva, Chao-Hong Liu, Alberto Poncelas, Andy Way |
| Abstract | Data selection is a process used in selecting a subset of parallel data for the training of machine translation (MT) systems, so that 1) resources for training might be reduced, 2) trained models could perform better than those trained with the whole corpus, and/or 3) trained models are more tailored to specific domains. It has been shown that for statistical MT (SMT), the use of data selection helps improve the MT performance significantly. In this study, we reviewed three data selection approaches for MT, namely Term Frequency{–} Inverse Document Frequency, Cross-Entropy Difference and Feature Decay Algorithm, and conducted experiments on Neural Machine Translation (NMT) with the selected data using the three approaches. The results showed that for NMT systems, using data selection also improved the performance, though the gain is not as much as for SMT systems. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6323/ |
| https://www.aclweb.org/anthology/W18-6323 | |
| PWC | https://paperswithcode.com/paper/extracting-in-domain-training-corpora-for |
| Repo | |
| Framework | |
A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping
| Title | A Hybrid l1-l0 Layer Decomposition Model for Tone Mapping |
| Authors | Zhetong Liang, Jun Xu, David Zhang, Zisheng Cao, Lei Zhang |
| Abstract | Tone mapping aims to reproduce a standard dynamic range image from a high dynamic range image with visual information preserved. State-of-the-art tone mapping algorithms mostly decompose an image into a base layer and a detail layer, and process them accordingly. These methods may have problems of halo artifacts and over-enhancement, due to the lack of proper priors imposed on the two layers. In this paper, we propose a hybrid L1-L0 decomposition model to address these problems. Specifically, an L1 sparsity term is imposed on the base layer to model its piecewise smoothness property. An L0 sparsity term is imposed on the detail layer as a structural prior, which leads to piecewise constant effect. We further propose a multiscale tone mapping scheme based on our layer decomposition model. Experiments show that our tone mapping algorithm achieves visually compelling results with little halo artifacts, outperforming the state-of-the-art tone mapping algorithms in both subjective and objective evaluations. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Liang_A_Hybrid_l1-l0_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Liang_A_Hybrid_l1-l0_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-hybrid-l1-l0-layer-decomposition-model-for |
| Repo | |
| Framework | |
STYLUS: A Resource for Systematically Derived Language Usage
| Title | STYLUS: A Resource for Systematically Derived Language Usage |
| Authors | Bonnie Dorr, Clare Voss |
| Abstract | We describe a resource derived through extraction of a set of argument realizations from an existing lexical-conceptual structure (LCS) Verb Database of 500 verb classes (containing a total of 9525 verb entries) to include information about realization of arguments for a range of different verb classes. We demonstrate that our extended resource, called STYLUS (SysTematicallY Derived Language USe), enables systematic derivation of regular patterns of language usage without requiring manual annotation. We posit that both spatially oriented applications such as robot navigation and more general applications such as narrative generation require a layered representation scheme where a set of primitives (often grounded in space/motion such as GO) is coupled with a representation of constraints at the syntax-semantics interface. We demonstrate that the resulting resource covers three cases of lexico-semantic operations applicable to both language understanding and language generation. |
| Tasks | Dialogue Management, Robot Navigation, Text Generation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3808/ |
| https://www.aclweb.org/anthology/W18-3808 | |
| PWC | https://paperswithcode.com/paper/stylus-a-resource-for-systematically-derived |
| Repo | |
| Framework | |
Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization
| Title | Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization |
| Authors | Haoran Li, Junnan Zhu, Jiajun Zhang, Chengqing Zong |
| Abstract | In this paper, we investigate the sentence summarization task that produces a summary from a source sentence. Neural sequence-to-sequence models have gained considerable success for this task, while most existing approaches only focus on improving the informativeness of the summary, which ignore the correctness, i.e., the summary should not contain unrelated information with respect to the source sentence. We argue that correctness is an essential requirement for summarization systems. Considering a correct summary is semantically entailed by the source sentence, we incorporate entailment knowledge into abstractive summarization models. We propose an entailment-aware encoder under multi-task framework (i.e., summarization generation and entailment recognition) and an entailment-aware decoder by entailment Reward Augmented Maximum Likelihood (RAML) training. Experiment results demonstrate that our models significantly outperform baselines from the aspects of informativeness and correctness. |
