Paper Group NANR 132
Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets. k-Support and Ordered Weighted Sparsity for Overlapping Groups: Hardness and Algorithms. Injecting Word Embeddings with Another Language’s Resource : An Application of Bilingual Embeddings. Lexical Simplification with the Deep Structured Similarity Model. …
Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets
| Title | Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets |
| Authors | Athanasios Giannakopoulos, Claudiu Musat, Andreea Hossmann, Michael Baeriswyl |
| Abstract | Aspect Term Extraction (ATE) identifies opinionated aspect terms in texts and is one of the tasks in the SemEval Aspect Based Sentiment Analysis (ABSA) contest. The small amount of available datasets for supervised ATE and the costly human annotation for aspect term labelling give rise to the need for unsupervised ATE. In this paper, we introduce an architecture that achieves top-ranking performance for supervised ATE. Moreover, it can be used efficiently as feature extractor and classifier for unsupervised ATE. Our second contribution is a method to automatically construct datasets for ATE. We train a classifier on our automatically labelled datasets and evaluate it on the human annotated SemEval ABSA test sets. Compared to a strong rule-based baseline, we obtain a dramatically higher F-score and attain precision values above 80{%}. Our unsupervised method beats the supervised ABSA baseline from SemEval, while preserving high precision scores. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5224/ |
| https://www.aclweb.org/anthology/W17-5224 | |
| PWC | https://paperswithcode.com/paper/unsupervised-aspect-term-extraction-with-b-1 |
| Repo | |
| Framework | |
k-Support and Ordered Weighted Sparsity for Overlapping Groups: Hardness and Algorithms
| Title | k-Support and Ordered Weighted Sparsity for Overlapping Groups: Hardness and Algorithms |
| Authors | Cong Han Lim, Stephen Wright |
| Abstract | The k-support and OWL norms generalize the l1 norm, providing better prediction accuracy and better handling of correlated variables. We study the norms obtained from extending the k-support norm and OWL norms to the setting in which there are overlapping groups. The resulting norms are in general NP-hard to compute, but they are tractable for certain collections of groups. To demonstrate this fact, we develop a dynamic program for the problem of projecting onto the set of vectors supported by a fixed number of groups. Our dynamic program utilizes tree decompositions and its complexity scales with the treewidth. This program can be converted to an extended formulation which, for the associated group structure, models the k-group support norms and an overlapping group variant of the ordered weighted l1 norm. Numerical results demonstrate the efficacy of the new penalties. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6632-k-support-and-ordered-weighted-sparsity-for-overlapping-groups-hardness-and-algorithms |
| http://papers.nips.cc/paper/6632-k-support-and-ordered-weighted-sparsity-for-overlapping-groups-hardness-and-algorithms.pdf | |
| PWC | https://paperswithcode.com/paper/k-support-and-ordered-weighted-sparsity-for |
| Repo | |
| Framework | |
Injecting Word Embeddings with Another Language’s Resource : An Application of Bilingual Embeddings
| Title | Injecting Word Embeddings with Another Language’s Resource : An Application of Bilingual Embeddings |
| Authors | P, Prakhar ey, Vikram Pudi, Manish Shrivastava |
| Abstract | Word embeddings learned from text corpus can be improved by injecting knowledge from external resources, while at the same time also specializing them for similarity or relatedness. These knowledge resources (like WordNet, Paraphrase Database) may not exist for all languages. In this work we introduce a method to inject word embeddings of a language with knowledge resource of another language by leveraging bilingual embeddings. First we improve word embeddings of German, Italian, French and Spanish using resources of English and test them on variety of word similarity tasks. Then we demonstrate the utility of our method by creating improved embeddings for Urdu and Telugu languages using Hindi WordNet, beating the previously established baseline for Urdu. |
| Tasks | Learning Word Embeddings, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2020/ |
| https://www.aclweb.org/anthology/I17-2020 | |
| PWC | https://paperswithcode.com/paper/injecting-word-embeddings-with-another |
| Repo | |
| Framework | |
Lexical Simplification with the Deep Structured Similarity Model
| Title | Lexical Simplification with the Deep Structured Similarity Model |
| Authors | Lis Pereira, Xiaodong Liu, John Lee |
| Abstract | We explore the application of a Deep Structured Similarity Model (DSSM) to ranking in lexical simplification. Our results show that the DSSM can effectively capture fine-grained features to perform semantic matching when ranking substitution candidates, outperforming the state-of-the-art on two standard datasets used for the task. |
| Tasks | Image Captioning, Learning Word Embeddings, Lexical Simplification, Machine Translation, Question Answering, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2073/ |
| https://www.aclweb.org/anthology/I17-2073 | |
| PWC | https://paperswithcode.com/paper/lexical-simplification-with-the-deep |
| Repo | |
| Framework | |
Joint Concept Learning and Semantic Parsing from Natural Language Explanations
| Title | Joint Concept Learning and Semantic Parsing from Natural Language Explanations |
| Authors | Shashank Srivastava, Igor Labutov, Tom Mitchell |
| Abstract | Natural language constitutes a predominant medium for much of human learning and pedagogy. We consider the problem of concept learning from natural language explanations, and a small number of labeled examples of the concept. For example, in learning the concept of a phishing email, one might say {`}this is a phishing email because it asks for your bank account number{'}. Solving this problem involves both learning to interpret open ended natural language statements, and learning the concept itself. We present a joint model for (1) language interpretation (semantic parsing) and (2) concept learning (classification) that does not require labeling statements with logical forms. Instead, the model prefers discriminative interpretations of statements in context of observable features of the data as a weak signal for parsing. On a dataset of email-related concepts, our approach yields across-the-board improvements in classification performance, with a 30{%} relative improvement in F1 score over competitive methods in the low data regime. | |
