Paper Group NANR 162
Neural Conversation Model Controllable by Given Dialogue Act Based on Adversarial Learning and Label-aware Objective. Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing. Cross-lingual morphological inflection with explicit alignment. Improved resistance of neural networks to adversarial images through generative …
Neural Conversation Model Controllable by Given Dialogue Act Based on Adversarial Learning and Label-aware Objective
| Title | Neural Conversation Model Controllable by Given Dialogue Act Based on Adversarial Learning and Label-aware Objective |
| Authors | Seiya Kawano, Koichiro Yoshino, Satoshi Nakamura |
| Abstract | Building a controllable neural conversation model (NCM) is an important task. In this paper, we focus on controlling the responses of NCMs by using dialogue act labels of responses as conditions. We introduce an adversarial learning framework for the task of generating conditional responses with a new objective to a discriminator, which explicitly distinguishes sentences by using labels. This change strongly encourages the generation of label-conditioned sentences. We compared the proposed method with some existing methods for generating conditional responses. The experimental results show that our proposed method has higher controllability for dialogue acts even though it has higher or comparable naturalness to existing methods. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8627/ |
| https://www.aclweb.org/anthology/W19-8627 | |
| PWC | https://paperswithcode.com/paper/neural-conversation-model-controllable-by |
| Repo | |
| Framework | |
Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing
| Title | Proceedings of the First NLPL Workshop on Deep Learning for Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6200/ |
| https://www.aclweb.org/anthology/W19-6200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-nlpl-workshop-on |
| Repo | |
| Framework | |
Cross-lingual morphological inflection with explicit alignment
| Title | Cross-lingual morphological inflection with explicit alignment |
| Authors | {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin |
| Abstract | This paper describes two related systems for cross-lingual morphological inflection for SIGMORPHON 2019 Shared Task participation. Both sets of results submitted to the shared task for evaluation are obtained using a simple approach of predicting transducer actions based on initial alignments on the training set, where cross-lingual transfer is limited to only using the high-resource language data as additional training set. The performance of the system does not reach the performance of the top two systems in the competition. However, we show that results can be improved with further tuning. We also present further analyses demonstrating that the cross-lingual gain is rather modest. |
| Tasks | Cross-Lingual Transfer, Morphological Inflection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4209/ |
| https://www.aclweb.org/anthology/W19-4209 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-morphological-inflection-with |
| Repo | |
| Framework | |
Improved resistance of neural networks to adversarial images through generative pre-training
| Title | Improved resistance of neural networks to adversarial images through generative pre-training |
| Authors | Joachim Wabnig |
| Abstract | We train a feed forward neural network with increased robustness against adversarial attacks compared to conventional training approaches. This is achieved using a novel pre-trained building block based on a mean field description of a Boltzmann machine. On the MNIST dataset the method achieves strong adversarial resistance without data augmentation or adversarial training. We show that the increased adversarial resistance is correlated with the generative performance of the underlying Boltzmann machine. |
| Tasks | Data Augmentation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJlEUoR9Km |
| https://openreview.net/pdf?id=HJlEUoR9Km | |
| PWC | https://paperswithcode.com/paper/improved-resistance-of-neural-networks-to |
| Repo | |
| Framework | |
MuST-C: a Multilingual Speech Translation Corpus
| Title | MuST-C: a Multilingual Speech Translation Corpus |
| Authors | Mattia A. Di Gangi, Roldano Cattoni, Luisa Bentivogli, Matteo Negri, Marco Turchi |
| Abstract | Current research on spoken language translation (SLT) has to confront with the scarcity of sizeable and publicly available training corpora. This problem hinders the adoption of neural end-to-end approaches, which represent the state of the art in the two parent tasks of SLT: automatic speech recognition and machine translation. To fill this gap, we created MuST-C, a multilingual speech translation corpus whose size and quality will facilitate the training of end-to-end systems for SLT from English into 8 languages. For each target language, MuST-C comprises at least 385 hours of audio recordings from English TED Talks, which are automatically aligned at the sentence level with their manual transcriptions and translations. Together with a description of the corpus creation methodology (scalable to add new data and cover new languages), we provide an empirical verification of its quality and SLT results computed with a state-of-the-art approach on each language direction. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1202/ |
| https://www.aclweb.org/anthology/N19-1202 | |
