Paper Group NANR 53
Multilingual Connotation Frames: A Case Study on Social Media for Targeted Sentiment Analysis and Forecast. On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models. Storyteller: Visual Analytics of Perspectives on Rich Text Interpretations. Slavic Forest, Norwegian Wood. Higher-Order Total Variation Classes on Grids: M …
Multilingual Connotation Frames: A Case Study on Social Media for Targeted Sentiment Analysis and Forecast
| Title | Multilingual Connotation Frames: A Case Study on Social Media for Targeted Sentiment Analysis and Forecast |
| Authors | Hannah Rashkin, Eric Bell, Yejin Choi, Svitlana Volkova |
| Abstract | People around the globe respond to major real world events through social media. To study targeted public sentiments across many languages and geographic locations, we introduce multilingual connotation frames: an extension from English connotation frames of Rashkin et al. (2016) with 10 additional European languages, focusing on the implied sentiments among event participants engaged in a frame. As a case study, we present large scale analysis on targeted public sentiments toward salient events and entities using 1.2 million multilingual connotation frames extracted from Twitter. |
| Tasks | Sentiment Analysis |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2073/ |
| https://www.aclweb.org/anthology/P17-2073 | |
| PWC | https://paperswithcode.com/paper/multilingual-connotation-frames-a-case-study |
| Repo | |
| Framework | |
On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models
| Title | On Separability of Loss Functions, and Revisiting Discriminative Vs Generative Models |
| Authors | Adarsh Prasad, Alexandru Niculescu-Mizil, Pradeep K. Ravikumar |
| Abstract | We revisit the classical analysis of generative vs discriminative models for general exponential families, and high-dimensional settings. Towards this, we develop novel technical machinery, including a notion of separability of general loss functions, which allow us to provide a general framework to obtain l∞ convergence rates for general M-estimators. We use this machinery to analyze l∞ and l2 convergence rates of generative and discriminative models, and provide insights into their nuanced behaviors in high-dimensions. Our results are also applicable to differential parameter estimation, where the quantity of interest is the difference between generative model parameters. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7280-on-separability-of-loss-functions-and-revisiting-discriminative-vs-generative-models |
| http://papers.nips.cc/paper/7280-on-separability-of-loss-functions-and-revisiting-discriminative-vs-generative-models.pdf | |
| PWC | https://paperswithcode.com/paper/on-separability-of-loss-functions-and |
| Repo | |
| Framework | |
Storyteller: Visual Analytics of Perspectives on Rich Text Interpretations
| Title | Storyteller: Visual Analytics of Perspectives on Rich Text Interpretations |
| Authors | Maarten van Meersbergen, Piek Vossen, Janneke van der Zwaan, Antske Fokkens, Willem van Hage, Inger Leemans, Isa Maks |
| Abstract | Complexity of event data in texts makes it difficult to assess its content, especially when considering larger collections in which different sources report on the same or similar situations. We present a system that makes it possible to visually analyze complex event and emotion data extracted from texts. We show that we can abstract from different data models for events and emotions to a single data model that can show the complex relations in four dimensions. The visualization has been applied to analyze 1) dynamic developments in how people both conceive and express emotions in theater plays and 2) how stories are told from the perspectyive of their sources based on rich event data extracted from news or biographies. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4207/ |
| https://www.aclweb.org/anthology/W17-4207 | |
| PWC | https://paperswithcode.com/paper/storyteller-visual-analytics-of-perspectives |
| Repo | |
| Framework | |
Slavic Forest, Norwegian Wood
| Title | Slavic Forest, Norwegian Wood |
| Authors | Rudolf Rosa, Daniel Zeman, David Mare{\v{c}}ek, Zden{\v{e}}k {\v{Z}}abokrtsk{'y} |
| Abstract | We once had a corp, or should we say, it once had us They showed us its tags, isn{'}t it great, unified tags They asked us to parse and they told us to use everything So we looked around and we noticed there was near nothing We took other langs, bitext aligned: words one-to-one We played for two weeks, and then they said, here is the test The parser kept training till morning, just until deadline So we had to wait and hope what we get would be just fine And, when we awoke, the results were done, we saw we{'}d won So, we wrote this paper, isn{'}t it good, Norwegian wood. |
| Tasks | Dependency Parsing, Machine Translation, Word Alignment |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1226/ |
| https://www.aclweb.org/anthology/W17-1226 | |
| PWC | https://paperswithcode.com/paper/slavic-forest-norwegian-wood |
| Repo | |
| Framework | |
Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods
