Paper Group NANR 129
Philippine Language Resources: Applications, Issues, and Directions. Generating a Linguistic Model for Requirement Quality Analysis. Mongolian Named Entity Recognition System with Rich Features. A Joint Model for Answer Sentence Ranking and Answer Extraction. Supervised learning through the lens of compression. Yggdrasil: An Optimized System for Tr …
Philippine Language Resources: Applications, Issues, and Directions
| Title | Philippine Language Resources: Applications, Issues, and Directions |
| Authors | Nathaniel Oco, Leif Romeritch Syliongka, Tod Allman, Rachel Edita Roxas |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-3015/ |
| https://www.aclweb.org/anthology/Y16-3015 | |
| PWC | https://paperswithcode.com/paper/philippine-language-resources-applications |
| Repo | |
| Framework | |
Generating a Linguistic Model for Requirement Quality Analysis
| Title | Generating a Linguistic Model for Requirement Quality Analysis |
| Authors | Juyeon Kang, Jungyeul Park |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-3016/ |
| https://www.aclweb.org/anthology/Y16-3016 | |
| PWC | https://paperswithcode.com/paper/generating-a-linguistic-model-for-requirement |
| Repo | |
| Framework | |
Mongolian Named Entity Recognition System with Rich Features
| Title | Mongolian Named Entity Recognition System with Rich Features |
| Authors | Weihua Wang, Feilong Bao, Guanglai Gao |
| Abstract | In this paper, we first build a manually annotated named entity corpus of Mongolian. Then, we propose three morphological processing methods and study comprehensive features, including syllable features, lexical features, context features, morphological features and semantic features in Mongolian named entity recognition. Moreover, we also evaluate the influence of word cluster features on the system and combine all features together eventually. The experimental result shows that segmenting each suffix into an individual token achieves better results than deleting suffixes or using the suffixes as feature. The system based on segmenting suffixes with all proposed features yields benchmark result of F-measure=84.65 on this corpus. |
| Tasks | Machine Translation, Named Entity Recognition, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1049/ |
| https://www.aclweb.org/anthology/C16-1049 | |
| PWC | https://paperswithcode.com/paper/mongolian-named-entity-recognition-system |
| Repo | |
| Framework | |
A Joint Model for Answer Sentence Ranking and Answer Extraction
| Title | A Joint Model for Answer Sentence Ranking and Answer Extraction |
| Authors | Md Arafat Sultan, Vittorio Castelli, Radu Florian |
| Abstract | Answer sentence ranking and answer extraction are two key challenges in question answering that have traditionally been treated in isolation, i.e., as independent tasks. In this article, we (1) explain how both tasks are related at their core by a common quantity, and (2) propose a simple and intuitive joint probabilistic model that addresses both via joint computation but task-specific application of that quantity. In our experiments with two TREC datasets, our joint model substantially outperforms state-of-the-art systems in both tasks. |
| Tasks | Information Retrieval, Question Answering, Semantic Textual Similarity |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1009/ |
| https://www.aclweb.org/anthology/Q16-1009 | |
| PWC | https://paperswithcode.com/paper/a-joint-model-for-answer-sentence-ranking-and |
| Repo | |
| Framework | |
Supervised learning through the lens of compression
| Title | Supervised learning through the lens of compression |
| Authors | Ofir David, Shay Moran, Amir Yehudayoff |
| Abstract | This work continues the study of the relationship between sample compression schemes and statistical learning, which has been mostly investigated within the framework of binary classification. We first extend the investigation to multiclass categorization: we prove that in this case learnability is equivalent to compression of logarithmic sample size and that the uniform convergence property implies compression of constant size. We use the compressibility-learnability equivalence to show that (i) for multiclass categorization, PAC and agnostic PAC learnability are equivalent, and (ii) to derive a compactness theorem for learnability. We then consider supervised learning under general loss functions: we show that in this case, in order to maintain the compressibility-learnability equivalence, it is necessary to consider an approximate variant of compression. We use it to show that PAC and agnostic PAC are not equivalent, even when the loss function has only three values. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6490-supervised-learning-through-the-lens-of-compression |
