Paper Group NANR 126
Questioning Arbitrariness in Language: a Data-Driven Study of Conventional Iconicity. Drop-out Conditional Random Fields for Twitter with Huge Mined Gazetteer. Evaluation Set for Slovak News Information Retrieval. The Forget-me-not Process. Neural Scoring Function for MST Parser. Deep Learning for Sentiment Analysis - Invited Talk. Extraction of Ke …
Questioning Arbitrariness in Language: a Data-Driven Study of Conventional Iconicity
| Title | Questioning Arbitrariness in Language: a Data-Driven Study of Conventional Iconicity |
| Authors | Ekaterina Abramova, Raquel Fern{'a}ndez |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1038/ |
| https://www.aclweb.org/anthology/N16-1038 | |
| PWC | https://paperswithcode.com/paper/questioning-arbitrariness-in-language-a-data |
| Repo | |
| Framework | |
Drop-out Conditional Random Fields for Twitter with Huge Mined Gazetteer
| Title | Drop-out Conditional Random Fields for Twitter with Huge Mined Gazetteer |
| Authors | Eunsuk Yang, Young-Bum Kim, Ruhi Sarikaya, Yu-Seop Kim |
| Abstract | |
| Tasks | Named Entity Recognition, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1032/ |
| https://www.aclweb.org/anthology/N16-1032 | |
| PWC | https://paperswithcode.com/paper/drop-out-conditional-random-fields-for |
| Repo | |
| Framework | |
Evaluation Set for Slovak News Information Retrieval
| Title | Evaluation Set for Slovak News Information Retrieval |
| Authors | Daniel Hl{'a}dek, Jan Sta{\v{s}}, Jozef Juh{'a}r |
| Abstract | This work proposes an information retrieval evaluation set for the Slovak language. A set of 80 queries written in the natural language is given together with the set of relevant documents. The document set contains 3980 newspaper articles sorted into 6 categories. Each document in the result set is manually annotated for relevancy with its corresponding query. The evaluation set is mostly compatible with the Cranfield test collection using the same methodology for queries and annotation of relevancy. In addition to that it provides annotation for document title, author, publication date and category that can be used for evaluation of automatic document clustering and categorization. |
| Tasks | Information Retrieval |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1302/ |
| https://www.aclweb.org/anthology/L16-1302 | |
| PWC | https://paperswithcode.com/paper/evaluation-set-for-slovak-news-information |
| Repo | |
| Framework | |
The Forget-me-not Process
| Title | The Forget-me-not Process |
| Authors | Kieran Milan, Joel Veness, James Kirkpatrick, Michael Bowling, Anna Koop, Demis Hassabis |
| Abstract | We introduce the Forget-me-not Process, an efficient, non-parametric meta-algorithm for online probabilistic sequence prediction for piecewise stationary, repeating sources. Our method works by taking a Bayesian approach to partition a stream of data into postulated task-specific segments, while simultaneously building a model for each task. We provide regret guarantees with respect to piecewise stationary data sources under the logarithmic loss, and validate the method empirically across a range of sequence prediction and task identification problems. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6055-the-forget-me-not-process |
| http://papers.nips.cc/paper/6055-the-forget-me-not-process.pdf | |
| PWC | https://paperswithcode.com/paper/the-forget-me-not-process |
| Repo | |
| Framework | |
Neural Scoring Function for MST Parser
| Title | Neural Scoring Function for MST Parser |
| Authors | Jind{\v{r}}ich Libovick{'y} |
| Abstract | Continuous word representations appeared to be a useful feature in many natural language processing tasks. Using fixed-dimension pre-trained word embeddings allows avoiding sparse bag-of-words representation and to train models with fewer parameters. In this paper, we use fixed pre-trained word embeddings as additional features for a neural scoring function in the MST parser. With the multi-layer architecture of the scoring function we can avoid handcrafting feature conjunctions. The continuous word representations on the input also allow us to reduce the number of lexical features, make the parser more robust to out-of-vocabulary words, and reduce the total number of parameters of the model. Although its accuracy stays below the state of the art, the model size is substantially smaller than with the standard features set. Moreover, it performs well for languages where only a smaller treebank is available and the results promise to be useful in cross-lingual parsing. |
| Tasks | Word Embeddings |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1110/ |
| https://www.aclweb.org/anthology/L16-1110 | |
| PWC | https://paperswithcode.com/paper/neural-scoring-function-for-mst-parser |
| Repo | |
| Framework | |
Deep Learning for Sentiment Analysis - Invited Talk
| Title | Deep Learning for Sentiment Analysis - Invited Talk |
| Authors | Richard Socher |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0408/ |
| https://www.aclweb.org/anthology/W16-0408 | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-sentiment-analysis-invited |
| Repo | |
| Framework | |
Extraction of Keywords of Novelties From Patent Claims
| Title | Extraction of Keywords of Novelties From Patent Claims |
| Authors | Shoko Suzuki, Hiromichi Takatsuka |
| Abstract | There are growing needs for patent analysis using Natural Language Processing (NLP)-based approaches. Although NLP-based approaches can extract various information from patents, there are very few approaches proposed to extract those parts what inventors regard as novel or having an inventive step compared to all existing works ever. To extract such parts is difficult even for human annotators except for well-trained experts. This causes many difficulties in analyzing patents. We propose a novel approach to automatically extract such keywords that relate to novelties or inventive steps from patent claims using the structure of the claims. In addition, we also propose a new framework of evaluating our approach. The experiments show that our approach outperforms the existing keyword extraction methods significantly in many technical fields. |
