Paper Group NANR 178
Composing a Picture Book by Automatic Story Understanding and Visualization. Learning to Respond to Mixed-code Queries using Bilingual Word Embeddings. Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm. How to Avoid Sentences Spelling Boring? Towards a Neural Approach to Unsupervised Metaphor Generation. PRINCIPLE: …
Composing a Picture Book by Automatic Story Understanding and Visualization
| Title | Composing a Picture Book by Automatic Story Understanding and Visualization |
| Authors | Xiaoyu Qi, Ruihua Song, Chunting Wang, Jin Zhou, Tetsuya Sakai |
| Abstract | Pictures can enrich storytelling experiences. We propose a framework that can automatically compose a picture book by understanding story text and visualizing it with painting elements, i.e., characters and backgrounds. For story understanding, we extract key information from a story on both sentence level and paragraph level, including characters, scenes and actions. These concepts are organized and visualized in a way that depicts the development of a story. We collect a set of Chinese stories for children and apply our approach to compose pictures for stories. Extensive experiments are conducted towards story event extraction for visualization to demonstrate the effectiveness of our method. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3401/ |
| https://www.aclweb.org/anthology/W19-3401 | |
| PWC | https://paperswithcode.com/paper/composing-a-picture-book-by-automatic-story |
| Repo | |
| Framework | |
Learning to Respond to Mixed-code Queries using Bilingual Word Embeddings
| Title | Learning to Respond to Mixed-code Queries using Bilingual Word Embeddings |
| Authors | Chia-Fang Ho, Jason Chang, Jhih-Jie Chen, Chingyu Yang |
| Abstract | We present a method for learning bilingual word embeddings in order to support second language (L2) learners in finding recurring phrases and example sentences that match mixed-code queries (e.g., {``}接 受 sentence{''}) composed of words in both target language and native language (L1). In our approach, mixed-code queries are transformed into target language queries aimed at maximizing the probability of retrieving relevant target language phrases and sentences. The method involves converting a given parallel corpus into mixed-code data, generating word embeddings from mixed-code data, and expanding queries in target languages based on bilingual word embeddings. We present a prototype search engine, x.Linggle, that applies the method to a linguistic search engine for a parallel corpus. Preliminary evaluation on a list of common word-translation shows that the method performs reasonablly well. | |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4005/ |
| https://www.aclweb.org/anthology/N19-4005 | |
| PWC | https://paperswithcode.com/paper/learning-to-respond-to-mixed-code-queries |
| Repo | |
| Framework | |
Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm
| Title | Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm |
| Authors | Amir-Massoud Farahmand |
| Abstract | This paper considers the problem of estimating the distribution of returns in reinforcement learning (i.e., distributional RL problem). It presents a new representational framework to maintain the uncertainty of returns and provides mathematical tools to compute it. We show that instead of representing a probability distribution function of returns, one can represent their characteristic function instead, the Fourier transform of their distribution. We call the new representation Characteristic Value Function (CVF), which can be interpreted as the frequency domain representation of the probability distribution of returns. We show that the CVF satisfies a Bellman-like equation, and its corresponding Bellman operator is contraction with respect to certain metrics. The contraction property allows us to devise an iterative procedure to compute the CVF, which we call Characteristic Value Iteration (CVI). We analyze CVI and its approximate variant and show how approximation errors affect the quality of computed CVF. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9620-value-function-in-frequency-domain-and-the-characteristic-value-iteration-algorithm |
| http://papers.nips.cc/paper/9620-value-function-in-frequency-domain-and-the-characteristic-value-iteration-algorithm.pdf | |
| PWC | https://paperswithcode.com/paper/value-function-in-frequency-domain-and-the |
| Repo | |
| Framework | |
How to Avoid Sentences Spelling Boring? Towards a Neural Approach to Unsupervised Metaphor Generation
| Title | How to Avoid Sentences Spelling Boring? Towards a Neural Approach to Unsupervised Metaphor Generation |
| Authors | Zhiwei Yu, Xiaojun Wan |
