May 4, 2019

1437 words 7 mins read

Paper Group NANR 198

Spanish NER with Word Representations and Conditional Random Fields. Regulating Orthography-Phonology Relationship for English to Thai Transliteration. Constructing a Japanese Basic Named Entity Corpus of Various Genres. Pronoun Prediction with Latent Anaphora Resolution. Distributed representation and estimation of WFST-based n-gram models. Segmen …

Spanish NER with Word Representations and Conditional Random Fields


Title	Spanish NER with Word Representations and Conditional Random Fields
Authors	Jenny Linet Copara Zea, Jose Eduardo Ochoa Luna, Camilo Thorne, Goran Glava{\v{s}}
Abstract
Tasks	Word Embeddings
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2705/
PDF	https://www.aclweb.org/anthology/W16-2705
PWC	https://paperswithcode.com/paper/spanish-ner-with-word-representations-and
Repo
Framework

Regulating Orthography-Phonology Relationship for English to Thai Transliteration


Title	Regulating Orthography-Phonology Relationship for English to Thai Transliteration
Authors	Binh Minh Nguyen, Hoang Gia Ngo, Nancy F. Chen
Abstract
Tasks	Machine Translation, Transliteration
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2712/
PDF	https://www.aclweb.org/anthology/W16-2712
PWC	https://paperswithcode.com/paper/regulating-orthography-phonology-relationship
Repo
Framework

Constructing a Japanese Basic Named Entity Corpus of Various Genres


Title	Constructing a Japanese Basic Named Entity Corpus of Various Genres
Authors	Tomoya Iwakura, Kanako Komiya, Ryuichi Tachibana
Abstract
Tasks	Information Retrieval, Question Answering
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2706/
PDF	https://www.aclweb.org/anthology/W16-2706
PWC	https://paperswithcode.com/paper/constructing-a-japanese-basic-named-entity
Repo
Framework

Pronoun Prediction with Latent Anaphora Resolution


Title	Pronoun Prediction with Latent Anaphora Resolution
Authors	Christian Hardmeier
Abstract
Tasks	Coreference Resolution, Language Modelling, Machine Translation
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2350/
PDF	https://www.aclweb.org/anthology/W16-2350
PWC	https://paperswithcode.com/paper/pronoun-prediction-with-latent-anaphora
Repo
Framework

Distributed representation and estimation of WFST-based n-gram models


Title	Distributed representation and estimation of WFST-based n-gram models
Authors	Cyril Allauzen, Michael Riley, Brian Roark
Abstract
Tasks	Language Modelling, Machine Translation, Speech Recognition
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2404/
PDF	https://www.aclweb.org/anthology/W16-2404
PWC	https://paperswithcode.com/paper/distributed-representation-and-estimation-of
Repo
Framework

Segment-Level Sequence Modeling using Gated Recursive Semi-Markov Conditional Random Fields


Title	Segment-Level Sequence Modeling using Gated Recursive Semi-Markov Conditional Random Fields
Authors	Jingwei Zhuo, Yong Cao, Jun Zhu, Bo Zhang, Zaiqing Nie
Abstract
Tasks	Chunking, Named Entity Recognition
Published	2016-08-01
URL	https://www.aclweb.org/anthology/P16-1134/
PDF	https://www.aclweb.org/anthology/P16-1134
PWC	https://paperswithcode.com/paper/segment-level-sequence-modeling-using-gated
Repo
Framework

Compilation of an Arabic Children’s Corpus


Title	Compilation of an Arabic Children’s Corpus
Authors	Latifa Al-Sulaiti, Noorhan Abbas, Claire Brierley, Eric Atwell, Ayman Alghamdi
Abstract	Inspired by the Oxford Children{'}s Corpus, we have developed a prototype corpus of Arabic texts written and/or selected for children. Our Arabic Children{'}s Corpus of 2950 documents and nearly 2 million words has been collected manually from the web during a 3-month project. It is of high quality, and contains a range of different children{'}s genres based on sources located, including classic tales from The Arabian Nights, and popular fictional characters such as Goha. We anticipate that the current and subsequent versions of our corpus will lead to interesting studies in text classification, language use, and ideology in children{'}s texts.
Tasks	Text Classification
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1285/
PDF	https://www.aclweb.org/anthology/L16-1285
PWC	https://paperswithcode.com/paper/compilation-of-an-arabic-childrens-corpus
Repo
Framework