| PWC | https://paperswithcode.com/paper/must-c-a-multilingual-speech-translation |
| Repo | |
| Framework | |
Polarimetric Camera Calibration Using an LCD Monitor
| Title | Polarimetric Camera Calibration Using an LCD Monitor |
| Authors | Zhixiang Wang, Yinqiang Zheng, Yung-Yu Chuang |
| Abstract | It is crucial for polarimetric imaging to accurately calibrate the polarizer angles and the camera response function (CRF) of a polarizing camera. When this polarizing camera is used in a setting of multiview geometric imaging, it is often required to calibrate its intrinsic and extrinsic parameters as well, for which Zhang’s calibration method is the most widely used with either a physical checker board, or more conveniently a virtual checker pattern displayed on a monitor. In this paper, we propose to jointly calibrate the polarizer angles and the inverse CRF (ICRF) using a slightly adapted checker pattern displayed on a liquid crystal display (LCD) monitor. Thanks to the lighting principles and the industry standards of the LCD monitors, the polarimetric and radiometric calibration can be significantly simplified, when assisted by the extrinsic parameters estimated from the checker pattern. We present a simple linear method for polarizer angle calibration and a convex method for radiometric calibration, both of which can be jointly refined in a process similar to bundle adjustment. Experiments have verified the feasibility and accuracy of the proposed calibration method. |
| Tasks | Calibration |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Polarimetric_Camera_Calibration_Using_an_LCD_Monitor_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Polarimetric_Camera_Calibration_Using_an_LCD_Monitor_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/polarimetric-camera-calibration-using-an-lcd |
| Repo | |
| Framework | |
Red-faced ROUGE: Examining the Suitability of ROUGE for Opinion Summary Evaluation
| Title | Red-faced ROUGE: Examining the Suitability of ROUGE for Opinion Summary Evaluation |
| Authors | Wenyi Tay, Aditya Joshi, Xiuzhen Zhang, Sarvnaz Karimi, Stephen Wan |
| Abstract | One of the most common metrics to automatically evaluate opinion summaries is ROUGE, a metric developed for text summarisation. ROUGE counts the overlap of word or word units between a candidate summary against reference summaries. This formulation treats all words in the reference summary equally.In opinion summaries, however, not all words in the reference are equally important. Opinion summarisation requires to correctly pair two types of semantic information: (1) aspect or opinion target; and (2) polarity of candidate and reference summaries. We investigate the suitability of ROUGE for evaluating opin-ion summaries of online reviews. Using three simulation-based experiments, we evaluate the behaviour of ROUGE for opinion summarisation on the ability to match aspect and polarity. We show that ROUGE cannot distinguish opinion summaries of similar or opposite polarities for the same aspect. Moreover,ROUGE scores have significant variance under different configuration settings. As a result, we present three recommendations for future work that uses ROUGE to evaluate opinion summarisation. |
| Tasks | |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1008/ |
| https://www.aclweb.org/anthology/U19-1008 | |
| PWC | https://paperswithcode.com/paper/red-faced-rouge-examining-the-suitability-of |
| Repo | |
| Framework | |
Adversarial Semantic Alignment for Improved Image Captions
| Title | Adversarial Semantic Alignment for Improved Image Captions |
| Authors | Pierre Dognin, Igor Melnyk, Youssef Mroueh, Jerret Ross, Tom Sercu |
| Abstract | In this paper, we study image captioning as a conditional GAN training, proposing both a context-aware LSTM captioner and co-attentive discriminator, which enforces semantic alignment between images and captions. We empirically focus on the viability of two training methods: Self-critical Sequence Training (SCST) and Gumbel Straight-Through (ST) and demonstrate that SCST shows more stable gradient behavior and improved results over Gumbel ST, even without accessing discriminator gradients directly. We also address the problem of automatic evaluation for captioning models and introduce a new semantic score, and show its correlation to human judgement. As an evaluation paradigm, we argue that an important criterion for a captioner is the ability to generalize to compositions of objects that do not usually co-occur together. To this end, we introduce a small captioned Out of Context (OOC) test set. The OOC set, combined with our semantic score, are the proposed new diagnosis tools for the captioning community. When evaluated on OOC and MS-COCO benchmarks, we show that SCST-based training has a strong performance in both semantic score and human evaluation, promising to be a valuable new approach for efficient discrete GAN training. |
| Tasks | Image Captioning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Dognin_Adversarial_Semantic_Alignment_for_Improved_Image_Captions_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Dognin_Adversarial_Semantic_Alignment_for_Improved_Image_Captions_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-semantic-alignment-for-improved |
| Repo | |
| Framework | |
Fast and Discriminative Semantic Embedding
| Title | Fast and Discriminative Semantic Embedding |
