Paper Group NANR 172
Keynote Lecture 2: Neural (and other Machine Learning) Approaches to Text Normalization. Visualization of Dynamic Reference Graphs. Context Tailoring for Text Normalization. The Limits of Learning with Missing Data. Unsupervised Timeline Generation for Wikipedia History Articles. Tuning Bayes Baseline for Dialect Detection. Learning and Forecasting …
Keynote Lecture 2: Neural (and other Machine Learning) Approaches to Text Normalization
| Title | Keynote Lecture 2: Neural (and other Machine Learning) Approaches to Text Normalization |
| Authors | Richard Sproat |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6323/ |
| https://www.aclweb.org/anthology/W16-6323 | |
| PWC | https://paperswithcode.com/paper/keynote-lecture-2-neural-and-other-machine |
| Repo | |
| Framework | |
Visualization of Dynamic Reference Graphs
| Title | Visualization of Dynamic Reference Graphs |
| Authors | Ivan Rodin, Ekaterina Chernyak, Mikhail Dubov, Boris Mirkin |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1406/ |
| https://www.aclweb.org/anthology/W16-1406 | |
| PWC | https://paperswithcode.com/paper/visualization-of-dynamic-reference-graphs |
| Repo | |
| Framework | |
Context Tailoring for Text Normalization
| Title | Context Tailoring for Text Normalization |
| Authors | Seniz Demir |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1402/ |
| https://www.aclweb.org/anthology/W16-1402 | |
| PWC | https://paperswithcode.com/paper/context-tailoring-for-text-normalization |
| Repo | |
| Framework | |
The Limits of Learning with Missing Data
| Title | The Limits of Learning with Missing Data |
| Authors | Brian Bullins, Elad Hazan, Tomer Koren |
| Abstract | We study regression and classification in a setting where the learning algorithm is allowed to access only a limited number of attributes per example, known as the limited attribute observation model. In this well-studied model, we provide the first lower bounds giving a limit on the precision attainable by any algorithm for several variants of regression, notably linear regression with the absolute loss and the squared loss, as well as for classification with the hinge loss. We complement these lower bounds with a general purpose algorithm that gives an upper bound on the achievable precision limit in the setting of learning with missing data. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6171-the-limits-of-learning-with-missing-data |
| http://papers.nips.cc/paper/6171-the-limits-of-learning-with-missing-data.pdf | |
| PWC | https://paperswithcode.com/paper/the-limits-of-learning-with-missing-data |
| Repo | |
| Framework | |
Unsupervised Timeline Generation for Wikipedia History Articles
| Title | Unsupervised Timeline Generation for Wikipedia History Articles |
| Authors | S Bauer, ro, Simone Teufel |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1259/ |
| https://www.aclweb.org/anthology/D16-1259 | |
| PWC | https://paperswithcode.com/paper/unsupervised-timeline-generation-for |
| Repo | |
| Framework | |
Tuning Bayes Baseline for Dialect Detection
| Title | Tuning Bayes Baseline for Dialect Detection |
| Authors | Hector-Hugo Franco-Penya, Liliana Mamani Sanchez |
| Abstract | This paper describes an analysis of our submissions to the Dialect Detection Shared Task 2016. We proposed three different systems that involved simplistic features, to name: a Naive-bayes system, a Support Vector Machines-based system and a Tree Kernel-based system. These systems underperform when compared to other submissions in this shared task, since the best one achieved an accuracy of {\textasciitilde}0.834. |
| Tasks | Domain Adaptation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4829/ |
| https://www.aclweb.org/anthology/W16-4829 | |
| PWC | https://paperswithcode.com/paper/tuning-bayes-baseline-for-dialect-detection |
| Repo | |
| Framework | |
Learning and Forecasting Opinion Dynamics in Social Networks
| Title | Learning and Forecasting Opinion Dynamics in Social Networks |
| Authors | Abir De, Isabel Valera, Niloy Ganguly, Sourangshu Bhattacharya, Manuel Gomez Rodriguez |
| Abstract | Social media and social networking sites have become a global pinboard for exposition and discussion of news, topics, and ideas, where social media users often update their opinions about a particular topic by learning from the opinions shared by their friends. In this context, can we learn a data-driven model of opinion dynamics that is able to accurately forecast users’ opinions? In this paper, we introduce SLANT, a probabilistic modeling framework of opinion dynamics, which represents users’ opinions over time by means of marked jump diffusion stochastic differential equations, and allows for efficient model simulation and parameter estimation from historical fine grained event data. We then leverage our framework to derive a set of efficient predictive formulas for opinion forecasting and identify conditions under which opinions converge to a steady state. Experiments on data gathered from Twitter show that our model provides a good fit to the data and our formulas achieve more accurate forecasting than alternatives. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6193-learning-and-forecasting-opinion-dynamics-in-social-networks |
| http://papers.nips.cc/paper/6193-learning-and-forecasting-opinion-dynamics-in-social-networks.pdf | |
| PWC | https://paperswithcode.com/paper/learning-and-forecasting-opinion-dynamics-in |
| Repo | |
| Framework | |
Learning Text Similarity with Siamese Recurrent Networks
| Title | Learning Text Similarity with Siamese Recurrent Networks |
| Authors | Paul Neculoiu, Maarten Versteegh, Mihai Rotaru |
| Abstract | |
| Tasks | Recommendation Systems, Representation Learning, Semantic Textual Similarity, Sentiment Analysis |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1617/ |