| Tasks | Abstractive Sentence Summarization, Abstractive Text Summarization, Text Summarization |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1121/ |
| https://www.aclweb.org/anthology/C18-1121 | |
| PWC | https://paperswithcode.com/paper/ensure-the-correctness-of-the-summary |
| Repo | |
| Framework | |
探討鑑別式訓練聲學模型之類神經網路架構及優化方法的改進 (Discriminative Training of Acoustic Models Leveraging Improved Neural Network Architecture and Optimization Method) [In Chinese]
| Title | 探討鑑別式訓練聲學模型之類神經網路架構及優化方法的改進 (Discriminative Training of Acoustic Models Leveraging Improved Neural Network Architecture and Optimization Method) [In Chinese] |
| Authors | Wei-Cheng Chao, Hsiu-Jui Chang, Tien-Hong Lo, Berlin Chen |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1010/ |
| https://www.aclweb.org/anthology/O18-1010 | |
| PWC | https://paperswithcode.com/paper/e-eaa14e-c-e2a-aa1eccc2e-aaaa13c1e2 |
| Repo | |
| Framework | |
Gold Corpus for Telegraphic Summarization
| Title | Gold Corpus for Telegraphic Summarization |
| Authors | Chanakya Malireddy, Srivenkata N M Somisetty, Manish Shrivastava |
| Abstract | Most extractive summarization techniques operate by ranking all the source sentences and then select the top ranked sentences as the summary. Such methods are known to produce good summaries, especially when applied to news articles and scientific texts. However, they don{'}t fare so well when applied to texts such as fictional narratives, which don{'}t have a single central or recurrent theme. This is because usually the information or plot of the story is spread across several sentences. In this paper, we discuss a different summarization technique called Telegraphic Summarization. Here, we don{'}t select whole sentences, rather pick short segments of text spread across sentences, as the summary. We have tailored a set of guidelines to create such summaries and, using the same, annotate a gold corpus of 200 English short stories. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3810/ |
| https://www.aclweb.org/anthology/W18-3810 | |
| PWC | https://paperswithcode.com/paper/gold-corpus-for-telegraphic-summarization |
| Repo | |
| Framework | |
Pre- and In-Parsing Models for Neural Empty Category Detection
| Title | Pre- and In-Parsing Models for Neural Empty Category Detection |
| Authors | Yufei Chen, Yuanyuan Zhao, Weiwei Sun, Xiaojun Wan |
| Abstract | Motivated by the positive impact of empty category on syntactic parsing, we study neural models for pre- and in-parsing detection of empty category, which has not previously been investigated. We find several non-obvious facts: (a) BiLSTM can capture non-local contextual information which is essential for detecting empty categories, (b) even with a BiLSTM, syntactic information is still able to enhance the detection, and (c) automatic detection of empty categories improves parsing quality for overt words. Our neural ECD models outperform the prior state-of-the-art by significant margins. |
| Tasks | Dependency Parsing, Structured Prediction |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1250/ |
| https://www.aclweb.org/anthology/P18-1250 | |
| PWC | https://paperswithcode.com/paper/pre-and-in-parsing-models-for-neural-empty |
| Repo | |
| Framework | |
Design and Development of Speech Corpora for Air Traffic Control Training
| Title | Design and Development of Speech Corpora for Air Traffic Control Training |
| Authors | Lubo{\v{s}} {\v{S}}m{'\i}dl, Jan {\v{S}}vec, Daniel Tihelka, Jind{\v{r}}ich Matou{\v{s}}ek, Jan Romportl, Pavel Ircing |
| Abstract | |
| Tasks | Speech Recognition, Speech Synthesis, Text-To-Speech Synthesis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1450/ |
| https://www.aclweb.org/anthology/L18-1450 | |
| PWC | https://paperswithcode.com/paper/design-and-development-of-speech-corpora-for |
| Repo | |
| Framework | |
Robust Hough Transform Based 3D Reconstruction From Circular Light Fields
| Title | Robust Hough Transform Based 3D Reconstruction From Circular Light Fields |
| Authors | Alessandro Vianello, Jens Ackermann, Maximilian Diebold, Bernd Jähne |
| Abstract | Light-field imaging is based on images taken on a regular grid. Thus, high-quality 3D reconstructions are obtainable by analyzing orientations in epipolar plane images (EPIs). Unfortunately, such data only allows to evaluate one side of the object. Moreover, a constant intensity along each orientation is mandatory for most of the approaches. This paper presents a novel method which allows to reconstruct depth information from data acquired with a circular camera motion, termed circular light fields. With this approach it is possible to determine the full 360 degree view of target objects. Additionally, circular light fields allow retrieving depth from datasets acquired with telecentric lenses, which is not possible with linear light fields. The proposed method finds trajectories of 3D points in the EPIs by means of a modified Hough transform. For this purpose, binary EPI-edge images are used, which not only allow to obtain reliable depth information, but also overcome the limitation of constant intensity along trajectories. Experimental results on synthetic and real datasets demonstrate the quality of the proposed algorithm. |
