Paper Group NANR 62
Generating Paraphrases with Lean Vocabulary. Reflection Removal Using a Dual-Pixel Sensor. Legal Linking: Citation Resolution and Suggestion in Constitutional Law. Multi-level analysis and recognition of the text sentiment on the example of consumer opinions. Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing. …
Generating Paraphrases with Lean Vocabulary
| Title | Generating Paraphrases with Lean Vocabulary |
| Authors | Tadashi Nomoto |
| Abstract | In this work, we examine whether it is possible to achieve the state of the art performance in paraphrase generation with reduced vocabulary. Our approach consists of building a convolution to sequence model (Conv2Seq) partially guided by the reinforcement learning, and training it on the subword representation of the input. The experiment on the Quora dataset, which contains over 140,000 pairs of sentences and corresponding paraphrases, found that with less than 1,000 token types, we were able to achieve performance which exceeded that of the current state of the art. |
| Tasks | Paraphrase Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8655/ |
| https://www.aclweb.org/anthology/W19-8655 | |
| PWC | https://paperswithcode.com/paper/generating-paraphrases-with-lean-vocabulary |
| Repo | |
| Framework | |
Reflection Removal Using a Dual-Pixel Sensor
| Title | Reflection Removal Using a Dual-Pixel Sensor |
| Authors | Abhijith Punnappurath, Michael S. Brown |
| Abstract | Reflection removal is the challenging problem of removing unwanted reflections that occur when imaging a scene that is behind a pane of glass. In this paper, we show that most cameras have an overlooked mechanism that can greatly simplify this task. Specifically, modern DLSR and smartphone cameras use dual pixel (DP) sensors that have two photodiodes per pixel to provide two sub-aperture views of the scene from a single captured image. “Defocus-disparity” cues, which are natural by-products of the DP sensor encoded within these two sub-aperture views, can be used to distinguish between image gradients belonging to the in-focus background and those caused by reflection interference. This gradient information can then be incorporated into an optimization framework to recover the background layer with higher accuracy than currently possible from the single captured image. As part of this work, we provide the first image dataset for reflection removal consisting of the sub-aperture views from the DP sensor. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Punnappurath_Reflection_Removal_Using_a_Dual-Pixel_Sensor_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Punnappurath_Reflection_Removal_Using_a_Dual-Pixel_Sensor_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/reflection-removal-using-a-dual-pixel-sensor |
| Repo | |
| Framework | |
Legal Linking: Citation Resolution and Suggestion in Constitutional Law
| Title | Legal Linking: Citation Resolution and Suggestion in Constitutional Law |
| Authors | Robert Shaffer, Stephen Mayhew |
| Abstract | This paper describes a dataset and baseline systems for linking paragraphs from court cases to clauses or amendments in the US Constitution. We implement a rule-based system, a linear model, and a neural architecture for matching pairs of paragraphs, taking training data from online databases in a distantly-supervised fashion. In experiments on a manually-annotated evaluation set, we find that our proposed neural system outperforms a rules-driven baseline. Qualitatively, this performance gap seems largest for abstract or indirect links between documents, which suggests that our system might be useful for answering political science and legal research questions or discovering novel links. We release the dataset along with the manually-annotated evaluation set to foster future work. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2205/ |
| https://www.aclweb.org/anthology/W19-2205 | |
| PWC | https://paperswithcode.com/paper/legal-linking-citation-resolution-and |
| Repo | |
| Framework | |
Multi-level analysis and recognition of the text sentiment on the example of consumer opinions
| Title | Multi-level analysis and recognition of the text sentiment on the example of consumer opinions |
| Authors | Jan Koco{'n}, Monika Za{'s}ko-Zieli{'n}ska, Piotr Mi{\l}kowski |
| Abstract | In this article, we present a novel multi-domain dataset of Polish text reviews, annotated with sentiment on different levels: sentences and the whole documents. The annotation was made by linguists in a 2+1 scheme (with inter-annotator agreement analysis). We present a preliminary approach to the classification of labelled data using logistic regression, bidirectional long short-term memory recurrent neural networks (BiLSTM) and bidirectional encoder representations from transformers (BERT). |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1066/ |
| https://www.aclweb.org/anthology/R19-1066 | |
| PWC | https://paperswithcode.com/paper/multi-level-analysis-and-recognition-of-the |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
| Title | Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6000/ |
| https://www.aclweb.org/anthology/D19-6000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-16 |
| Repo | |
| Framework | |
Using Syntax to Resolve NPE in English
| Title | Using Syntax to Resolve NPE in English |
| Authors | Payal Khullar, Allen Antony, Manish Shrivastava |
