Paper Group NANR 261
Disconnected Recurrent Neural Networks for Text Categorization. ELISA-EDL: A Cross-lingual Entity Extraction, Linking and Localization System. SemEval 2018 Task 4: Character Identification on Multiparty Dialogues. JFCKB: Japanese Feature Change Knowledge Base. Scalable Exemplar-based Subspace Clustering on Class-Imbalanced Data. Analysing Finnish w …
Disconnected Recurrent Neural Networks for Text Categorization
Title | Disconnected Recurrent Neural Networks for Text Categorization |
Authors | Baoxin Wang |
Abstract | Recurrent neural network (RNN) has achieved remarkable performance in text categorization. RNN can model the entire sequence and capture long-term dependencies, but it does not do well in extracting key patterns. In contrast, convolutional neural network (CNN) is good at extracting local and position-invariant features. In this paper, we present a novel model named disconnected recurrent neural network (DRNN), which incorporates position-invariance into RNN. By limiting the distance of information flow in RNN, the hidden state at each time step is restricted to represent words near the current position. The proposed model makes great improvements over RNN and CNN models and achieves the best performance on several benchmark datasets for text categorization. |
Tasks | Sentiment Analysis, Text Classification |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-1215/ |
https://www.aclweb.org/anthology/P18-1215 | |
PWC | https://paperswithcode.com/paper/disconnected-recurrent-neural-networks-for |
Repo | |
Framework | |
ELISA-EDL: A Cross-lingual Entity Extraction, Linking and Localization System
Title | ELISA-EDL: A Cross-lingual Entity Extraction, Linking and Localization System |
Authors | Boliang Zhang, Ying Lin, Xiaoman Pan, Di Lu, Jonathan May, Kevin Knight, Heng Ji |
Abstract | We demonstrate ELISA-EDL, a state-of-the-art re-trainable system to extract entity mentions from low-resource languages, link them to external English knowledge bases, and visualize locations related to disaster topics on a world heatmap. We make all of our data sets, resources and system training and testing APIs publicly available for research purpose. |
Tasks | Entity Extraction, Entity Linking, Transfer Learning |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/N18-5009/ |
https://www.aclweb.org/anthology/N18-5009 | |
PWC | https://paperswithcode.com/paper/elisa-edl-a-cross-lingual-entity-extraction |
Repo | |
Framework | |
SemEval 2018 Task 4: Character Identification on Multiparty Dialogues
Title | SemEval 2018 Task 4: Character Identification on Multiparty Dialogues |
Authors | Jinho D. Choi, Henry Y. Chen |
Abstract | Character identification is a task of entity linking that finds the global entity of each personal mention in multiparty dialogue. For this task, the first two seasons of the popular TV show Friends are annotated, comprising a total of 448 dialogues, 15,709 mentions, and 401 entities. The personal mentions are detected from nominals referring to certain characters in the show, and the entities are collected from the list of all characters in those two seasons of the show. This task is challenging because it requires the identification of characters that are mentioned but may not be active during the conversation. Among 90+ participants, four of them submitted their system outputs and showed strengths in different aspects about the task. Thorough analyses of the distributed datasets, system outputs, and comparative studies are also provided. To facilitate the momentum, we create an open-source project for this task and publicly release a larger and cleaner dataset, hoping to support researchers for more enhanced modeling. |
Tasks | Entity Linking, Machine Translation, Question Answering |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1007/ |
https://www.aclweb.org/anthology/S18-1007 | |
PWC | https://paperswithcode.com/paper/semeval-2018-task-4-character-identification |
Repo | |
Framework | |
JFCKB: Japanese Feature Change Knowledge Base
Title | JFCKB: Japanese Feature Change Knowledge Base |
Authors | Tetsuaki Nakamura, Daisuke Kawahara |
Abstract | |
Tasks | Common Sense Reasoning |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1223/ |
https://www.aclweb.org/anthology/L18-1223 | |
PWC | https://paperswithcode.com/paper/jfckb-japanese-feature-change-knowledge-base |
Repo | |
Framework | |
Scalable Exemplar-based Subspace Clustering on Class-Imbalanced Data
Title | Scalable Exemplar-based Subspace Clustering on Class-Imbalanced Data |
