Paper Group NAWR 7
Building a Dictionary of Affixal Negations. Unconstrained Salient Object Detection via Proposal Subset Optimization. Supervised Word Mover’s Distance. A Graph Degeneracy-based Approach to Keyword Extraction. Don’t Count, Predict! An Automatic Approach to Learning Sentiment Lexicons for Short Text. Cross-Lingual Word Representations via Spectral Gra …
Building a Dictionary of Affixal Negations
| Title | Building a Dictionary of Affixal Negations |
| Authors | Chantal van Son, Emiel van Miltenburg, Roser Morante |
| Abstract | This paper discusses the need for a dictionary of affixal negations and regular antonyms to facilitate their automatic detection in text. Without such a dictionary, affixal negations are very difficult to detect. In addition, we show that the set of affixal negations is not homogeneous, and that different NLP tasks may require different subsets. A dictionary can store the subtypes of affixal negations, making it possible to select a certain subset or to make inferences on the basis of these subtypes. We take a first step towards creating a negation dictionary by annotating all direct antonym pairs inWordNet using an existing typology of affixal negations. By highlighting some of the issues that were encountered in this annotation experiment, we hope to provide some insights into the necessary steps of building a negation dictionary. |
| Tasks | Natural Language Inference, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5007/ |
| https://www.aclweb.org/anthology/W16-5007 | |
| PWC | https://paperswithcode.com/paper/building-a-dictionary-of-affixal-negations |
| Repo | https://github.com/cltl/lexical-negation-dictionary |
| Framework | none |
Unconstrained Salient Object Detection via Proposal Subset Optimization
| Title | Unconstrained Salient Object Detection via Proposal Subset Optimization |
| Authors | Jianming Zhang, Stan Sclaroff, Zhe Lin, Xiaohui Shen, Brian Price, Radomir Mech |
| Abstract | We aim at detecting salient objects in unconstrained images. In unconstrained images, the number of salient objects (if any) varies from image to image, and is not given. We present a salient object detection system that directly outputs a compact set of detection windows, if any, for an input image. Our system leverages a Convolutional-Neural-Network model to generate location proposals of salient objects. Location proposals tend to be highly overlapping and noisy. Based on the Maximum a Posteriori principle, we propose a novel subset optimization framework to generate a compact set of detection windows out of noisy proposals. In experiments, we show that our subset optimization formulation greatly enhances the performance of our system, and our system attains 16-34% relative improvement in Average Precision compared with the state-of-the-art on three challenging salient object datasets. |
| Tasks | Object Detection, Salient Object Detection |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Zhang_Unconstrained_Salient_Object_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Zhang_Unconstrained_Salient_Object_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/unconstrained-salient-object-detection-via |
| Repo | https://github.com/GuillaumeBalezo/SOD-python |
| Framework | tf |
Supervised Word Mover’s Distance
| Title | Supervised Word Mover’s Distance |
| Authors | Gao Huang, Chuan Guo, Matt J. Kusner, Yu Sun, Fei Sha, Kilian Q. Weinberger |
| Abstract | Accurately measuring the similarity between text documents lies at the core of many real world applications of machine learning. These include web-search ranking, document recommendation, multi-lingual document matching, and article categorization. Recently, a new document metric, the word mover’s distance (WMD), has been proposed with unprecedented results on kNN-based document classification. The WMD elevates high quality word embeddings to document metrics by formulating the distance between two documents as an optimal transport problem between the embedded words. However, the document distances are entirely unsupervised and lack a mechanism to incorporate supervision when available. In this paper we propose an efficient technique to learn a supervised metric, which we call the Supervised WMD (S-WMD) metric. Our algorithm learns document distances that measure the underlying semantic differences between documents by leveraging semantic differences between individual words discovered during supervised training. This is achieved with an linear transformation of the underlying word embedding space and tailored word-specific weights, learned to minimize the stochastic leave-one-out nearest neighbor classification error on a per-document level. We evaluate our metric on eight real-world text classification tasks on which S-WMD consistently outperforms almost all of our 26 competitive baselines. |
| Tasks | Document Classification, Text Classification, Word Embeddings |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6139-supervised-word-movers-distance |
| http://papers.nips.cc/paper/6139-supervised-word-movers-distance.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-word-movers-distance |
| Repo | https://github.com/gaohuang/S-WMD |
| Framework | none |
A Graph Degeneracy-based Approach to Keyword Extraction
| Title | A Graph Degeneracy-based Approach to Keyword Extraction |
| Authors | Antoine Tixier, Fragkiskos Malliaros, Michalis Vazirgiannis |
| Abstract | |
| Tasks | Document Classification, Information Retrieval, Keyword Extraction, Text Classification, Word Embeddings |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1191/ |