| Authors | Rob Koopman, Shenghui Wang, Gwenn Englebienne |
| Abstract | The embedding of words and documents in compact, semantically meaningful vector spaces is a crucial part of modern information systems. Deep Learning models are powerful but their hyperparameter selection is often complex and they are expensive to train, and while pre-trained models are available, embeddings trained on general corpora are not necessarily well-suited to domain specific tasks. We propose a novel embedding method which extends random projection by weighting and projecting raw term embeddings orthogonally to an average language vector, thus improving the discriminating power of resulting term embeddings, and build more meaningful document embeddings by assigning appropriate weights to individual terms. We describe how updating the term embeddings online as we process the training data results in an extremely efficient method, in terms of both computational and memory requirements. Our experiments show highly competitive results with various state-of-the-art embedding methods on different tasks, including the standard STS benchmark and a subject prediction task, at a fraction of the computational cost. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0420/ |
| https://www.aclweb.org/anthology/W19-0420 | |
| PWC | https://paperswithcode.com/paper/fast-and-discriminative-semantic-embedding |
| Repo | |
| Framework | |
Learning to Refer to 3D Objects with Natural Language
| Title | Learning to Refer to 3D Objects with Natural Language |
| Authors | Panos Achlioptas, Judy E. Fan, Robert X.D. Hawkins, Noah D. Goodman, Leo Guibas |
| Abstract | Human world knowledge is both structured and flexible. When people see an object, they represent it not as a pixel array but as a meaningful arrangement of semantic parts. Moreover, when people refer to an object, they provide descriptions that are not merely true but also relevant in the current context. Here, we combine these two observations in order to learn fine-grained correspondences between language and contextually relevant geometric properties of 3D objects. To do this, we employed an interactive communication task with human participants to construct a large dataset containing natural utterances referring to 3D objects from ShapeNet in a wide variety of contexts. Using this dataset, we developed neural listener and speaker models with strong capacity for generalization. By performing targeted lesions of visual and linguistic input, we discovered that the neural listener depends heavily on part-related words and associates these words correctly with the corresponding geometric properties of objects, suggesting that it has learned task-relevant structure linking the two input modalities. We further show that a neural speaker that is listener-aware' --- that plans its utterances according to how an imagined listener would interpret its words in context --- produces more discriminative referring expressions than an listener-unaware’ speaker, as measured by human performance in identifying the correct object. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkgZ3oR9FX |
| https://openreview.net/pdf?id=rkgZ3oR9FX | |
| PWC | https://paperswithcode.com/paper/learning-to-refer-to-3d-objects-with-natural |
| Repo | |
| Framework | |
Deep Generative Models for learning Coherent Latent Representations from Multi-Modal Data
| Title | Deep Generative Models for learning Coherent Latent Representations from Multi-Modal Data |
| Authors | Timo Korthals, Marc Hesse, Jürgen Leitner |
| Abstract | The application of multi-modal generative models by means of a Variational Auto Encoder (VAE) is an upcoming research topic for sensor fusion and bi-directional modality exchange. This contribution gives insights into the learned joint latent representation and shows that expressiveness and coherence are decisive properties for multi-modal datasets. Furthermore, we propose a multi-modal VAE derived from the full joint marginal log-likelihood that is able to learn the most meaningful representation for ambiguous observations. Since the properties of multi-modal sensor setups are essential for our approach but hardly available, we also propose a technique to generate correlated datasets from uni-modal ones. |
| Tasks | Sensor Fusion |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJl8FoRcY7 |
| https://openreview.net/pdf?id=rJl8FoRcY7 | |
| PWC | https://paperswithcode.com/paper/deep-generative-models-for-learning-coherent |
| Repo | |
| Framework | |
From Insanely Jealous to Insanely Delicious: Computational Models for the Semantic Bleaching of English Intensifiers
| Title | From Insanely Jealous to Insanely Delicious: Computational Models for the Semantic Bleaching of English Intensifiers |
| Authors | Yiwei Luo, Dan Jurafsky, Beth Levin |