| Title | Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods |
| Authors | Veeranjaneyulu Sadhanala, Yu-Xiang Wang, James L. Sharpnack, Ryan J. Tibshirani |
| Abstract | We consider the problem of estimating the values of a function over $n$ nodes of a $d$-dimensional grid graph (having equal side lengths $n^{1/d}$) from noisy observations. The function is assumed to be smooth, but is allowed to exhibit different amounts of smoothness at different regions in the grid. Such heterogeneity eludes classical measures of smoothness from nonparametric statistics, such as Holder smoothness. Meanwhile, total variation (TV) smoothness classes allow for heterogeneity, but are restrictive in another sense: only constant functions count as perfectly smooth (achieve zero TV). To move past this, we define two new higher-order TV classes, based on two ways of compiling the discrete derivatives of a parameter across the nodes. We relate these two new classes to Holder classes, and derive lower bounds on their minimax errors. We also analyze two naturally associated trend filtering methods; when $d=2$, each is seen to be rate optimal over the appropriate class. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7162-higher-order-total-variation-classes-on-grids-minimax-theory-and-trend-filtering-methods |
| http://papers.nips.cc/paper/7162-higher-order-total-variation-classes-on-grids-minimax-theory-and-trend-filtering-methods.pdf | |
| PWC | https://paperswithcode.com/paper/higher-order-total-variation-classes-on-grids |
| Repo | |
| Framework | |
Proceedings of the 1st Workshop on Natural Language Processing and Information Retrieval associated with RANLP 2017
| Title | Proceedings of the 1st Workshop on Natural Language Processing and Information Retrieval associated with RANLP 2017 |
| Authors | University of Wolverhampton Mireille Makary, University of Wolverhampton Michael Oakes |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/papers/W17-7700/w17-7700 |
| https://www.aclweb.org/anthology/W17-7700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-1st-workshop-on-natural |
| Repo | |
| Framework | |
Extracting Forbidden Factors from Regular Stringsets
| Title | Extracting Forbidden Factors from Regular Stringsets |
| Authors | James Rogers, Dakotah Lambert |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3404/ |
| https://www.aclweb.org/anthology/W17-3404 | |
| PWC | https://paperswithcode.com/paper/extracting-forbidden-factors-from-regular |
| Repo | |
| Framework | |
A Universal Analysis of Large-Scale Regularized Least Squares Solutions
| Title | A Universal Analysis of Large-Scale Regularized Least Squares Solutions |
| Authors | Ashkan Panahi, Babak Hassibi |
| Abstract | A problem that has been of recent interest in statistical inference, machine learning and signal processing is that of understanding the asymptotic behavior of regularized least squares solutions under random measurement matrices (or dictionaries). The Least Absolute Shrinkage and Selection Operator (LASSO or least-squares with $\ell_1$ regularization) is perhaps one of the most interesting examples. Precise expressions for the asymptotic performance of LASSO have been obtained for a number of different cases, in particular when the elements of the dictionary matrix are sampled independently from a Gaussian distribution. It has also been empirically observed that the resulting expressions remain valid when the entries of the dictionary matrix are independently sampled from certain non-Gaussian distributions. In this paper, we confirm these observations theoretically when the distribution is sub-Gaussian. We further generalize the previous expressions for a broader family of regularization functions and under milder conditions on the underlying random, possibly non-Gaussian, dictionary matrix. In particular, we establish the universality of the asymptotic statistics (e.g., the average quadratic risk) of LASSO with non-Gaussian dictionaries. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6930-a-universal-analysis-of-large-scale-regularized-least-squares-solutions |
| http://papers.nips.cc/paper/6930-a-universal-analysis-of-large-scale-regularized-least-squares-solutions.pdf | |
| PWC | https://paperswithcode.com/paper/a-universal-analysis-of-large-scale |
| Repo | |
| Framework | |
L1-L2 Parallel Dependency Treebank as Learner Corpus
| Title | L1-L2 Parallel Dependency Treebank as Learner Corpus |
| Authors | John Lee, Keying Li, Herman Leung |
| Abstract | This opinion paper proposes the use of parallel treebank as learner corpus. We show how an L1-L2 parallel treebank {—} i.e., parse trees of non-native sentences, aligned to the parse trees of their target hypotheses {—} can facilitate retrieval of sentences with specific learner errors. We argue for its benefits, in terms of corpus re-use and interoperability, over a conventional learner corpus annotated with error tags. As a proof of concept, we conduct a case study on word-order errors made by learners of Chinese as a foreign language. We report precision and recall in retrieving a range of word-order error categories from L1-L2 tree pairs annotated in the Universal Dependency framework. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6306/ |
