Paper Group NANR 67
Sentence Alignment Methods for Improving Text Simplification Systems. The TALP-UPC Neural Machine Translation System for German/Finnish-English Using the Inverse Direction Model in Rescoring. Digital Watermarking Model for CityGML. Code-Switching as a Social Act: The Case of Arabic Wikipedia Talk Pages. Waldayu and Waldayu Mobile: Modern digital di …
Sentence Alignment Methods for Improving Text Simplification Systems
| Title | Sentence Alignment Methods for Improving Text Simplification Systems |
| Authors | Sanja {\v{S}}tajner, Marc Franco-Salvador, Simone Paolo Ponzetto, Paolo Rosso, Heiner Stuckenschmidt |
| Abstract | We provide several methods for sentence-alignment of texts with different complexity levels. Using the best of them, we sentence-align the Newsela corpora, thus providing large training materials for automatic text simplification (ATS) systems. We show that using this dataset, even the standard phrase-based statistical machine translation models for ATS can outperform the state-of-the-art ATS systems. |
| Tasks | Lexical Simplification, Machine Translation, Text Simplification, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2016/ |
| https://www.aclweb.org/anthology/P17-2016 | |
| PWC | https://paperswithcode.com/paper/sentence-alignment-methods-for-improving-text |
| Repo | |
| Framework | |
The TALP-UPC Neural Machine Translation System for German/Finnish-English Using the Inverse Direction Model in Rescoring
| Title | The TALP-UPC Neural Machine Translation System for German/Finnish-English Using the Inverse Direction Model in Rescoring |
| Authors | Carlos Escolano, Marta R. Costa-juss{`a}, Jos{'e} A. R. Fonollosa |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4725/ |
| https://www.aclweb.org/anthology/W17-4725 | |
| PWC | https://paperswithcode.com/paper/the-talp-upc-neural-machine-translation |
| Repo | |
| Framework | |
Digital Watermarking Model for CityGML
| Title | Digital Watermarking Model for CityGML |
| Authors | Jongweon, Kim |
| Abstract | The geospatial information is getting more important as autonomous navigation technology is applied to moving objects such as automobiles and drones. In addition, examples of using spatial information in virtual reality augmented reality, and games are increasing. CityGML is an international standard for effectively representing 3D geospatial information. As more applications using geospatial information appear, the controversy over copyright infringement is also increasing. Despite the controversy over copyright infringement, CityGML still does not study the technology for copyright protection. In this paper, we propose a digital watermarking model for copyright protection of CityGML and analyze the technical requirements of the model. |
| Tasks | Autonomous Navigation |
| Published | 2017-10-01 |
| URL | http://macrojournals.com/yahoo_site_admin/assets/docs/1TI17Ki.225555.pdf |
| http://macrojournals.com/yahoo_site_admin/assets/docs/1TI17Ki.225555.pdf | |
| PWC | https://paperswithcode.com/paper/digital-watermarking-model-for-citygml |
| Repo | |
| Framework | |
Code-Switching as a Social Act: The Case of Arabic Wikipedia Talk Pages
| Title | Code-Switching as a Social Act: The Case of Arabic Wikipedia Talk Pages |
| Authors | Michael Yoder, Shruti Rijhwani, Carolyn Ros{'e}, Lori Levin |
| Abstract | Code-switching has been found to have social motivations in addition to syntactic constraints. In this work, we explore the social effect of code-switching in an online community. We present a task from the Arabic Wikipedia to capture language choice, in this case code-switching between Arabic and other languages, as a predictor of social influence in collaborative editing. We find that code-switching is positively associated with Wikipedia editor success, particularly borrowing technical language on pages with topics less directly related to Arabic-speaking regions. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2911/ |
| https://www.aclweb.org/anthology/W17-2911 | |
| PWC | https://paperswithcode.com/paper/code-switching-as-a-social-act-the-case-of |
| Repo | |
| Framework | |
Waldayu and Waldayu Mobile: Modern digital dictionary interfaces for endangered languages
| Title | Waldayu and Waldayu Mobile: Modern digital dictionary interfaces for endangered languages |