Authors | Chong You, Chi Li, Daniel P. Robinson, Rene Vidal |
Abstract | Subspace clustering methods based on expressing each data point as a linear combination of a few other data points (e.g., sparse subspace clustering) have become a popular tool for unsupervised learning due to their empirical success and theoretical guarantees. However, their performance can be affected by imbalanced data distributions and large-scale datasets. This paper presents an exemplar-based subspace clustering method to tackle the problem of imbalanced and large-scale datasets. The proposed method searches for a subset of the data that best represents all data points as measured by the $ell_1$-norm of the representation coefficients. To solve our model efficiently, we introduce a farthest first search algorithm which iteratively selects the least well-represented point as an exemplar. When data comes from a union of subspaces, we prove that the computed subset contains enough exemplars from each subspace for expressing all data points even if the data are imbalanced. Our experiments demonstrate that the proposed method outperforms state-of-the-art subspace clustering methods in two large-scale image datasets that are imbalanced. We also demonstrate the effectiveness of our method on unsupervised data subset selection for a face image classification task. |
Tasks | Image Classification |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Chong_You_A_Scalable_Exemplar-based_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Chong_You_A_Scalable_Exemplar-based_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/scalable-exemplar-based-subspace-clustering |
Repo | |
Framework | |
Analysing Finnish with word lists: the DDI approach to morphology revisited
Title | Analysing Finnish with word lists: the DDI approach to morphology revisited |
Authors | Atro Voutilainen, Maria Palolahti |
Abstract | |
Tasks | Morphological Analysis |
Published | 2018-01-01 |
URL | https://www.aclweb.org/anthology/W18-0214/ |
https://www.aclweb.org/anthology/W18-0214 | |
PWC | https://paperswithcode.com/paper/analysing-finnish-with-word-lists-the-ddi |
Repo | |
Framework | |
A convex program for bilinear inversion of sparse vectors
Title | A convex program for bilinear inversion of sparse vectors |
Authors | Alireza Aghasi, Ali Ahmed, Paul Hand, Babhru Joshi |
Abstract | We consider the bilinear inverse problem of recovering two vectors, x in R^L and w in R^L, from their entrywise product. We consider the case where x and w have known signs and are sparse with respect to known dictionaries of size K and N, respectively. Here, K and N may be larger than, smaller than, or equal to L. We introduce L1-BranchHull, which is a convex program posed in the natural parameter space and does not require an approximate solution or initialization in order to be stated or solved. We study the case where x and w are S1- and S2-sparse with respect to a random dictionary, with the sparse vectors satisfying an effective sparsity condition, and present a recovery guarantee that depends on the number of measurements as L > Omega(S1+S2)(log(K+N))^2. Numerical experiments verify that the scaling constant in the theorem is not too large. One application of this problem is the sweep distortion removal task in dielectric imaging, where one of the signals is a nonnegative reflectivity, and the other signal lives in a known subspace, for example that given by dominant wavelet coefficients. We also introduce a variants of L1-BranchHull for the purposes of tolerating noise and outliers, and for the purpose of recovering piecewise constant signals. We provide an ADMM implementation of these variants and show they can extract piecewise constant behavior from real images. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8074-a-convex-program-for-bilinear-inversion-of-sparse-vectors |
http://papers.nips.cc/paper/8074-a-convex-program-for-bilinear-inversion-of-sparse-vectors.pdf | |
PWC | https://paperswithcode.com/paper/a-convex-program-for-bilinear-inversion-of |
Repo | |
Framework | |
A Syntax-Based Scheme for the Annotation and Segmentation of German Spoken Language Interactions
Title | A Syntax-Based Scheme for the Annotation and Segmentation of German Spoken Language Interactions |
Authors | Swantje Westpfahl, Jan Gorisch |