| Abstract | Metaphor generation attempts to replicate human creativity with language, which is an attractive but challengeable text generation task. Previous efforts mainly focus on template-based or rule-based methods and result in a lack of linguistic subtlety. In order to create novel metaphors, we propose a neural approach to metaphor generation and explore the shared inferential structure of a metaphorical usage and a literal usage of a verb. Our approach does not require any manually annotated metaphors for training. We extract the metaphorically used verbs with their metaphorical senses in an unsupervised way and train a neural language model from wiki corpus. Then we generate metaphors conveying the assigned metaphorical senses with an improved decoding algorithm. Automatic metrics and human evaluations demonstrate that our approach can generate metaphors with good readability and creativity. |
| Tasks | Language Modelling, Text Generation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1092/ |
| https://www.aclweb.org/anthology/N19-1092 | |
| PWC | https://paperswithcode.com/paper/how-to-avoid-sentences-spelling-boring |
| Repo | |
| Framework | |
PRINCIPLE: Providing Resources in Irish, Norwegian, Croatian and Icelandic for the Purposes of Language Engineering
| Title | PRINCIPLE: Providing Resources in Irish, Norwegian, Croatian and Icelandic for the Purposes of Language Engineering |
| Authors | Andy Way, Federico Gaspari |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6718/ |
| https://www.aclweb.org/anthology/W19-6718 | |
| PWC | https://paperswithcode.com/paper/principle-providing-resources-in-irish |
| Repo | |
| Framework | |
Monads for hyperintensionality? A situation semantics for hyperintensional side effects
| Title | Monads for hyperintensionality? A situation semantics for hyperintensional side effects |
| Authors | Luke Burke |
| Abstract | We outline a hyperintensional situation semantics in which hyperintensionality is modelled as a {}side effect{'}, as this term has been understood in natural language semantics and in functional programming. We use monads from category theory in order to {}upgrade{'} an ordinary intensional semantics to a possible hyperintensional counterpart. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-1104/ |
| https://www.aclweb.org/anthology/W19-1104 | |
| PWC | https://paperswithcode.com/paper/monads-for-hyperintensionality-a-situation |
| Repo | |
| Framework | |
Weighted posets: Learning surface order from dependency trees
| Title | Weighted posets: Learning surface order from dependency trees |
| Authors | William Dyer |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7807/ |
| https://www.aclweb.org/anthology/W19-7807 | |
| PWC | https://paperswithcode.com/paper/weighted-posets-learning-surface-order-from |
| Repo | |
| Framework | |
Give Me More Feedback II: Annotating Thesis Strength and Related Attributes in Student Essays
| Title | Give Me More Feedback II: Annotating Thesis Strength and Related Attributes in Student Essays |
| Authors | Zixuan Ke, Hrishikesh Inamdar, Hui Lin, Vincent Ng |
| Abstract | While the vast majority of existing work on automated essay scoring has focused on holistic scoring, researchers have recently begun work on scoring specific dimensions of essay quality. Nevertheless, progress on dimension-specific essay scoring is limited in part by the lack of annotated corpora. To facilitate advances in this area, we design a scoring rubric for scoring a core, yet unexplored dimension of persuasive essay quality, thesis strength, and annotate a corpus of essays with thesis strength scores. We additionally identify the attributes that could impact thesis strength and annotate the essays with the values of these attributes, which, when predicted by computational models, could provide further feedback to students on why her essay receives a particular thesis strength score. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1390/ |
| https://www.aclweb.org/anthology/P19-1390 | |
| PWC | https://paperswithcode.com/paper/give-me-more-feedback-ii-annotating-thesis |
| Repo | |
| Framework | |
CSI Peru News: finding the culprit, victim and location in news articles
| Title | CSI Peru News: finding the culprit, victim and location in news articles |
| Authors | Gina Bustamante, Arturo Oncevay |
| Abstract | We introduce a shift on the DS method over the domain of crime-related news from Peru, attempting to find the culprit, victim and location of a crime description from a RE perspective. Obtained results are highly promising and show that proposed modifications are effective in non-traditional domains. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3654/ |
| https://www.aclweb.org/anthology/W19-3654 | |
| PWC | https://paperswithcode.com/paper/csi-peru-news-finding-the-culprit-victim-and |
| Repo | |
| Framework | |
Salient Object Detection With Pyramid Attention and Salient Edges
| Title | Salient Object Detection With Pyramid Attention and Salient Edges |
| Authors | Wenguan Wang, Shuyang Zhao, Jianbing Shen, Steven C. H. Hoi, Ali Borji |