| Authors | Patrick Littell, Aidan Pine, Henry Davis |
| Abstract | |
| Tasks | |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0119/ |
| https://www.aclweb.org/anthology/W17-0119 | |
| PWC | https://paperswithcode.com/paper/waldayu-and-waldayu-mobile-modern-digital |
| Repo | |
| Framework | |
Grounding Language for Interactive Task Learning
| Title | Grounding Language for Interactive Task Learning |
| Authors | Peter Lindes, Aaron Mininger, James R. Kirk, John E. Laird |
| Abstract | This paper describes how language is grounded by a comprehension system called Lucia within a robotic agent called Rosie that can manipulate objects and navigate indoors. The whole system is built within the Soar cognitive architecture and uses Embodied Construction Grammar (ECG) as a formalism for describing linguistic knowledge. Grounding is performed using knowledge from the grammar itself, from the linguistic context, from the agents perception, and from an ontology of long-term knowledge about object categories and properties and actions the agent can perform. The paper also describes a benchmark corpus of 200 sentences in this domain along with test versions of the world model and ontology and gold-standard meanings for each of the sentences. The benchmark is contained in the supplemental materials. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2801/ |
| https://www.aclweb.org/anthology/W17-2801 | |
| PWC | https://paperswithcode.com/paper/grounding-language-for-interactive-task |
| Repo | |
| Framework | |
Unsupervised Text Segmentation Based on Native Language Characteristics
| Title | Unsupervised Text Segmentation Based on Native Language Characteristics |
| Authors | Shervin Malmasi, Mark Dras, Mark Johnson, Lan Du, Magdalena Wolska |
| Abstract | Most work on segmenting text does so on the basis of topic changes, but it can be of interest to segment by other, stylistically expressed characteristics such as change of authorship or native language. We propose a Bayesian unsupervised text segmentation approach to the latter. While baseline models achieve essentially random segmentation on our task, indicating its difficulty, a Bayesian model that incorporates appropriately compact language models and alternating asymmetric priors can achieve scores on the standard metrics around halfway to perfect segmentation. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1134/ |
| https://www.aclweb.org/anthology/P17-1134 | |
| PWC | https://paperswithcode.com/paper/unsupervised-text-segmentation-based-on |
| Repo | |
| Framework | |
What Makes Popular Culture Popular? Product Features and Optimal Differentiation in Music
| Title | What Makes Popular Culture Popular? Product Features and Optimal Differentiation in Music |
| Authors | Noah Askin, Michael Mauskapf |
| Abstract | In this article, we propose a new explanation for why certain cultural products outperform their peers to achieve widespread success. We argue that products’ position in feature space significantly predicts their popular success. Using tools from computer science, we construct a novel dataset allowing us to examine whether the musical features of nearly 27,000 songs from Billboard’s Hot 100 charts predict their levels of success in this cultural market. We find that, in addition to artist familiarity, genre affiliation, and institutional support, a song’s perceived proximity to its peers influences its position on the charts. Contrary to the claim that all popular music sounds the same, we find that songs sounding too much like previous and contemporaneous productions—those that are highly typical—are less likely to succeed. Songs exhibiting some degree of optimal differentiation are more likely to rise to the top of the charts. These findings offer a new perspective on success in cultural markets by specifying how content organizes product competition and audience consumption behavior. |
| Tasks | |
| Published | 2017-09-06 |
| URL | https://journals.sagepub.com/doi/full/10.1177/0003122417728662 |
| https://journals.sagepub.com/doi/full/10.1177/0003122417728662 | |
| PWC | https://paperswithcode.com/paper/what-makes-popular-culture-popular-product |
| Repo | |
| Framework | |
Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values
| Title | Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values |
| Authors | Chaoxu Zhou, Wenbo Gao, Donald Goldfarb |