| Abstract | We introduce novel computational models for modeling semantic bleaching, a widespread category of change in which words become more abstract or lose elements of meaning, like the development of {}arrive{''} from its earlier meaning {`}become at shore.{'} We validate our methods on a widespread case of bleaching in English: de-adjectival adverbs that originate as manner adverbs (as in {}awfully behaved{''}) and later become intensifying adverbs (as in {}awfully nice{''}). Our methods formally quantify three reflexes of bleaching: decreasing similarity to the source meaning (e.g., {}awful{''}), increasing similarity to a fully bleached prototype (e.g., {}very{''}), and increasing productivity (e.g., the breadth of adjectives that an adverb modifies). We also test a new causal model and find evidence that bleaching is initially triggered in contexts such as {}conspicuously evident{''} and {}insanely jealous{''}, where an adverb premodifies a semantically similar adjective. These contexts provide a form of {}bridging context{''} (Evans and Wilkins, 2000) that allow a manner adverb to be reinterpreted as an intensifying adverb similar to {``}very{''}. | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4701/ |
| https://www.aclweb.org/anthology/W19-4701 | |
| PWC | https://paperswithcode.com/paper/from-insanely-jealous-to-insanely-delicious |
| Repo | |
| Framework | |
Spatially Variant Linear Representation Models for Joint Filtering
| Title | Spatially Variant Linear Representation Models for Joint Filtering |
| Authors | Jinshan Pan, Jiangxin Dong, Jimmy S. Ren, Liang Lin, Jinhui Tang, Ming-Hsuan Yang |
| Abstract | Joint filtering mainly uses an additional guidance image as a prior and transfers its structures to the target image in the filtering process. Different from existing algorithms that rely on locally linear models or hand-designed objective functions to extract the structural information from the guidance image, we propose a new joint filter based on a spatially variant linear representation model (SVLRM), where the target image is linearly represented by the guidance image. However, the SVLRM leads to a highly ill-posed problem. To estimate the linear representation coefficients, we develop an effective algorithm based on a deep convolutional neural network (CNN). The proposed deep CNN (constrained by the SVLRM) is able to estimate the spatially variant linear representation coefficients which are able to model the structural information of both the guidance and input images. We show that the proposed algorithm can be effectively applied to a variety of applications, including depth/RGB image upsampling and restoration, flash/no-flash image deblurring, natural image denoising, scale-aware filtering, etc. Extensive experimental results demonstrate that the proposed algorithm performs favorably against state-of-the-art methods that have been specially designed for each task. |
| Tasks | Deblurring, Denoising, Image Denoising |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Pan_Spatially_Variant_Linear_Representation_Models_for_Joint_Filtering_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Pan_Spatially_Variant_Linear_Representation_Models_for_Joint_Filtering_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spatially-variant-linear-representation |
| Repo | |
| Framework | |
Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus
| Title | Multi-lingual Wikipedia Summarization and Title Generation On Low Resource Corpus |
| Authors | Wei Liu, Lei Li, Zuying Huang, Yinan Liu |
| Abstract | MultiLing 2019 Headline Generation Task on Wikipedia Corpus raised a critical and practical problem: multilingual task on low resource corpus. In this paper we proposed QDAS extractive summarization model enhanced by sentence2vec and try to apply transfer learning based on large multilingual pre-trained language model for Wikipedia Headline Generation task. We treat it as sequence labeling task and develop two schemes to handle with it. Experimental results have shown that large pre-trained model can effectively utilize learned knowledge to extract certain phrase using low resource supervised data. |
| Tasks | Language Modelling, Transfer Learning |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8904/ |
| https://www.aclweb.org/anthology/W19-8904 | |
| PWC | https://paperswithcode.com/paper/multi-lingual-wikipedia-summarization-and |
| Repo | |
| Framework | |
Blind Image Deblurring With Local Maximum Gradient Prior
| Title | Blind Image Deblurring With Local Maximum Gradient Prior |
| Authors | Liang Chen, Faming Fang, Tingting Wang, Guixu Zhang |
| Abstract | Blind image deblurring aims to recover sharp image from a blurred one while the blur kernel is unknown. To solve this ill-posed problem, a great amount of image priors have been explored and employed in this area. In this paper, we present a blind deblurring method based on Local Maximum Gradient (LMG) prior. Our work is inspired by the simple and intuitive observation that the maximum value of a local patch gradient will diminish after the blur process, which is proved to be true both mathematically and empirically. This inherent property of blur process helps us to establish a new energy function. By introducing an liner operator to compute the Local Maximum Gradient, together with an effective optimization scheme, our method can handle various specific scenarios. Extensive experimental results illustrate that our method is able to achieve favorable performance against state-of-the-art algorithms on both synthetic and real-world images. |
| Tasks | Blind Image Deblurring, Deblurring |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Chen_Blind_Image_Deblurring_With_Local_Maximum_Gradient_Prior_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_Blind_Image_Deblurring_With_Local_Maximum_Gradient_Prior_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/blind-image-deblurring-with-local-maximum |
| Repo | |
| Framework | |
