Paper Group NANR 63
Local Aggregative Games. Diachrony-aware Induction of Binary Latent Representations from Typological Features. A Novel Trajectory-based Spatial-Temporal Spectral Features for Speech Emotion Recognition. Cheap Translation for Cross-Lingual Named Entity Recognition. A Multilayer Perceptron based Ensemble Technique for Fine-grained Financial Sentiment …
Local Aggregative Games
| Title | Local Aggregative Games |
| Authors | Vikas Garg, Tommi Jaakkola |
| Abstract | Aggregative games provide a rich abstraction to model strategic multi-agent interactions. We focus on learning local aggregative games, where the payoff of each player is a function of its own action and the aggregate behavior of its neighbors in a connected digraph. We show the existence of a pure strategy epsilon-Nash equilibrium in such games when the payoff functions are convex or sub-modular. We prove an information theoretic lower bound, in a value oracle model, on approximating the structure of the digraph with non-negative monotone sub-modular cost functions on the edge set cardinality. We also introduce gamma-aggregative games that generalize local aggregative games, and admit epsilon-Nash equilibrium that are stable with respect to small changes in some specified graph property. Moreover, we provide estimation algorithms for the game theoretic model that can meaningfully recover the underlying structure and payoff functions from real voting data. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7118-local-aggregative-games |
| http://papers.nips.cc/paper/7118-local-aggregative-games.pdf | |
| PWC | https://paperswithcode.com/paper/local-aggregative-games |
| Repo | |
| Framework | |
Diachrony-aware Induction of Binary Latent Representations from Typological Features
| Title | Diachrony-aware Induction of Binary Latent Representations from Typological Features |
| Authors | Yugo Murawaki |
| Abstract | Although features of linguistic typology are a promising alternative to lexical evidence for tracing evolutionary history of languages, a large number of missing values in the dataset pose serious difficulties for statistical modeling. In this paper, we combine two existing approaches to the problem: (1) the synchronic approach that focuses on interdependencies between features and (2) the diachronic approach that exploits phylogenetically- and/or spatially-related languages. Specifically, we propose a Bayesian model that (1) represents each language as a sequence of binary latent parameters encoding inter-feature dependencies and (2) relates a language{'}s parameters to those of its phylogenetic and spatial neighbors. Experiments show that the proposed model recovers missing values more accurately than others and that induced representations retain phylogenetic and spatial signals observed for surface features. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1046/ |
| https://www.aclweb.org/anthology/I17-1046 | |
| PWC | https://paperswithcode.com/paper/diachrony-aware-induction-of-binary-latent |
| Repo | |
| Framework | |
A Novel Trajectory-based Spatial-Temporal Spectral Features for Speech Emotion Recognition
| Title | A Novel Trajectory-based Spatial-Temporal Spectral Features for Speech Emotion Recognition |
| Authors | Chun-Min Chang, Wei-Cheng Lin, Chi-Chun Lee |
| Abstract | |
| Tasks | Emotion Recognition, Speech Emotion Recognition |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/O17-3008/ |
| https://www.aclweb.org/anthology/O17-3008 | |
| PWC | https://paperswithcode.com/paper/a-novel-trajectory-based-spatial-temporal |
| Repo | |
| Framework | |
Cheap Translation for Cross-Lingual Named Entity Recognition
| Title | Cheap Translation for Cross-Lingual Named Entity Recognition |
| Authors | Stephen Mayhew, Chen-Tse Tsai, Dan Roth |
| Abstract | Recent work in NLP has attempted to deal with low-resource languages but still assumed a resource level that is not present for most languages, e.g., the availability of Wikipedia in the target language. We propose a simple method for cross-lingual named entity recognition (NER) that works well in settings with \textit{very} minimal resources. Our approach makes use of a lexicon to {``}translate{''} annotated data available in one or several high resource language(s) into the target language, and learns a standard monolingual NER model there. Further, when Wikipedia is available in the target language, our method can enhance Wikipedia based methods to yield state-of-the-art NER results; we evaluate on 7 diverse languages, improving the state-of-the-art by an average of 5.5{%} F1 points. With the minimal resources required, this is an extremely portable cross-lingual NER approach, as illustrated using a truly low-resource language, Uyghur. | |
| Tasks | Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1269/ |
| https://www.aclweb.org/anthology/D17-1269 | |
| PWC | https://paperswithcode.com/paper/cheap-translation-for-cross-lingual-named |
| Repo | |
| Framework | |
A Multilayer Perceptron based Ensemble Technique for Fine-grained Financial Sentiment Analysis
| Title | A Multilayer Perceptron based Ensemble Technique for Fine-grained Financial Sentiment Analysis |