Abstract | Unlike corpora of written language where segmentation can mainly be derived from orthographic punctuation marks, the basis for segmenting spoken language corpora is not predetermined by the primary data, but rather has to be established by the corpus compilers. This impedes consistent querying and visualization of such data. Several ways of segmenting have been proposed, some of which are based on syntax. In this study, we developed and evaluated annotation and segmentation guidelines in reference to the topological field model for German. We can show that these guidelines are used consistently across annotators. We also investigated the influence of various interactional settings with a rather simple measure, the word-count per segment and unit-type. We observed that the word count and the distribution of each unit type differ in varying interactional settings and that our developed segmentation and annotation guidelines are used consistently across annotators. In conclusion, our syntax-based segmentations reflect interactional properties that are intrinsic to the social interactions that participants are involved in. This can be used for further analysis of social interaction and opens the possibility for automatic segmentation of transcripts. |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4913/ |
https://www.aclweb.org/anthology/W18-4913 | |
PWC | https://paperswithcode.com/paper/a-syntax-based-scheme-for-the-annotation-and |
Repo | |
Framework | |
Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions
Title | Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions |
Authors | Pan Xu, Tianhao Wang, Quanquan Gu |
Abstract | We provide a second-order stochastic differential equation (SDE), which characterizes the continuous-time dynamics of accelerated stochastic mirror descent (ASMD) for strongly convex functions. This SDE plays a central role in designing new discrete-time ASMD algorithms via numerical discretization, and providing neat analyses of their convergence rates based on Lyapunov functions. Our results suggest that the only existing ASMD algorithm, namely, AC-SA proposed in Ghadimi & Lan (2012) is one instance of its kind, and we can actually derive new instances of ASMD with fewer tuning parameters. This sheds light on revisiting accelerated stochastic optimization through the lens of SDEs, which can lead to a better understanding of acceleration in stochastic optimization, as well as new simpler algorithms. Numerical experiments on both synthetic and real data support our theory. |
Tasks | Stochastic Optimization |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2166 |
http://proceedings.mlr.press/v80/xu18g/xu18g.pdf | |
PWC | https://paperswithcode.com/paper/continuous-and-discrete-time-accelerated |
Repo | |
Framework | |
Fine-grained evaluation of Quality Estimation for Machine translation based on a linguistically motivated Test Suite
Title | Fine-grained evaluation of Quality Estimation for Machine translation based on a linguistically motivated Test Suite |
Authors | Eleftherios Avramidis, Vivien Macketanz, Arle Lommel, Hans Uszkoreit |
Abstract | |
Tasks | Automatic Post-Editing, Common Sense Reasoning, Machine Translation |
Published | 2018-03-01 |
URL | https://www.aclweb.org/anthology/W18-2107/ |
https://www.aclweb.org/anthology/W18-2107 | |
PWC | https://paperswithcode.com/paper/fine-grained-evaluation-of-quality-estimation |
Repo | |
Framework | |
Neural Machine Translation with Decoding History Enhanced Attention
Title | Neural Machine Translation with Decoding History Enhanced Attention |
Authors | Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Chao Bian |
Abstract | Neural machine translation with source-side attention have achieved remarkable performance. however, there has been little work exploring to attend to the target-side which can potentially enhance the memory capbility of NMT. We reformulate a Decoding History Enhanced Attention mechanism (DHEA) to render NMT model better at selecting both source-side and target-side information. DHA enables dynamic control of the ratios at which source and target contexts contribute to the generation of target words, offering a way to weakly induce structure relations among both source and target tokens. It also allows training errors to be directly back-propagated through short-cut connections and effectively alleviates the gradient vanishing problem. The empirical study on Chinese-English translation shows that our model with proper configuration can improve by 0:9 BLEU upon Transformer and the best reported results in the dataset. On WMT14 English-German task and a larger WMT14 English-French task, our model achieves comparable results with the state-of-the-art. |
Tasks | Language Modelling, Machine Translation |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1124/ |