| Abstract | This paper presents a new method for detecting salient objects in images using convolutional neural networks (CNNs). The proposed network, named PAGE-Net, offers two key contributions. The first is the exploitation of an essential pyramid attention structure for salient object detection. This enables the network to concentrate more on salient regions while considering multi-scale saliency information. Such a stacked attention design provides a powerful tool to efficiently improve the representation ability of the corresponding network layer with an enlarged receptive field. The second contribution lies in the emphasis on the importance of salient edges. Salient edge information offers a strong cue to better segment salient objects and refine object boundaries. To this end, our model is equipped with a salient edge detection module, which is learned for precise salient boundary estimation. This encourages better edge-preserving salient object segmentation. Exhaustive experiments confirm that the proposed pyramid attention and salient edges are effective for salient object detection. We show that our deep saliency model outperforms state-of-the-art approaches for several benchmarks with a fast processing speed (25fps on one GPU). |
| Tasks | Edge Detection, Object Detection, Salient Object Detection, Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Salient_Object_Detection_With_Pyramid_Attention_and_Salient_Edges_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Salient_Object_Detection_With_Pyramid_Attention_and_Salient_Edges_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/salient-object-detection-with-pyramid |
| Repo | |
| Framework | |
Collecting domain specific data for MT: an evaluation of the ParaCrawlpipeline
| Title | Collecting domain specific data for MT: an evaluation of the ParaCrawlpipeline |
| Authors | Arne Defauw, Tom Vanallemeersch, Sara Szoc, Frederic Everaert, Koen Van Winckel, Kim Scholte, Joris Brabers, Joachim Van den Bogaert |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6733/ |
| https://www.aclweb.org/anthology/W19-6733 | |
| PWC | https://paperswithcode.com/paper/collecting-domain-specific-data-for-mt-an |
| Repo | |
| Framework | |
Speech technology and Argentinean Welsh
| Title | Speech technology and Argentinean Welsh |
| Authors | Elise Bell |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6903/ |
| https://www.aclweb.org/anthology/W19-6903 | |
| PWC | https://paperswithcode.com/paper/speech-technology-and-argentinean-welsh |
| Repo | |
| Framework | |
Factored Neural Machine Translation at LoResMT 2019
| Title | Factored Neural Machine Translation at LoResMT 2019 |
| Authors | B, Saptarashmi yopadhyay |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6811/ |
| https://www.aclweb.org/anthology/W19-6811 | |
| PWC | https://paperswithcode.com/paper/factored-neural-machine-translation-at |
| Repo | |
| Framework | |
Litigation Analytics: Extracting and querying motions and orders from US federal courts
| Title | Litigation Analytics: Extracting and querying motions and orders from US federal courts |
| Authors | Thomas Vacek, Dezhao Song, Hugo Molina-Salgado, Ronald Teo, Conner Cowling, Frank Schilder |
| Abstract | Legal litigation planning can benefit from statistics collected from past decisions made by judges. Information on the typical duration for a submitted motion, for example, can give valuable clues for developing a successful strategy. Such information is encoded in semi-structured documents called dockets. In order to extract and aggregate this information, we deployed various information extraction and machine learning techniques. The aggregated data can be queried in real time within the Westlaw Edge search engine. In addition to a keyword search for judges, lawyers, law firms, parties and courts, we also implemented a question answering interface that offers targeted questions in order to get to the respective answers quicker. |
| Tasks | Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4020/ |
| https://www.aclweb.org/anthology/N19-4020 | |
| PWC | https://paperswithcode.com/paper/litigation-analytics-extracting-and-querying |
| Repo | |
| Framework | |
ADVISER: A Dialog System Framework for Education & Research
| Title | ADVISER: A Dialog System Framework for Education & Research |
| Authors | Daniel Ortega, Dirk V{"a}th, Gianna Weber, V, Lindsey erlyn, Maximilian Schmidt, Moritz V{"o}lkel, Zorica Karacevic, Ngoc Thang Vu |
| Abstract | In this paper, we present ADVISER - an open source dialog system framework for education and research purposes. This system supports multi-domain task-oriented conversations in two languages. It additionally provides a flexible architecture in which modules can be arbitrarily combined or exchanged - allowing for easy switching between rules-based and neural network based implementations. Furthermore, ADVISER offers a transparent, user-friendly framework designed for interdisciplinary collaboration: from a flexible back end, allowing easy integration of new features, to an intuitive graphical user interface supporting nontechnical users. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-3016/ |
| https://www.aclweb.org/anthology/P19-3016 | |
| PWC | https://paperswithcode.com/paper/adviser-a-dialog-system-framework-for |
| Repo | |
| Framework | |