| Abstract | We propose a novel class of stochastic, adaptive methods for minimizing self-concordant functions which can be expressed as an expected value. These methods generate an estimate of the true objective function by taking the empirical mean over a sample drawn at each step, making the problem tractable. The use of adaptive step sizes eliminates the need for the user to supply a step size. Methods in this class include extensions of gradient descent (GD) and BFGS. We show that, given a suitable amount of sampling, the stochastic adaptive GD attains linear convergence in expectation, and with further sampling, the stochastic adaptive BFGS attains R-superlinear convergence. We present experiments showing that these methods compare favorably to SGD. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=856 |
| http://proceedings.mlr.press/v70/zhou17a/zhou17a.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-adaptive-quasi-newton-methods-for |
| Repo | |
| Framework | |
Morphological Inflection Generation with Multi-space Variational Encoder-Decoders
| Title | Morphological Inflection Generation with Multi-space Variational Encoder-Decoders |
| Authors | Chunting Zhou, Graham Neubig |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Morphological Inflection |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-2005/ |
| https://www.aclweb.org/anthology/K17-2005 | |
| PWC | https://paperswithcode.com/paper/morphological-inflection-generation-with |
| Repo | |
| Framework | |
Seq2seq for Morphological Reinflection: When Deep Learning Fails
| Title | Seq2seq for Morphological Reinflection: When Deep Learning Fails |
| Authors | Hajime Senuma, Akiko Aizawa |
| Abstract | |
| Tasks | Machine Translation, Morphological Inflection, Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-2011/ |
| https://www.aclweb.org/anthology/K17-2011 | |
| PWC | https://paperswithcode.com/paper/seq2seq-for-morphological-reinflection-when |
| Repo | |
| Framework | |
CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
| Title | CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies |
| Authors | Daniel Zeman, Martin Popel, Milan Straka, Jan Haji{\v{c}}, Joakim Nivre, Filip Ginter, Juhani Luotolahti, Sampo Pyysalo, Slav Petrov, Martin Potthast, Francis Tyers, Elena Badmaeva, Memduh Gokirmak, Anna Nedoluzhko, Silvie Cinkov{'a}, Jan Haji{\v{c}} jr., Jaroslava Hlav{'a}{\v{c}}ov{'a}, V{'a}clava Kettnerov{'a}, Zde{\v{n}}ka Ure{\v{s}}ov{'a}, Jenna Kanerva, Stina Ojala, Anna Missil{"a}, Christopher D. Manning, Sebastian Schuster, Siva Reddy, Dima Taji, Nizar Habash, Herman Leung, Marie-Catherine de Marneffe, Manuela Sanguinetti, Maria Simi, Hiroshi Kanayama, Valeria de Paiva, Kira Droganova, H{'e}ctor Mart{'\i}nez Alonso, {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin, Umut Sulubacak, Hans Uszkoreit, Vivien Macketanz, Aljoscha Burchardt, Kim Harris, Katrin Marheinecke, Georg Rehm, Tolga Kayadelen, Mohammed Attia, Ali Elkahky, Zhuoran Yu, Emily Pitler, Saran Lertpradit, M, Michael l, Jesse Kirchner, Hector Fern Alcalde, ez, Jana Strnadov{'a}, Esha Banerjee, Ruli Manurung, Antonio Stella, Atsuko Shimada, Sookyoung Kwak, Gustavo Mendon{\c{c}}a, L, Tatiana o, Rattima Nitisaroj, Josie Li |
| Abstract | The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets. In 2017, the task was devoted to learning dependency parsers for a large number of languages, in a real-world setting without any gold-standard annotation on input. All test sets followed a unified annotation scheme, namely that of Universal Dependencies. In this paper, we define the task and evaluation methodology, describe how the data sets were prepared, report and analyze the main results, and provide a brief categorization of the different approaches of the participating systems. |
| Tasks | Dependency Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3001/ |
| https://www.aclweb.org/anthology/K17-3001 | |
| PWC | https://paperswithcode.com/paper/conll-2017-shared-task-multilingual-parsing |
| Repo | |
| Framework | |
Abstractive Document Summarization with a Graph-Based Attentional Neural Model
| Title | Abstractive Document Summarization with a Graph-Based Attentional Neural Model |
| Authors | Jiwei Tan, Xiaojun Wan, Jianguo Xiao |