| Abstract | This paper describes a novel, syntax-based system for automatic detection and resolution of Noun Phrase Ellipsis (NPE) in English. The system takes in free input English text, detects the site of nominal elision, and if present, selects potential antecedent candidates. The rules are built using the syntactic information on ellipsis and its antecedent discussed in previous theoretical linguistics literature on NPE. Additionally, we prepare a curated dataset of 337 sentences from well-known, reliable sources, containing positive and negative samples of NPE. We split this dataset into two parts, and use one part to refine our rules and the other to test the performance of our final system. We get an F1-score of 76.47{%} for detection and 70.27{%} for NPE resolution on the testset. To the best of our knowledge, ours is the first system that detects and resolves NPE in English. The curated dataset used for this task, albeit small, covers a wide variety of NPE cases and will be made public for future work. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1063/ |
| https://www.aclweb.org/anthology/R19-1063 | |
| PWC | https://paperswithcode.com/paper/using-syntax-to-resolve-npe-in-english |
| Repo | |
| Framework | |
Real World Voice Assistant System for Cooking
| Title | Real World Voice Assistant System for Cooking |
| Authors | Takahiko Ito, Shintaro Inuzuka, Yoshiaki Yamada, Jun Harashima |
| Abstract | This study presents a voice assistant system to support cooking by utilizing smart speakers in Japan. This system not only speaks the procedures written in recipes point by point but also answers the common questions from users for the specified recipes. The system applies machine comprehension techniques to millions of recipes for answering the common questions in cooking such as {``}人参はどうしたらよいですか (How should I cook carrots?){''}. Furthermore, numerous machine-learning techniques are applied to generate better responses to users. | |
| Tasks | Reading Comprehension |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8663/ |
| https://www.aclweb.org/anthology/W19-8663 | |
| PWC | https://paperswithcode.com/paper/real-world-voice-assistant-system-for-cooking |
| Repo | |
| Framework | |
Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation
| Title | Proceedings of the Workshop on Methods for Optimizing and Evaluating Neural Language Generation |
| Authors | |
| Abstract | |
| Tasks | Text Generation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2300/ |
| https://www.aclweb.org/anthology/W19-2300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-methods-for |
| Repo | |
| Framework | |
How to Compare Summarizers without Target Length? Pitfalls, Solutions and Re-Examination of the Neural Summarization Literature
| Title | How to Compare Summarizers without Target Length? Pitfalls, Solutions and Re-Examination of the Neural Summarization Literature |
| Authors | Simeng Sun, Ori Shapira, Ido Dagan, Ani Nenkova |
| Abstract | We show that plain ROUGE F1 scores are not ideal for comparing current neural systems which on average produce different lengths. This is due to a non-linear pattern between ROUGE F1 and summary length. To alleviate the effect of length during evaluation, we have proposed a new method which normalizes the ROUGE F1 scores of a system by that of a random system with same average output length. A pilot human evaluation has shown that humans prefer short summaries in terms of the verbosity of a summary but overall consider longer summaries to be of higher quality. While human evaluations are more expensive in time and resources, it is clear that normalization, such as the one we proposed for automatic evaluation, will make human evaluations more meaningful. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2303/ |
| https://www.aclweb.org/anthology/W19-2303 | |
| PWC | https://paperswithcode.com/paper/how-to-compare-summarizers-without-target |
| Repo | |
| Framework | |
Online Distilling from Checkpoints for Neural Machine Translation
| Title | Online Distilling from Checkpoints for Neural Machine Translation |
| Authors | Hao-Ran Wei, Shujian Huang, Ran Wang, Xin-yu Dai, Jiajun Chen |
| Abstract | Current predominant neural machine translation (NMT) models often have a deep structure with large amounts of parameters, making these models hard to train and easily suffering from over-fitting. A common practice is to utilize a validation set to evaluate the training process and select the best checkpoint. Average and ensemble techniques on checkpoints can lead to further performance improvement. However, as these methods do not affect the training process, the system performance is restricted to the checkpoints generated in original training procedure. In contrast, we propose an online knowledge distillation method. Our method on-the-fly generates a teacher model from checkpoints, guiding the training process to obtain better performance. Experiments on several datasets and language pairs show steady improvement over a strong self-attention-based baseline system. We also provide analysis on data-limited setting against over-fitting. Furthermore, our method leads to an improvement in a machine reading experiment as well. |
| Tasks | Machine Translation, Reading Comprehension |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1192/ |
| https://www.aclweb.org/anthology/N19-1192 | |
| PWC | https://paperswithcode.com/paper/online-distilling-from-checkpoints-for-neural |
| Repo | |
| Framework | |
Variational recurrent models for representation learning
| Title | Variational recurrent models for representation learning |
| Authors | Qingming Tang, Mingda Chen, Weiran Wang, Karen Livescu |