Predicting the Rise and Fall of Scientific Topics from Trends in their Rhetorical Framing


Title	Predicting the Rise and Fall of Scientific Topics from Trends in their Rhetorical Framing
Authors	Vinodkumar Prabhakaran, William L. Hamilton, Dan McFarland, Dan Jurafsky
Abstract
Tasks	Topic Models
Published	2016-08-01
URL	https://www.aclweb.org/anthology/papers/P16-1111/p16-1111
PDF	https://www.aclweb.org/anthology/P16-1111
PWC	https://paperswithcode.com/paper/predicting-the-rise-and-fall-of-scientific
Repo
Framework

Evaluating multi-sense embeddings for semantic resolution monolingually and in word translation


Title	Evaluating multi-sense embeddings for semantic resolution monolingually and in word translation
Authors	G{'a}bor Borb{'e}ly, M{'a}rton Makrai, D{'a}vid M{'a}rk Nemeskey, Andr{'a}s Kornai
Abstract
Tasks	Word Embeddings
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2515/
PDF	https://www.aclweb.org/anthology/W16-2515
PWC	https://paperswithcode.com/paper/evaluating-multi-sense-embeddings-for
Repo
Framework

A Language Resource of German Errors Written by Children with Dyslexia


Title	A Language Resource of German Errors Written by Children with Dyslexia
Authors	Maria Rauschenberger, Luz Rello, Silke F{"u}chsel, J{"o}rg Thomaschewski
Abstract	In this paper we present a language resource for German, composed of a list of 1,021 unique errors extracted from a collection of texts written by people with dyslexia. The errors were annotated with a set of linguistic characteristics as well as visual and phonetic features. We present the compilation and the annotation criteria for the different types of dyslexic errors. This language resource has many potential uses since errors written by people with dyslexia reflect their difficulties. For instance, it has already been used to design language exercises to treat dyslexia in German. To the best of our knowledge, this is first resource of this kind in German.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1013/
PDF	https://www.aclweb.org/anthology/L16-1013
PWC	https://paperswithcode.com/paper/a-language-resource-of-german-errors-written
Repo
Framework


Title	You Shall Know People by the Company They Keep: Person Name Disambiguation for Social Network Construction
Authors	Mariona Coll Ardanuy, Maarten van den Bos, Caroline Sporleder
Abstract
Tasks	Coreference Resolution, Word Sense Disambiguation
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2107/
PDF	https://www.aclweb.org/anthology/W16-2107
PWC	https://paperswithcode.com/paper/you-shall-know-people-by-the-company-they
Repo
Framework

Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels


Title	Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels
Authors	Ilya O. Tolstikhin, Bharath K. Sriperumbudur, Bernhard Schölkopf
Abstract	Maximum Mean Discrepancy (MMD) is a distance on the space of probability measures which has found numerous applications in machine learning and nonparametric testing. This distance is based on the notion of embedding probabilities in a reproducing kernel Hilbert space. In this paper, we present the first known lower bounds for the estimation of MMD based on finite samples. Our lower bounds hold for any radial universal kernel on $\R^d$ and match the existing upper bounds up to constants that depend only on the properties of the kernel. Using these lower bounds, we establish the minimax rate optimality of the empirical estimator and its $U$-statistic variant, which are usually employed in applications.
Tasks
Published	2016-12-01
URL	http://papers.nips.cc/paper/6483-minimax-estimation-of-maximum-mean-discrepancy-with-radial-kernels
PDF	http://papers.nips.cc/paper/6483-minimax-estimation-of-maximum-mean-discrepancy-with-radial-kernels.pdf
PWC	https://paperswithcode.com/paper/minimax-estimation-of-maximum-mean
Repo
Framework