| Abstract | Abstractive summarization is the ultimate goal of document summarization research, but previously it is less investigated due to the immaturity of text generation techniques. Recently impressive progress has been made to abstractive sentence summarization using neural models. Unfortunately, attempts on abstractive document summarization are still in a primitive stage, and the evaluation results are worse than extractive methods on benchmark datasets. In this paper, we review the difficulties of neural abstractive document summarization, and propose a novel graph-based attention mechanism in the sequence-to-sequence framework. The intuition is to address the saliency factor of summarization, which has been overlooked by prior works. Experimental results demonstrate our model is able to achieve considerable improvement over previous neural abstractive models. The data-driven neural abstractive method is also competitive with state-of-the-art extractive methods. |
| Tasks | Abstractive Sentence Summarization, Abstractive Text Summarization, Document Summarization, Image Captioning, Machine Translation, Text Generation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1108/ |
| https://www.aclweb.org/anthology/P17-1108 | |
| PWC | https://paperswithcode.com/paper/abstractive-document-summarization-with-a |
| Repo | |
| Framework | |
Question Generation for Language Learning: From ensuring texts are read to supporting learning
| Title | Question Generation for Language Learning: From ensuring texts are read to supporting learning |
| Authors | Maria Chinkina, Detmar Meurers |
| Abstract | In Foreign Language Teaching and Learning (FLTL), questions are systematically used to assess the learner{'}s understanding of a text. Computational linguistic approaches have been developed to generate such questions automatically given a text (e.g., Heilman, 2011). In this paper, we want to broaden the perspective on the different functions questions can play in FLTL and discuss how automatic question generation can support the different uses. Complementing the focus on meaning and comprehension, we want to highlight the fact that questions can also be used to make learners notice form aspects of the linguistic system and their interpretation. Automatically generating questions that target linguistic forms and grammatical categories in a text in essence supports incidental focus-on-form (Loewen, 2005) in a meaning-focused reading task. We discuss two types of questions serving this purpose, how they can be generated automatically; and we report on a crowd-sourcing evaluation comparing automatically generated to manually written questions targeting particle verbs, a challenging linguistic form for learners of English. |
| Tasks | Decision Making, Language Acquisition, Question Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5038/ |
| https://www.aclweb.org/anthology/W17-5038 | |
| PWC | https://paperswithcode.com/paper/question-generation-for-language-learning |
| Repo | |
| Framework | |
Towards Improving Abstractive Summarization via Entailment Generation
| Title | Towards Improving Abstractive Summarization via Entailment Generation |
| Authors | Ramakanth Pasunuru, Han Guo, Mohit Bansal |
| Abstract | Abstractive summarization, the task of rewriting and compressing a document into a short summary, has achieved considerable success with neural sequence-to-sequence models. However, these models can still benefit from stronger natural language inference skills, since a correct summary is logically entailed by the input document, i.e., it should not contain any contradictory or unrelated information. We incorporate such knowledge into an abstractive summarization model via multi-task learning, where we share its decoder parameters with those of an entailment generation model. We achieve promising initial improvements based on multiple metrics and datasets (including a test-only setting). The domain mismatch between the entailment (captions) and summarization (news) datasets suggests that the model is learning some domain-agnostic inference skills. |
| Tasks | Abstractive Text Summarization, Machine Translation, Multi-Task Learning, Natural Language Inference |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4504/ |
| https://www.aclweb.org/anthology/W17-4504 | |
| PWC | https://paperswithcode.com/paper/towards-improving-abstractive-summarization |
| Repo | |
| Framework | |