| http://papers.nips.cc/paper/6490-supervised-learning-through-the-lens-of-compression.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-learning-through-the-lens-of |
| Repo | |
| Framework | |
Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale
| Title | Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale |
| Authors | Firas Abuzaid, Joseph K. Bradley, Feynman T. Liang, Andrew Feng, Lee Yang, Matei Zaharia, Ameet S. Talwalkar |
| Abstract | Deep distributed decision trees and tree ensembles have grown in importance due to the need to model increasingly large datasets. However, PLANET, the standard distributed tree learning algorithm implemented in systems such as \xgboost and Spark MLlib, scales poorly as data dimensionality and tree depths grow. We present Yggdrasil, a new distributed tree learning method that outperforms existing methods by up to 24x. Unlike PLANET, Yggdrasil is based on vertical partitioning of the data (i.e., partitioning by feature), along with a set of optimized data structures to reduce the CPU and communication costs of training. Yggdrasil (1) trains directly on compressed data for compressible features and labels; (2) introduces efficient data structures for training on uncompressed data; and (3) minimizes communication between nodes by using sparse bitvectors. Moreover, while PLANET approximates split points through feature binning, Yggdrasil does not require binning, and we analytically characterize the impact of this approximation. We evaluate Yggdrasil against the MNIST 8M dataset and a high-dimensional dataset at Yahoo; for both, Yggdrasil is faster by up to an order of magnitude. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6366-yggdrasil-an-optimized-system-for-training-deep-decision-trees-at-scale |
| http://papers.nips.cc/paper/6366-yggdrasil-an-optimized-system-for-training-deep-decision-trees-at-scale.pdf | |
| PWC | https://paperswithcode.com/paper/yggdrasil-an-optimized-system-for-training |
| Repo | |
| Framework | |
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations
| Title | Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: System Demonstrations |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2000/ |
| https://www.aclweb.org/anthology/C16-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-coling-2016-the-26th |
| Repo | |
| Framework | |
Word Sense-Aware Machine Translation: Including Senses as Contextual Features for Improved Translation Models
| Title | Word Sense-Aware Machine Translation: Including Senses as Contextual Features for Improved Translation Models |
| Authors | Steven Neale, Lu{'\i}s Gomes, Eneko Agirre, Oier Lopez de Lacalle, Ant{'o}nio Branco |
| Abstract | Although it is commonly assumed that word sense disambiguation (WSD) should help to improve lexical choice and improve the quality of machine translation systems, how to successfully integrate word senses into such systems remains an unanswered question. Some successful approaches have involved reformulating either WSD or the word senses it produces, but work on using traditional word senses to improve machine translation have met with limited success. In this paper, we build upon previous work that experimented on including word senses as contextual features in maxent-based translation models. Training on a large, open-domain corpus (Europarl), we demonstrate that this aproach yields significant improvements in machine translation from English to Portuguese. |
| Tasks | Machine Translation, Word Sense Disambiguation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1441/ |
| https://www.aclweb.org/anthology/L16-1441 | |
| PWC | https://paperswithcode.com/paper/word-sense-aware-machine-translation |
| Repo | |
| Framework | |
Adaptive Skills Adaptive Partitions (ASAP)
| Title | Adaptive Skills Adaptive Partitions (ASAP) |
| Authors | Daniel J. Mankowitz, Timothy A. Mann, Shie Mannor |
| Abstract | We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them. We believe that both (1) and (2) are necessary for a truly general skill learning framework, which is a key building block needed to scale up to lifelong learning agents. The ASAP framework is also able to solve related new tasks simply by adapting where it applies its existing learned skills. We prove that ASAP converges to a local optimum under natural conditions. Finally, our experimental results, which include a RoboCup domain, demonstrate the ability of ASAP to learn where to reuse skills as well as solve multiple tasks with considerably less experience than solving each task from scratch. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6350-adaptive-skills-adaptive-partitions-asap |