https://www.aclweb.org/anthology/C18-1124 | |
PWC | https://paperswithcode.com/paper/neural-machine-translation-with-decoding |
Repo | |
Framework | |
On Binary Classification in Extreme Regions
Title | On Binary Classification in Extreme Regions |
Authors | Hamid Jalalzai, Stephan Clémençon, Anne Sabourin |
Abstract | In pattern recognition, a random label Y is to be predicted based upon observing a random vector X valued in $\mathbb{R}^d$ with d>1 by means of a classification rule with minimum probability of error. In a wide variety of applications, ranging from finance/insurance to environmental sciences through teletraffic data analysis for instance, extreme (i.e. very large) observations X are of crucial importance, while contributing in a negligible manner to the (empirical) error however, simply because of their rarity. As a consequence, empirical risk minimizers generally perform very poorly in extreme regions. It is the purpose of this paper to develop a general framework for classification in the extremes. Precisely, under non-parametric heavy-tail assumptions for the class distributions, we prove that a natural and asymptotic notion of risk, accounting for predictive performance in extreme regions of the input space, can be defined and show that minimizers of an empirical version of a non-asymptotic approximant of this dedicated risk, based on a fraction of the largest observations, lead to classification rules with good generalization capacity, by means of maximal deviation inequalities in low probability regions. Beyond theoretical results, numerical experiments are presented in order to illustrate the relevance of the approach developed. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/7572-on-binary-classification-in-extreme-regions |
http://papers.nips.cc/paper/7572-on-binary-classification-in-extreme-regions.pdf | |
PWC | https://paperswithcode.com/paper/on-binary-classification-in-extreme-regions |
Repo | |
Framework | |
UNAM at SemEval-2018 Task 10: Unsupervised Semantic Discriminative Attribute Identification in Neural Word Embedding Cones
Title | UNAM at SemEval-2018 Task 10: Unsupervised Semantic Discriminative Attribute Identification in Neural Word Embedding Cones |
Authors | Ignacio Arroyo-Fern{'a}ndez, Ivan Meza, Carlos-Francisco M{'e}ndez-Cruz |
Abstract | In this paper we report an unsupervised method aimed to identify whether an attribute is discriminative for two words (which are treated as concepts, in our particular case). To this end, we use geometrically inspired vector operations underlying unsupervised decision functions. These decision functions operate on state-of-the-art neural word embeddings of the attribute and the concepts. The main idea can be described as follows: if attribute $q$ discriminates concept $a$ from concept $b$, then $q$ is excluded from the feature set shared by these two concepts: the intersection. That is, the membership $q\in (a\cap b)$ does not hold. As $a,b,q$ are represented with neural word embeddings, we tested vector operations allowing us to measure membership, i.e. fuzzy set operations (t-norm, for fuzzy intersection, and t-conorm, for fuzzy union) and the similarity between $q$ and the convex cone described by $a$ and $b$. |
Tasks | Word Embeddings |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1161/ |
https://www.aclweb.org/anthology/S18-1161 | |
PWC | https://paperswithcode.com/paper/unam-at-semeval-2018-task-10-unsupervised |
Repo | |
Framework | |
Deep Learning for Dialogue Systems
Title | Deep Learning for Dialogue Systems |
Authors | Yun-Nung Chen, Asli Celikyilmaz, Dilek Hakkani-T{"u}r |
Abstract | |
Tasks | Dialogue Management, Speech Recognition, Spoken Dialogue Systems, Task-Oriented Dialogue Systems, Text Generation |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-3006/ |
https://www.aclweb.org/anthology/C18-3006 | |
PWC | https://paperswithcode.com/paper/deep-learning-for-dialogue-systems |
Repo | |
Framework | |
Improved Transcription and Indexing of Oral History Interviews for Digital Humanities Research
Title | Improved Transcription and Indexing of Oral History Interviews for Digital Humanities Research |
Authors | Michael Gref, Joachim K{"o}hler, Almut Leh |
Abstract | |
Tasks | Robust Speech Recognition, Speech Recognition |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1493/ |
https://www.aclweb.org/anthology/L18-1493 | |
PWC | https://paperswithcode.com/paper/improved-transcription-and-indexing-of-oral |
Repo | |
Framework | |