| https://www.aclweb.org/anthology/W17-6306 | |
| PWC | https://paperswithcode.com/paper/l1-l2-parallel-dependency-treebank-as-learner |
| Repo | |
| Framework | |
Min-Max Propagation
| Title | Min-Max Propagation |
| Authors | Christopher Srinivasa, Inmar Givoni, Siamak Ravanbakhsh, Brendan J. Frey |
| Abstract | We study the application of min-max propagation, a variation of belief propagation, for approximate min-max inference in factor graphs. We show that for “any” high-order function that can be minimized in O(ω), the min-max message update can be obtained using an efficient O(K(ω + log(K)) procedure, where K is the number of variables. We demonstrate how this generic procedure, in combination with efficient updates for a family of high-order constraints, enables the application of min-max propagation to efficiently approximate the NP-hard problem of makespan minimization, which seeks to distribute a set of tasks on machines, such that the worst case load is minimized. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7140-min-max-propagation |
| http://papers.nips.cc/paper/7140-min-max-propagation.pdf | |
| PWC | https://paperswithcode.com/paper/min-max-propagation |
| Repo | |
| Framework | |
LIMSI@WMT’17
| Title | LIMSI@WMT’17 |
| Authors | Franck Burlot, Pooyan Safari, Matthieu Labeau, Alex Allauzen, re, Fran{\c{c}}ois Yvon |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4721/ |
| https://www.aclweb.org/anthology/W17-4721 | |
| PWC | https://paperswithcode.com/paper/limsiwmt17 |
| Repo | |
| Framework | |
TDParse: Multi-target-specific sentiment recognition on Twitter
| Title | TDParse: Multi-target-specific sentiment recognition on Twitter |
| Authors | Bo Wang, Maria Liakata, Arkaitz Zubiaga, Rob Procter |
| Abstract | Existing target-specific sentiment recognition methods consider only a single target per tweet, and have been shown to miss nearly half of the actual targets mentioned. We present a corpus of UK election tweets, with an average of 3.09 entities per tweet and more than one type of sentiment in half of the tweets. This requires a method for multi-target specific sentiment recognition, which we develop by using the context around a target as well as syntactic dependencies involving the target. We present results of our method on both a benchmark corpus of single targets and the multi-target election corpus, showing state-of-the art performance in both corpora and outperforming previous approaches to multi-target sentiment task as well as deep learning models for single-target sentiment. |
| Tasks | Dependency Parsing, Opinion Mining, Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1046/ |
| https://www.aclweb.org/anthology/E17-1046 | |
| PWC | https://paperswithcode.com/paper/tdparse-multi-target-specific-sentiment |
| Repo | |
| Framework | |
CASICT-DCU Neural Machine Translation Systems for WMT17
| Title | CASICT-DCU Neural Machine Translation Systems for WMT17 |
| Authors | Jinchao Zhang, Peerachet Porkaew, Jiawei Hu, Qiuye Zhao, Qun Liu |
| Abstract | |
| Tasks | Machine Translation, Word Alignment |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4745/ |
| https://www.aclweb.org/anthology/W17-4745 | |
| PWC | https://paperswithcode.com/paper/casict-dcu-neural-machine-translation-systems |
| Repo | |
| Framework | |
Identifying Comparative Structures in Biomedical Text
| Title | Identifying Comparative Structures in Biomedical Text |
| Authors | Samir Gupta, A.S.M. Ashique Mahmood, Karen Ross, Cathy Wu, K. Vijay-Shanker |
| Abstract | Comparison sentences are very commonly used by authors in biomedical literature to report results of experiments. In such comparisons, authors typically make observations under two different scenarios. In this paper, we present a system to automatically identify such comparative sentences and their components i.e. the compared entities, the scale of the comparison and the aspect on which the entities are being compared. Our methodology is based on dependencies obtained by applying a parser to extract a wide range of comparison structures. We evaluated our system for its effectiveness in identifying comparisons and their components. The system achieved a F-score of 0.87 for comparison sentence identification and 0.77-0.81 for identifying its components. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2326/ |
| https://www.aclweb.org/anthology/W17-2326 | |
| PWC | https://paperswithcode.com/paper/identifying-comparative-structures-in |
| Repo | |
| Framework | |
改進的向量空間可適性濾波器用於聲學回聲消除 (Acoustic Echo Cancellation Using an Improved Vector-Space-Based Adaptive Filtering Algorithm) [In Chinese]
| Title | 改進的向量空間可適性濾波器用於聲學回聲消除 (Acoustic Echo Cancellation Using an Improved Vector-Space-Based Adaptive Filtering Algorithm) [In Chinese] |
| Authors | Jin Li-You, Yu Tsao, Ying-Ren Chien |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1018/ |
| https://www.aclweb.org/anthology/O17-1018 | |
| PWC | https://paperswithcode.com/paper/1e2caecoea-e343a-c-14e2a-ae2e-acoustic-echo-1 |
| Repo | |
| Framework | |