| http://papers.nips.cc/paper/6350-adaptive-skills-adaptive-partitions-asap.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-skills-adaptive-partitions-asap-1 |
| Repo | |
| Framework | |
Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers
| Title | Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers |
| Authors | Ond{\v{r}}ej Bojar, Christian Buck, Rajen Chatterjee, Christian Federmann, Liane Guillou, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Aur{'e}lie N{'e}v{'e}ol, Mariana Neves, Pavel Pecina, Martin Popel, Philipp Koehn, Christof Monz, Matteo Negri, Matt Post, Lucia Specia, Karin Verspoor, J{"o}rg Tiedemann, Marco Turchi |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W16/W16-2300/ |
| https://www.aclweb.org/anthology/W16-2300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-conference-on |
| Repo | |
| Framework | |
Innovative Semi-Automatic Methodology to Annotate Emotional Corpora
| Title | Innovative Semi-Automatic Methodology to Annotate Emotional Corpora |
| Authors | Lea Canales, Carlo Strapparava, Ester Boldrini, Patricio Mart{'\i}nez-Barco |
| Abstract | Detecting depression or personality traits, tutoring and student behaviour systems, or identifying cases of cyber-bulling are a few of the wide range of the applications, in which the automatic detection of emotion is a crucial element. Emotion detection has the potential of high impact by contributing the benefit of business, society, politics or education. Given this context, the main objective of our research is to contribute to the resolution of one of the most important challenges in textual emotion detection task: the problems of emotional corpora annotation. This will be tackled by proposing of a new semi-automatic methodology. Our innovative methodology consists in two main phases: (1) an automatic process to pre-annotate the unlabelled sentences with a reduced number of emotional categories; and (2) a refinement manual process where human annotators will determine which is the predominant emotion between the emotional categories selected in the phase 1. Our proposal in this paper is to show and evaluate the pre-annotation process to analyse the feasibility and the benefits by the methodology proposed. The results obtained are promising and allow obtaining a substantial improvement of annotation time and cost and confirm the usefulness of our pre-annotation process to improve the annotation task. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4310/ |
| https://www.aclweb.org/anthology/W16-4310 | |
| PWC | https://paperswithcode.com/paper/innovative-semi-automatic-methodology-to |
| Repo | |
| Framework | |
Planting Trees in the Desert: Delexicalized Tagging and Parsing Combined
| Title | Planting Trees in the Desert: Delexicalized Tagging and Parsing Combined |
| Authors | Daniel Zeman, David Mare{\v{c}}ek, Zhiwei Yu, Zden{\v{e}}k {\v{Z}}abokrtsk{'y} |
| Abstract | |
| Tasks | Dependency Parsing, Machine Translation, Question Answering, Word Alignment |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-2018/ |
| https://www.aclweb.org/anthology/Y16-2018 | |
| PWC | https://paperswithcode.com/paper/planting-trees-in-the-desert-delexicalized |
| Repo | |
| Framework | |
Implicit Semantic Roles in a Multilingual Setting
| Title | Implicit Semantic Roles in a Multilingual Setting |
| Authors | Jennifer Sikos, Yannick Versley, Anette Frank |
| Abstract | |
| Tasks | Language Modelling, Semantic Role Labeling |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/S16-2005/ |
| https://www.aclweb.org/anthology/S16-2005 | |
| PWC | https://paperswithcode.com/paper/implicit-semantic-roles-in-a-multilingual |
| Repo | |
| Framework | |
MayAnd at SemEval-2016 Task 5: Syntactic and word2vec-based approach to aspect-based polarity detection in Russian
| Title | MayAnd at SemEval-2016 Task 5: Syntactic and word2vec-based approach to aspect-based polarity detection in Russian |
| Authors | Vladimir Mayorov, Ivan Andrianov |
| Abstract | |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1052/ |
| https://www.aclweb.org/anthology/S16-1052 | |
| PWC | https://paperswithcode.com/paper/mayand-at-semeval-2016-task-5-syntactic-and |
| Repo | |
| Framework | |
On the Role of Seed Lexicons in Learning Bilingual Word Embeddings
| Title | On the Role of Seed Lexicons in Learning Bilingual Word Embeddings |
| Authors | Ivan Vuli{'c}, Anna Korhonen |
| Abstract | |
| Tasks | Cross-Lingual Entity Linking, Entity Linking, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1024/ |
| https://www.aclweb.org/anthology/P16-1024 | |
| PWC | https://paperswithcode.com/paper/on-the-role-of-seed-lexicons-in-learning |
| Repo | |
| Framework | |