| https://www.aclweb.org/anthology/D16-1191 | |
| PWC | https://paperswithcode.com/paper/a-graph-degeneracy-based-approach-to-keyword |
| Repo | https://github.com/Tixierae/EMNLP_2016 |
| Framework | none |
Don’t Count, Predict! An Automatic Approach to Learning Sentiment Lexicons for Short Text
| Title | Don’t Count, Predict! An Automatic Approach to Learning Sentiment Lexicons for Short Text |
| Authors | Duy Tin Vo, Yue Zhang |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2036/ |
| https://www.aclweb.org/anthology/P16-2036 | |
| PWC | https://paperswithcode.com/paper/dont-count-predict-an-automatic-approach-to |
| Repo | https://github.com/duytinvo/acl2016 |
| Framework | none |
Cross-Lingual Word Representations via Spectral Graph Embeddings
| Title | Cross-Lingual Word Representations via Spectral Graph Embeddings |
| Authors | Takamasa Oshikiri, Kazuki Fukui, Hidetoshi Shimodaira |
| Abstract | |
| Tasks | Information Retrieval, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2080/ |
| https://www.aclweb.org/anthology/P16-2080 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-word-representations-via |
| Repo | https://github.com/shimo-lab/kadingir |
| Framework | none |
Constraint-Based Question Answering with Knowledge Graph
| Title | Constraint-Based Question Answering with Knowledge Graph |
| Authors | Junwei Bao, Nan Duan, Zhao Yan, Ming Zhou, Tiejun Zhao |
| Abstract | WebQuestions and SimpleQuestions are two benchmark data-sets commonly used in recent knowledge-based question answering (KBQA) work. Most questions in them are {}simple{'} questions which can be answered based on a single relation in the knowledge base. Such data-sets lack the capability of evaluating KBQA systems on complicated questions. Motivated by this issue, we release a new data-set, namely ComplexQuestions, aiming to measure the quality of KBQA systems on {}multi-constraint{'} questions which require multiple knowledge base relations to get the answer. Beside, we propose a novel systematic KBQA approach to solve multi-constraint questions. Compared to state-of-the-art methods, our approach not only obtains comparable results on the two existing benchmark data-sets, but also achieves significant improvements on the ComplexQuestions. |
| Tasks | Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1236/ |
| https://www.aclweb.org/anthology/C16-1236 | |
| PWC | https://paperswithcode.com/paper/constraint-based-question-answering-with |
| Repo | https://github.com/JunweiBao/MulCQA |
| Framework | none |
The Next Step for Multi-Document Summarization: A Heterogeneous Multi-Genre Corpus Built with a Novel Construction Approach
| Title | The Next Step for Multi-Document Summarization: A Heterogeneous Multi-Genre Corpus Built with a Novel Construction Approach |
| Authors | Markus Zopf, Maxime Peyrard, Judith Eckle-Kohler |
| Abstract | Research in multi-document summarization has focused on newswire corpora since the early beginnings. However, the newswire genre provides genre-specific features such as sentence position which are easy to exploit in summarization systems. Such easy to exploit genre-specific features are available in other genres as well. We therefore present the new hMDS corpus for multi-document summarization, which contains heterogeneous source documents from multiple text genres, as well as summaries with different lengths. For the construction of the corpus, we developed a novel construction approach which is suited to build large and heterogeneous summarization corpora with little effort. The method reverses the usual process of writing summaries for given source documents: it combines already available summaries with appropriate source documents. In a detailed analysis, we show that our new corpus is significantly different from the homogeneous corpora commonly used, and that it is heterogeneous along several dimensions. Our experimental evaluation using well-known state-of-the-art summarization systems shows that our corpus poses new challenges in the field of multi-document summarization. Last but not least, we make our corpus publicly available to the research community at the corpus web page \url{https://github.com/AIPHES/hMDS}. |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1145/ |
| https://www.aclweb.org/anthology/C16-1145 | |
| PWC | https://paperswithcode.com/paper/the-next-step-for-multi-document |
| Repo | https://github.com/AIPHES/hMDS |
| Framework | none |
Improving Fluency in Narrative Text Generation With Grammatical Transformations and Probabilistic Parsing
| Title | Improving Fluency in Narrative Text Generation With Grammatical Transformations and Probabilistic Parsing |
| Authors | Emily Ahn, Fabrizio Morbini, Andrew Gordon |
| Abstract | |
| Tasks | Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6611/ |
| https://www.aclweb.org/anthology/W16-6611 | |
| PWC | https://paperswithcode.com/paper/improving-fluency-in-narrative-text |
| Repo | https://github.com/fmorbini/hsit-generation |
| Framework | none |
A Context-aware Natural Language Generator for Dialogue Systems
| Title | A Context-aware Natural Language Generator for Dialogue Systems |
| Authors | Ond{\v{r}}ej Du{\v{s}}ek, Filip Jur{\v{c}}{'\i}{\v{c}}ek |
| Abstract | |
| Tasks | Spoken Dialogue Systems, Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3622/ |
| https://www.aclweb.org/anthology/W16-3622 | |
| PWC | https://paperswithcode.com/paper/a-context-aware-natural-language-generator-1 |
| Repo | https://github.com/UFAL-DSG/tgen |
| Framework | tf |
Supervised Learning with Tensor Networks