| Authors | Md Shad Akhtar, Abhishek Kumar, Deepanway Ghosal, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | In this paper, we propose a novel method for combining deep learning and classical feature based models using a Multi-Layer Perceptron (MLP) network for financial sentiment analysis. We develop various deep learning models based on Convolutional Neural Network (CNN), Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). These are trained on top of pre-trained, autoencoder-based, financial word embeddings and lexicon features. An ensemble is constructed by combining these deep learning models and a classical supervised model based on Support Vector Regression (SVR). We evaluate our proposed technique on a benchmark dataset of SemEval-2017 shared task on financial sentiment analysis. The propose model shows impressive results on two datasets, i.e. microblogs and news headlines datasets. Comparisons show that our proposed model performs better than the existing state-of-the-art systems for the above two datasets by 2.0 and 4.1 cosine points, respectively. |
| Tasks | Sentiment Analysis, Stock Prediction, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1057/ |
| https://www.aclweb.org/anthology/D17-1057 | |
| PWC | https://paperswithcode.com/paper/a-multilayer-perceptron-based-ensemble |
| Repo | |
| Framework | |
OCR Post-Processing Text Correction using Simulated Annealing (OPTeCA)
| Title | OCR Post-Processing Text Correction using Simulated Annealing (OPTeCA) |
| Authors | Gitansh Khirbat |
| Abstract | |
| Tasks | Feature Engineering, Optical Character Recognition |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1015/ |
| https://www.aclweb.org/anthology/U17-1015 | |
| PWC | https://paperswithcode.com/paper/ocr-post-processing-text-correction-using |
| Repo | |
| Framework | |
Opinion Recommendation Using A Neural Model
| Title | Opinion Recommendation Using A Neural Model |
| Authors | Zhongqing Wang, Yue Zhang |
| Abstract | We present opinion recommendation, a novel task of jointly generating a review with a rating score that a certain user would give to a certain product which is unreviewed by the user, given existing reviews to the product by other users, and the reviews that the user has given to other products. A characteristic of opinion recommendation is the reliance of multiple data sources for multi-task joint learning. We use a single neural network to model users and products, generating customised product representations using a deep memory network, from which customised ratings and reviews are constructed jointly. Results show that our opinion recommendation system gives ratings that are closer to real user ratings on Yelp.com data compared with Yelp{'}s own ratings. our methods give better results compared to several pipelines baselines. |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1170/ |
| https://www.aclweb.org/anthology/D17-1170 | |
| PWC | https://paperswithcode.com/paper/opinion-recommendation-using-a-neural-model |
| Repo | |
| Framework | |
Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication
| Title | Polynomial Codes: an Optimal Design for High-Dimensional Coded Matrix Multiplication |
| Authors | Qian Yu, Mohammad Maddah-Ali, Salman Avestimehr |
| Abstract | We consider a large-scale matrix multiplication problem where the computation is carried out using a distributed system with a master node and multiple worker nodes, where each worker can store parts of the input matrices. We propose a computation strategy that leverages ideas from coding theory to design intermediate computations at the worker nodes, in order to optimally deal with straggling workers. The proposed strategy, named as \emph{polynomial codes}, achieves the optimum recovery threshold, defined as the minimum number of workers that the master needs to wait for in order to compute the output. This is the first code that achieves the optimal utilization of redundancy for tolerating stragglers or failures in distributed matrix multiplication. Furthermore, by leveraging the algebraic structure of polynomial codes, we can map the reconstruction problem of the final output to a polynomial interpolation problem, which can be solved efficiently. Polynomial codes provide order-wise improvement over the state of the art in terms of recovery threshold, and are also optimal in terms of several other metrics including computation latency and communication load. Moreover, we extend this code to distributed convolution and show its order-wise optimality. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7027-polynomial-codes-an-optimal-design-for-high-dimensional-coded-matrix-multiplication |
| http://papers.nips.cc/paper/7027-polynomial-codes-an-optimal-design-for-high-dimensional-coded-matrix-multiplication.pdf | |
| PWC | https://paperswithcode.com/paper/polynomial-codes-an-optimal-design-for-high |
| Repo | |
| Framework | |
Analyzing Human and Machine Performance In Resolving Ambiguous Spoken Sentences
| Title | Analyzing Human and Machine Performance In Resolving Ambiguous Spoken Sentences |
| Authors | Hussein Ghaly, M, Michael el |
| Abstract | Written sentences can be more ambiguous than spoken sentences. We investigate this difference for two different types of ambiguity: prepositional phrase (PP) attachment and sentences where the addition of commas changes the meaning. We recorded a native English speaker saying several of each type of sentence both with and without disambiguating contextual information. These sentences were then presented either as text or audio and either with or without context to subjects who were asked to select the proper interpretation of the sentence. Results suggest that comma-ambiguous sentences are easier to disambiguate than PP-attachment-ambiguous sentences, possibly due to the presence of clear prosodic boundaries, namely silent pauses. Subject performance for sentences with PP-attachment ambiguity without context was 52{%} for text only while it was 72.4{%} for audio only, suggesting that audio has more disambiguating information than text. Using an analysis of acoustic features of two PP-attachment sentences, a simple classifier was implemented to resolve the PP-attachment ambiguity being early or late closure with a mean accuracy of 80{%}. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4603/ |