| Tasks | Keyword Extraction |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1113/ |
| https://www.aclweb.org/anthology/C16-1113 | |
| PWC | https://paperswithcode.com/paper/extraction-of-keywords-of-novelties-from |
| Repo | |
| Framework | |
Word Sense Clustering and Clusterability
| Title | Word Sense Clustering and Clusterability |
| Authors | Diana McCarthy, Marianna Apidianaki, Katrin Erk |
| Abstract | |
| Tasks | Word Sense Disambiguation, Word Sense Induction |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/J16-2003/ |
| https://www.aclweb.org/anthology/J16-2003 | |
| PWC | https://paperswithcode.com/paper/word-sense-clustering-and-clusterability |
| Repo | |
| Framework | |
On Developing Resources for Patient-level Information Retrieval
| Title | On Developing Resources for Patient-level Information Retrieval |
| Authors | Stephen Wu, Tamara Timmons, Amy Yates, Meikun Wang, Steven Bedrick, William Hersh, Hongfang Liu |
| Abstract | Privacy concerns have often served as an insurmountable barrier for the production of research and resources in clinical information retrieval (IR). We believe that both clinical IR research innovation and legitimate privacy concerns can be served by the creation of intra-institutional, fully protected resources. In this paper, we provide some principles and tools for IR resource-building in the unique problem setting of patient-level IR, following the tradition of the Cranfield paradigm. |
| Tasks | Information Retrieval |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1544/ |
| https://www.aclweb.org/anthology/L16-1544 | |
| PWC | https://paperswithcode.com/paper/on-developing-resources-for-patient-level |
| Repo | |
| Framework | |
Unsupervised Multi-Author Document Decomposition Based on Hidden Markov Model
| Title | Unsupervised Multi-Author Document Decomposition Based on Hidden Markov Model |
| Authors | Khaled Aldebei, Xiangjian He, Wenjing Jia, Jie Yang |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1067/ |
| https://www.aclweb.org/anthology/P16-1067 | |
| PWC | https://paperswithcode.com/paper/unsupervised-multi-author-document |
| Repo | |
| Framework | |
A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order
| Title | A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order |
| Authors | Xiangru Lian, Huan Zhang, Cho-Jui Hsieh, Yijun Huang, Ji Liu |
| Abstract | Asynchronous parallel optimization received substantial successes and extensive attention recently. One of core theoretical questions is how much speedup (or benefit) the asynchronous parallelization can bring to us. This paper provides a comprehensive and generic analysis to study the speedup property for a broad range of asynchronous parallel stochastic algorithms from the zeroth order to the first order methods. Our result recovers or improves existing analysis on special cases, provides more insights for understanding the asynchronous parallel behaviors, and suggests a novel asynchronous parallel zeroth order method for the first time. Our experiments provide novel applications of the proposed asynchronous parallel zeroth order method on hyper parameter tuning and model blending problems. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6551-a-comprehensive-linear-speedup-analysis-for-asynchronous-stochastic-parallel-optimization-from-zeroth-order-to-first-order |
| http://papers.nips.cc/paper/6551-a-comprehensive-linear-speedup-analysis-for-asynchronous-stochastic-parallel-optimization-from-zeroth-order-to-first-order.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-linear-speedup-analysis-for |
| Repo | |
| Framework | |
Exploring a Continuous and Flexible Representation of the Lexicon
| Title | Exploring a Continuous and Flexible Representation of the Lexicon |
| Authors | Pierre Marchal, Thierry Poibeau |
| Abstract | We aim at showing that lexical descriptions based on multifactorial and continuous models can be used by linguists and lexicographers (and not only by machines) so long as they are provided with a way to efficiently navigate data collections. We propose to demonstrate such a system. |
| Tasks | Semantic Textual Similarity |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2062/ |
| https://www.aclweb.org/anthology/C16-2062 | |
| PWC | https://paperswithcode.com/paper/exploring-a-continuous-and-flexible |
| Repo | |
| Framework | |
Event Detection with Burst Information Networks
| Title | Event Detection with Burst Information Networks |
| Authors | Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou |
| Abstract | Retrospective event detection is an important task for discovering previously unidentified events in a text stream. In this paper, we propose two fast centroid-aware event detection models based on a novel text stream representation {–} Burst Information Networks (BINets) for addressing the challenge. The BINets are time-aware, efficient and can be easily analyzed for identifying key information (centroids). These advantages allow the BINet-based approaches to achieve the state-of-the-art performance on multiple datasets, demonstrating the efficacy of BINets for the task of event detection. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1309/ |
| https://www.aclweb.org/anthology/C16-1309 | |
| PWC | https://paperswithcode.com/paper/event-detection-with-burst-information |
| Repo | |
| Framework | |
Farasa: A Fast and Furious Segmenter for Arabic
| Title | Farasa: A Fast and Furious Segmenter for Arabic |
| Authors | Ahmed Abdelali, Kareem Darwish, Nadir Durrani, Hamdy Mubarak |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Tokenization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-3003/ |
| https://www.aclweb.org/anthology/N16-3003 | |
| PWC | https://paperswithcode.com/paper/farasa-a-fast-and-furious-segmenter-for |
| Repo | |
| Framework | |
Non-projectivity and valency
| Title | Non-projectivity and valency |
| Authors | Zdenka Uresova, Eva Fucikova, Jan Hajic |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0902/ |
| https://www.aclweb.org/anthology/W16-0902 | |
| PWC | https://paperswithcode.com/paper/non-projectivity-and-valency |
| Repo | |
| Framework | |