| https://www.aclweb.org/anthology/W16-1617 | |
| PWC | https://paperswithcode.com/paper/learning-text-similarity-with-siamese |
| Repo | |
| Framework | |
Building the Macedonian-Croatian Parallel Corpus
| Title | Building the Macedonian-Croatian Parallel Corpus |
| Authors | Ines Cebovi{'c}, Marko Tadi{'c} |
| Abstract | In this paper we present the newly created parallel corpus of two under-resourced languages, namely, Macedonian-Croatian Parallel Corpus (mk-hr{_}pcorp) that has been collected during 2015 at the Faculty of Humanities and Social Sciences, University of Zagreb. The mk-hr{_}pcorp is a unidirectional (mk→hr) parallel corpus composed of synchronic fictional prose texts received already in digital form with over 500 Kw in each language. The corpus was sentence segmented and provides 39,735 aligned sentences. The alignment was done automatically and then post-corrected manually. The alignments order was shuffled and this enabled the corpus to be available under CC-BY license through META-SHARE. However, this prevents the research in language units over the sentence level. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1671/ |
| https://www.aclweb.org/anthology/L16-1671 | |
| PWC | https://paperswithcode.com/paper/building-the-macedonian-croatian-parallel |
| Repo | |
| Framework | |
Crowdsourcing a Large Dataset of Domain-Specific Context-Sensitive Semantic Verb Relations
| Title | Crowdsourcing a Large Dataset of Domain-Specific Context-Sensitive Semantic Verb Relations |
| Authors | Maria Sukhareva, Judith Eckle-Kohler, Ivan Habernal, Iryna Gurevych |
| Abstract | We present a new large dataset of 12403 context-sensitive verb relations manually annotated via crowdsourcing. These relations capture fine-grained semantic information between verb-centric propositions, such as temporal or entailment relations. We propose a novel semantic verb relation scheme and design a multi-step annotation approach for scaling-up the annotations using crowdsourcing. We employ several quality measures and report on agreement scores. The resulting dataset is available under a permissive CreativeCommons license at www.ukp.tu-darmstadt.de/data/verb-relations/. It represents a valuable resource for various applications, such as automatic information consolidation or automatic summarization. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1338/ |
| https://www.aclweb.org/anthology/L16-1338 | |
| PWC | https://paperswithcode.com/paper/crowdsourcing-a-large-dataset-of-domain |
| Repo | |
| Framework | |
A study on the production of collocations by European Portuguese learners
| Title | A study on the production of collocations by European Portuguese learners |
| Authors | {^A}ngela Costa, Lu{'\i}sa Coheur, Teresa Lino |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1814/ |
| https://www.aclweb.org/anthology/W16-1814 | |
| PWC | https://paperswithcode.com/paper/a-study-on-the-production-of-collocations-by |
| Repo | |
| Framework | |
The Effects of Data Collection Methods in Twitter
| Title | The Effects of Data Collection Methods in Twitter |
| Authors | Sunghwan Mac Kim, Stephen Wan, C{'e}cile Paris, Brian Jin, Bella Robinson |
| Abstract | |
| Tasks | Keyword Spotting |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5611/ |
| https://www.aclweb.org/anthology/W16-5611 | |
| PWC | https://paperswithcode.com/paper/the-effects-of-data-collection-methods-in |
| Repo | |
| Framework | |
A Framework for Discriminative Rule Selection in Hierarchical Moses
| Title | A Framework for Discriminative Rule Selection in Hierarchical Moses |
| Authors | Fabienne Braune, Alex Fraser, er, Hal Daum{'e} III, Ale{\v{s}} Tamchyna |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2210/ |
| https://www.aclweb.org/anthology/W16-2210 | |
| PWC | https://paperswithcode.com/paper/a-framework-for-discriminative-rule-selection |
| Repo | |
| Framework | |
Semantic Indexing of Multilingual Corpora and its Application on the History Domain
| Title | Semantic Indexing of Multilingual Corpora and its Application on the History Domain |
| Authors | Aless Raganato, ro, Jose Camacho-Collados, Antonio Raganato, Yunseo Joung |
| Abstract | The increasing amount of multilingual text collections available in different domains makes its automatic processing essential for the development of a given field. However, standard processing techniques based on statistical clues and keyword searches have clear limitations. Instead, we propose a knowledge-based processing pipeline which overcomes most of the limitations of these techniques. This, in turn, enables direct comparison across texts in different languages without the need of translation. In this paper we show the potential of this approach for semantically indexing multilingual text collections in the history domain. In our experiments we used a version of the Bible translated in four different languages, evaluating the precision of our semantic indexing pipeline and showing its reliability on the cross-lingual text retrieval task. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4019/ |
| https://www.aclweb.org/anthology/W16-4019 | |
| PWC | https://paperswithcode.com/paper/semantic-indexing-of-multilingual-corpora-and |
| Repo | |
| Framework | |
Minions at SemEval-2016 Task 4: or how to build a sentiment analyzer using off-the-shelf resources?
| Title | Minions at SemEval-2016 Task 4: or how to build a sentiment analyzer using off-the-shelf resources? |
| Authors | C{\u{a}}lin-Cristian Ciubotariu, Marius-Valentin Hri{\c{s}}ca, Mihail Gliga, Diana Daraban{\u{a}}, Tr, Diana ab{\u{a}}{\c{t}}, Adrian Iftene |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1038/ |
| https://www.aclweb.org/anthology/S16-1038 | |
| PWC | https://paperswithcode.com/paper/minions-at-semeval-2016-task-4-or-how-to |
| Repo | |
| Framework | |