| https://www.aclweb.org/anthology/W17-4603 | |
| PWC | https://paperswithcode.com/paper/analyzing-human-and-machine-performance-in |
| Repo | |
| Framework | |
Tensor Biclustering
| Title | Tensor Biclustering |
| Authors | Soheil Feizi, Hamid Javadi, David Tse |
| Abstract | Consider a dataset where data is collected on multiple features of multiple individuals over multiple times. This type of data can be represented as a three dimensional individual/feature/time tensor and has become increasingly prominent in various areas of science. The tensor biclustering problem computes a subset of individuals and a subset of features whose signal trajectories over time lie in a low-dimensional subspace, modeling similarity among the signal trajectories while allowing different scalings across different individuals or different features. We study the information-theoretic limit of this problem under a generative model. Moreover, we propose an efficient spectral algorithm to solve the tensor biclustering problem and analyze its achievability bound in an asymptotic regime. Finally, we show the efficiency of our proposed method in several synthetic and real datasets. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6730-tensor-biclustering |
| http://papers.nips.cc/paper/6730-tensor-biclustering.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-biclustering |
| Repo | |
| Framework | |
Semgrex-Plus: a Tool for Automatic Dependency-Graph Rewriting
| Title | Semgrex-Plus: a Tool for Automatic Dependency-Graph Rewriting |
| Authors | Fabio Tamburini |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6528/ |
| https://www.aclweb.org/anthology/W17-6528 | |
| PWC | https://paperswithcode.com/paper/semgrex-plus-a-tool-for-automatic-dependency |
| Repo | |
| Framework | |
Hungarian Copula Constructions in Dependency Syntax and Parsing
| Title | Hungarian Copula Constructions in Dependency Syntax and Parsing |
| Authors | Katalin Ilona Simk{'o}, Veronika Vincze |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6527/ |
| https://www.aclweb.org/anthology/W17-6527 | |
| PWC | https://paperswithcode.com/paper/hungarian-copula-constructions-in-dependency |
| Repo | |
| Framework | |
Utilizando Features Lingu'\isticas Gen'ericas para Classifica\cc~ao de Triplas Relacionais em Portugu^es (Generic Linguistic Features for Relational Triples Classification in Portuguese)[In Portuguese]
| Title | Utilizando Features Lingu'\isticas Gen'ericas para Classifica\cc~ao de Triplas Relacionais em Portugu^es (Generic Linguistic Features for Relational Triples Classification in Portuguese)[In Portuguese] |
| Authors | George Barbosa, Daniela Barreiro Claro |
| Abstract | |
| Tasks | Open Information Extraction, Part-Of-Speech Tagging, Tokenization |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6616/ |
| https://www.aclweb.org/anthology/W17-6616 | |
| PWC | https://paperswithcode.com/paper/utilizando-features-linguasticas-genaricas |
| Repo | |
| Framework | |
IITP at SemEval-2017 Task 5: An Ensemble of Deep Learning and Feature Based Models for Financial Sentiment Analysis
| Title | IITP at SemEval-2017 Task 5: An Ensemble of Deep Learning and Feature Based Models for Financial Sentiment Analysis |
| Authors | Deepanway Ghosal, Shobhit Bhatnagar, Md Shad Akhtar, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | In this paper we propose an ensemble based model which combines state of the art deep learning sentiment analysis algorithms like Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) along with feature based models to identify optimistic or pessimistic sentiments associated with companies and stocks in financial texts. We build our system to participate in a competition organized by Semantic Evaluation 2017 International Workshop. We combined predictions from various models using an artificial neural network to determine the opinion towards an entity in (a) Microblog Messages and (b) News Headlines data. Our models achieved a cosine similarity score of 0.751 and 0.697 for the above two tracks giving us the rank of 2nd and 7th best team respectively. |
| Tasks | Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2154/ |
| https://www.aclweb.org/anthology/S17-2154 | |
| PWC | https://paperswithcode.com/paper/iitp-at-semeval-2017-task-5-an-ensemble-of |
| Repo | |
| Framework | |
PASS: A Dutch data-to-text system for soccer, targeted towards specific audiences
| Title | PASS: A Dutch data-to-text system for soccer, targeted towards specific audiences |
| Authors | Chris van der Lee, Emiel Krahmer, S Wubben, er |
| Abstract | We present PASS, a data-to-text system that generates Dutch soccer reports from match statistics. One of the novel elements of PASS is the fact that the system produces corpus-based texts tailored towards fans of one club or the other, which can most prominently be observed in the tone of voice used in the reports. Furthermore, the system is open source and uses a modular design, which makes it relatively easy for people to add extensions. Human-based evaluation shows that people are generally positive towards PASS in regards to its clarity and fluency, and that the tailoring is accurately recognized in most cases. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3513/ |
| https://www.aclweb.org/anthology/W17-3513 | |
| PWC | https://paperswithcode.com/paper/pass-a-dutch-data-to-text-system-for-soccer |
| Repo | |
| Framework | |