| Tasks | 3D Reconstruction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Vianello_Robust_Hough_Transform_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Vianello_Robust_Hough_Transform_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-hough-transform-based-3d |
| Repo | |
| Framework | |
Multi-Scale Weighted Nuclear Norm Image Restoration
| Title | Multi-Scale Weighted Nuclear Norm Image Restoration |
| Authors | Noam Yair, Tomer Michaeli |
| Abstract | A prominent property of natural images is that groups of similar patches within them tend to lie on low-dimensional subspaces. This property has been previously used for image denoising, with particularly notable success via weighted nuclear norm minimization (WNNM). In this paper, we extend the WNNM method into a general image restoration algorithm, capable of handling arbitrary degradations (e.g. blur, missing pixels, etc.). Our approach is based on a novel regularization term which simultaneously penalizes for high weighted nuclear norm values of all the patch groups in the image. Our regularizer is isolated from the data-term, thus enabling convenient treatment of arbitrary degradations. Furthermore, it exploits the fractal property of natural images, by accounting for patch similarities also across different scales of the image. We propose a variable splitting method for solving the resulting optimization problem. This leads to an algorithm that is quite different from `plug-and-play’ techniques, which solve image-restoration problems using a sequence of denoising steps. As we verify through extensive experiments, our algorithm achieves state of the art results in deblurring and inpainting, outperforming even the recent deep net based methods. | |
| Tasks | Deblurring, Denoising, Image Denoising, Image Restoration |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Yair_Multi-Scale_Weighted_Nuclear_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Yair_Multi-Scale_Weighted_Nuclear_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-weighted-nuclear-norm-image |
| Repo | |
| Framework | |
A 2nd Longitudinal Corpus for Children’s Writing with Enhanced Output for Specific Spelling Patterns
| Title | A 2nd Longitudinal Corpus for Children’s Writing with Enhanced Output for Specific Spelling Patterns |
| Authors | Kay Berkling |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1358/ |
| https://www.aclweb.org/anthology/L18-1358 | |
| PWC | https://paperswithcode.com/paper/a-2nd-longitudinal-corpus-for-childrens |
| Repo | |
| Framework | |
Parallel Corpora for bi-Directional Statistical Machine Translation for Seven Ethiopian Language Pairs
| Title | Parallel Corpora for bi-Directional Statistical Machine Translation for Seven Ethiopian Language Pairs |
| Authors | Solomon Teferra Abate, Michael Melese, Martha Yifiru Tachbelie, Million Meshesha, Solomon Atinafu, Wondwossen Mulugeta, Yaregal Assabie, Hafte Abera, Binyam Ephrem, Tewodros Abebe, Wondimagegnhue Tsegaye, Amanuel Lemma, Tsegaye Andargie, Seifedin Shifaw |
| Abstract | In this paper, we describe the development of parallel corpora for Ethiopian Languages: Amharic, Tigrigna, Afan-Oromo, Wolaytta and Geez. To check the usability of all the corpora we conducted baseline bi-directional statistical machine translation (SMT) experiments for seven language pairs. The performance of the bi-directional SMT systems shows that all the corpora can be used for further investigations. We have also shown that the morphological complexity of the Ethio-Semitic languages has a negative impact on the performance of the SMT especially when they are target languages. Based on the results we obtained, we are currently working towards handling the morphological complexities to improve the performance of statistical machine translation among the Ethiopian languages. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3812/ |
| https://www.aclweb.org/anthology/W18-3812 | |
| PWC | https://paperswithcode.com/paper/parallel-corpora-for-bi-directional |
| Repo | |
| Framework | |
SW4ALL: a CEFR Classified and Aligned Corpus for Language Learning
| Title | SW4ALL: a CEFR Classified and Aligned Corpus for Language Learning |
| Authors | Rodrigo Wilkens, Leonardo Zilio, C{'e}drick Fairon |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1055/ |
| https://www.aclweb.org/anthology/L18-1055 | |
| PWC | https://paperswithcode.com/paper/sw4all-a-cefr-classified-and-aligned-corpus |
| Repo | |
| Framework | |