| Abstract | We study the problem of learning representations of sequence data. Recent work has built on variational autoencoders to develop variational recurrent models for generation. Our main goal is not generation but rather representation learning for downstream prediction tasks. Existing variational recurrent models typically use stochastic recurrent connections to model the dependence among neighboring latent variables, while generation assumes independence of generated data per time step given the latent sequence. In contrast, our models assume independence among all latent variables given non-stochastic hidden states, which speeds up inference, while assuming dependence of observations at each time step on all latent variables, which improves representation quality. In addition, we propose and study extensions for improving downstream performance, including hierarchical auxiliary latent variables and prior updating during training. Experiments show improved performance on several speech and language tasks with different levels of supervision, as well as in a multi-view learning setting. |
| Tasks | MULTI-VIEW LEARNING, Representation Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkxCenR5F7 |
| https://openreview.net/pdf?id=HkxCenR5F7 | |
| PWC | https://paperswithcode.com/paper/variational-recurrent-models-for |
| Repo | |
| Framework | |
Are the Tools up to the Task? an Evaluation of Commercial Dialog Tools in Developing Conversational Enterprise-grade Dialog Systems
| Title | Are the Tools up to the Task? an Evaluation of Commercial Dialog Tools in Developing Conversational Enterprise-grade Dialog Systems |
| Authors | Marie Meteer, Meghan Hickey, Carmi Rothberg, David Nahamoo, Ellen Eide Kislal |
| Abstract | There has been a significant investment in dialog systems (tools and runtime) for building conversational systems by major companies including Google, IBM, Microsoft, and Amazon. The question remains whether these tools are up to the task of building conversational, task-oriented dialog applications at the enterprise level. In our company, we are exploring and comparing several toolsets in an effort to determine their strengths and weaknesses in meeting our goals for dialog system development: accuracy, time to market, ease of replicating and extending applications, and efficiency and ease of use by developers. In this paper, we provide both quantitative and qualitative results in three main areas: natural language understanding, dialog, and text generation. While existing toolsets were all incomplete, we hope this paper will provide a roadmap of where they need to go to meet the goal of building effective dialog systems. |
| Tasks | Text Generation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2014/ |
| https://www.aclweb.org/anthology/N19-2014 | |
| PWC | https://paperswithcode.com/paper/are-the-tools-up-to-the-task-an-evaluation-of |
| Repo | |
| Framework | |
Measuring text readability with machine comprehension: a pilot study
| Title | Measuring text readability with machine comprehension: a pilot study |
| Authors | Marc Benzahra, Fran{\c{c}}ois Yvon |
| Abstract | This article studies the relationship between text readability indice and automatic machine understanding systems. Our hypothesis is that the simpler a text is, the better it should be understood by a machine. We thus expect to a strong correlation between readability levels on the one hand, and performance of automatic reading systems on the other hand. We test this hypothesis with several understanding systems based on language models of varying strengths, measuring this correlation on two corpora of journalistic texts. Our results suggest that this correlation is rather small that existing comprehension systems are far to reproduce the gradual improvement of their performance on texts of decreasing complexity. |
| Tasks | Reading Comprehension |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4443/ |
| https://www.aclweb.org/anthology/W19-4443 | |
| PWC | https://paperswithcode.com/paper/measuring-text-readability-with-machine |
| Repo | |
| Framework | |
A fully automated periodicity detection in time series
| Title | A fully automated periodicity detection in time series |
| Authors | Tom Puech, Matthieu Boussard |
| Abstract | This paper presents a method to autonomously find periodicities in a signal. It is based on the same idea of using Fourier Transform and autocorrelation function presented in Vlachos et al. 2005. While showing interesting results this method does not perform well on noisy signals or signals with multiple periodicities. Thus, our method adds several new extra steps (hints clustering, filtering and detrending) to fix these issues. Experimental results show that the proposed method outperforms the state of the art algorithms. |
| Tasks | Time Series |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJMCdsC5tX |
| https://openreview.net/pdf?id=HJMCdsC5tX | |
| PWC | https://paperswithcode.com/paper/a-fully-automated-periodicity-detection-in |
| Repo | |
| Framework | |
Secrecy Rate Maximization for Intelligent Reflecting Surface Assisted Multi-Antenna Communications
| Title | Secrecy Rate Maximization for Intelligent Reflecting Surface Assisted Multi-Antenna Communications |
| Authors | Hong Shen;Wei Xu;Shulei Gong;Zhenyao He;Chunming Zhao |
| Abstract | We investigate transmission optimization for intelligent reflecting surface (IRS) assisted multi-antenna systems from the physical-layer security perspective. The design goal is to maximize the system secrecy rate subject to the source transmit power constraint and the unit modulus constraints imposed on phase shifts at the IRS. To solve this complicated non-convex problem, we develop an efficient alternating algorithm where the solutions to the transmit covariance of the source and the phase shift matrix of the IRS are achieved in closed form and semi-closed forms, respectively. The convergence of the proposed algorithm is guaranteed theoretically. Simulations results validate the performance advantage of the proposed optimized design. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1905.10075 |
| https://arxiv.org/pdf/1905.10075.pdf | |
| PWC | https://paperswithcode.com/paper/secrecy-rate-maximization-for-intelligent |
| Repo | |
| Framework | |