Annotating Characters in Literary Corpora: A Scheme, the CHARLES Tool, and an Annotated Novel


Title	Annotating Characters in Literary Corpora: A Scheme, the CHARLES Tool, and an Annotated Novel
Authors	Hardik Vala, Stefan Dimitrov, David Jurgens, Andrew Piper, Derek Ruths
Abstract	Characters form the focus of various studies of literary works, including social network analysis, archetype induction, and plot comparison. The recent rise in the computational modelling of literary works has produced a proportional rise in the demand for character-annotated literary corpora. However, automatically identifying characters is an open problem and there is low availability of literary texts with manually labelled characters. To address the latter problem, this work presents three contributions: (1) a comprehensive scheme for manually resolving mentions to characters in texts. (2) A novel collaborative annotation tool, CHARLES (CHAracter Resolution Label-Entry System) for character annotation and similiar cross-document tagging tasks. (3) The character annotations resulting from a pilot study on the novel Pride and Prejudice, demonstrating the scheme and tool facilitate the efficient production of high-quality annotations. We expect this work to motivate the further production of annotated literary corpora to help meet the demand of the community.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1028/
PDF	https://www.aclweb.org/anthology/L16-1028
PWC	https://paperswithcode.com/paper/annotating-characters-in-literary-corpora-a
Repo
Framework

Adaptive optimal training of animal behavior


Title	Adaptive optimal training of animal behavior
Authors	Ji Hyun Bak, Jung Yoon Choi, Athena Akrami, Ilana Witten, Jonathan W. Pillow
Abstract	Neuroscience experiments often require training animals to perform tasks designed to elicit various sensory, cognitive, and motor behaviors. Training typically involves a series of gradual adjustments of stimulus conditions and rewards in order to bring about learning. However, training protocols are usually hand-designed, relying on a combination of intuition, guesswork, and trial-and-error, and often require weeks or months to achieve a desired level of task performance. Here we combine ideas from reinforcement learning and adaptive optimal experimental design to formulate methods for adaptive optimal training of animal behavior. Our work addresses two intriguing problems at once: first, it seeks to infer the learning rules underlying an animal’s behavioral changes during training; second, it seeks to exploit these rules to select stimuli that will maximize the rate of learning toward a desired objective. We develop and test these methods using data collected from rats during training on a two-interval sensory discrimination task. We show that we can accurately infer the parameters of a policy-gradient-based learning algorithm that describes how the animal’s internal model of the task evolves over the course of training. We then formulate a theory for optimal training, which involves selecting sequences of stimuli that will drive the animal’s internal policy toward a desired location in the parameter space. Simulations show that our method can in theory provide a substantial speedup over standard training methods. We feel these results will hold considerable theoretical and practical implications both for researchers in reinforcement learning and for experimentalists seeking to train animals.
Tasks
Published	2016-12-01
URL	http://papers.nips.cc/paper/6344-adaptive-optimal-training-of-animal-behavior
PDF	http://papers.nips.cc/paper/6344-adaptive-optimal-training-of-animal-behavior.pdf
PWC	https://paperswithcode.com/paper/adaptive-optimal-training-of-animal-behavior
Repo
Framework

Fill the Gap! Analyzing Implicit Premises between Claims from Online Debates


Title	Fill the Gap! Analyzing Implicit Premises between Claims from Online Debates
Authors	Filip Boltu{\v{z}}i{'c}, Jan {\v{S}}najder
Abstract
Tasks	Argument Mining, Opinion Mining
Published	2016-08-01
URL	https://www.aclweb.org/anthology/W16-2815/
PDF	https://www.aclweb.org/anthology/W16-2815
PWC	https://paperswithcode.com/paper/fill-the-gap-analyzing-implicit-premises
Repo
Framework