| Title | Supervised Learning with Tensor Networks |
| Authors | Edwin Stoudenmire, David J. Schwab |
| Abstract | Tensor networks are approximations of high-order tensors which are efficient to work with and have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing tensor networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize non-linear kernel learning models. For the MNIST data set we obtain less than 1% test set classification error. We discuss an interpretation of the additional structure imparted by the tensor network to the learned model. |
| Tasks | Tensor Networks |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6211-supervised-learning-with-tensor-networks |
| http://papers.nips.cc/paper/6211-supervised-learning-with-tensor-networks.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-learning-with-tensor-networks |
| Repo | https://github.com/emstoudenmire/TNML |
| Framework | none |
The Role of Discourse Units in Near-Extractive Summarization
| Title | The Role of Discourse Units in Near-Extractive Summarization |
| Authors | Junyi Jessy Li, Kapil Thadani, Am Stent, a |
| Abstract | |
| Tasks | Document Summarization |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3617/ |
| https://www.aclweb.org/anthology/W16-3617 | |
| PWC | https://paperswithcode.com/paper/the-role-of-discourse-units-in-near |
| Repo | https://github.com/grimpil/nyt-summ |
| Framework | none |
Fast and accurate spike sorting of high-channel count probes with KiloSort
| Title | Fast and accurate spike sorting of high-channel count probes with KiloSort |
| Authors | Marius Pachitariu, Nicholas A. Steinmetz, Shabnam N. Kadir, Matteo Carandini, Kenneth D. Harris |
| Abstract | New silicon technology is enabling large-scale electrophysiological recordings in vivo from hundreds to thousands of channels. Interpreting these recordings requires scalable and accurate automated methods for spike sorting, which should minimize the time required for manual curation of the results. Here we introduce KiloSort, a new integrated spike sorting framework that uses template matching both during spike detection and during spike clustering. KiloSort models the electrical voltage as a sum of template waveforms triggered on the spike times, which allows overlapping spikes to be identified and resolved. Unlike previous algorithms that compress the data with PCA, KiloSort operates on the raw data which allows it to construct a more accurate model of the waveforms. Processing times are faster than in previous algorithms thanks to batch-based optimization on GPUs. We compare KiloSort to an established algorithm and show favorable performance, at much reduced processing times. A novel post-clustering merging step based on the continuity of the templates further reduced substantially the number of manual operations required on this data, for the neurons with near-zero error rates, paving the way for fully automated spike sorting of multichannel electrode recordings. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6326-fast-and-accurate-spike-sorting-of-high-channel-count-probes-with-kilosort |
| http://papers.nips.cc/paper/6326-fast-and-accurate-spike-sorting-of-high-channel-count-probes-with-kilosort.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-accurate-spike-sorting-of-high |
| Repo | https://github.com/cortex-lab/KiloSort |
| Framework | none |
Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States
| Title | Efficient Structured Inference for Transition-Based Parsing with Neural Networks and Error States |
| Authors | Ashish Vaswani, Kenji Sagae |
| Abstract | Transition-based approaches based on local classification are attractive for dependency parsing due to their simplicity and speed, despite producing results slightly below the state-of-the-art. In this paper, we propose a new approach for approximate structured inference for transition-based parsing that produces scores suitable for global scoring using local models. This is accomplished with the introduction of error states in local training, which add information about incorrect derivation paths typically left out completely in locally-trained models. Using neural networks for our local classifiers, our approach achieves 93.61{%} accuracy for transition-based dependency parsing in English. |
| Tasks | Dependency Parsing, Feature Engineering, Structured Prediction, Transition-Based Dependency Parsing, Word Embeddings |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/Q16-1014/ |
| https://www.aclweb.org/anthology/Q16-1014 | |
| PWC | https://paperswithcode.com/paper/efficient-structured-inference-for-transition |
| Repo | https://github.com/sagae/nndep |
| Framework | none |
Poisson-Gamma dynamical systems
| Title | Poisson-Gamma dynamical systems |
| Authors | Aaron Schein, Hanna Wallach, Mingyuan Zhou |
| Abstract | This paper presents a dynamical system based on the Poisson-Gamma construction for sequentially observed multivariate count data. Inherent to the model is a novel Bayesian nonparametric prior that ties and shrinks parameters in a powerful way. We develop theory about the model’s infinite limit and its steady-state. The model’s inductive bias is demonstrated on a variety of real-world datasets where it is shown to learn interpretable structure and have superior predictive performance. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6083-poisson-gamma-dynamical-systems |
| http://papers.nips.cc/paper/6083-poisson-gamma-dynamical-systems.pdf | |
| PWC | https://paperswithcode.com/paper/poisson-gamma-dynamical-systems-1 |
| Repo | https://github.com/aschein/pgds |
| Framework | none |