| Tasks | Semantic Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1161/ |
| https://www.aclweb.org/anthology/D17-1161 | |
| PWC | https://paperswithcode.com/paper/joint-concept-learning-and-semantic-parsing |
| Repo | |
| Framework | |
Beyond Worst-case: A Probabilistic Analysis of Affine Policies in Dynamic Optimization
| Title | Beyond Worst-case: A Probabilistic Analysis of Affine Policies in Dynamic Optimization |
| Authors | Omar El Housni, Vineet Goyal |
| Abstract | Affine policies (or control) are widely used as a solution approach in dynamic optimization where computing an optimal adjustable solution is usually intractable. While the worst case performance of affine policies can be significantly bad, the empirical performance is observed to be near-optimal for a large class of problem instances. For instance, in the two-stage dynamic robust optimization problem with linear covering constraints and uncertain right hand side, the worst-case approximation bound for affine policies is $O(\sqrt m)$ that is also tight (see Bertsimas and Goyal (2012)), whereas observed empirical performance is near-optimal. In this paper, we aim to address this stark-contrast between the worst-case and the empirical performance of affine policies. In particular, we show that affine policies give a good approximation for the two-stage adjustable robust optimization problem with high probability on random instances where the constraint coefficients are generated i.i.d. from a large class of distributions; thereby, providing a theoretical justification of the observed empirical performance. On the other hand, we also present a distribution such that the performance bound for affine policies on instances generated according to that distribution is $\Omega(\sqrt m)$ with high probability; however, the constraint coefficients are not i.i.d.. This demonstrates that the empirical performance of affine policies can depend on the generative model for instances. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7061-beyond-worst-case-a-probabilistic-analysis-of-affine-policies-in-dynamic-optimization |
| http://papers.nips.cc/paper/7061-beyond-worst-case-a-probabilistic-analysis-of-affine-policies-in-dynamic-optimization.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-worst-case-a-probabilistic-analysis-of |
| Repo | |
| Framework | |
Differentially Private Submodular Maximization: Data Summarization in Disguise
| Title | Differentially Private Submodular Maximization: Data Summarization in Disguise |
| Authors | Marko Mitrovic, Mark Bun, Andreas Krause, Amin Karbasi |
| Abstract | Many data summarization applications are captured by the general framework of submodular maximization. As a consequence, a wide range of efficient approximation algorithms have been developed. However, when such applications involve sensitive data about individuals, their privacy concerns are not automatically addressed. To remedy this problem, we propose a general and systematic study of differentially private submodular maximization. We present privacy-preserving algorithms for both monotone and non-monotone submodular maximization under cardinality, matroid, and p-extendible system constraints, with guarantees that are competitive with optimal. Along the way, we analyze a new algorithm for non-monotone submodular maximization, which is the first (even non-privately) to achieve a constant approximation ratio while running in linear time. We additionally provide two concrete experiments to validate the efficacy of these algorithms. |
| Tasks | Data Summarization |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=637 |
| http://proceedings.mlr.press/v70/mitrovic17a/mitrovic17a.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-submodular |
| Repo | |
| Framework | |
Convergence rates of a partition based Bayesian multivariate density estimation method
| Title | Convergence rates of a partition based Bayesian multivariate density estimation method |
| Authors | Linxi Liu, Dangna Li, Wing Hung Wong |
| Abstract | We study a class of non-parametric density estimators under Bayesian settings. The estimators are obtained by adaptively partitioning the sample space. Under a suitable prior, we analyze the concentration rate of the posterior distribution, and demonstrate that the rate does not directly depend on the dimension of the problem in several special cases. Another advantage of this class of Bayesian density estimators is that it can adapt to the unknown smoothness of the true density function, thus achieving the optimal convergence rate without artificial conditions on the density. We also validate the theoretical results on a variety of simulated data sets. |
| Tasks | Density Estimation |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7059-convergence-rates-of-a-partition-based-bayesian-multivariate-density-estimation-method |
| http://papers.nips.cc/paper/7059-convergence-rates-of-a-partition-based-bayesian-multivariate-density-estimation-method.pdf | |
| PWC | https://paperswithcode.com/paper/convergence-rates-of-a-partition-based |
| Repo | |
| Framework | |
Predicting Translation Performance with Referential Translation Machines
| Title | Predicting Translation Performance with Referential Translation Machines |
| Authors | Ergun Bi{\c{c}}ici |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4759/ |
| https://www.aclweb.org/anthology/W17-4759 | |
| PWC | https://paperswithcode.com/paper/predicting-translation-performance-with |
| Repo | |
| Framework | |
Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation
| Title | Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation |
| Authors | Pranava Swaroop Madhyastha, Josiah Wang, Lucia Specia |
| Abstract | |
| Tasks | Image Captioning, Image Classification, Machine Translation, Multimodal Machine Translation, Question Answering, Visual Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4752/ |
| https://www.aclweb.org/anthology/W17-4752 | |
| PWC | https://paperswithcode.com/paper/sheffield-multimt-using-object-posterior |
| Repo | |
| Framework | |
NICT-NAIST System for WMT17 Multimodal Translation Task
| Title | NICT-NAIST System for WMT17 Multimodal Translation Task |
| Authors | Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig, Satoshi Nakamura |
| Abstract | |
| Tasks | Image Retrieval, Machine Translation, Multimodal Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4753/ |
| https://www.aclweb.org/anthology/W17-4753 | |
| PWC | https://paperswithcode.com/paper/nict-naist-system-for-wmt17-multimodal |
| Repo | |
| Framework | |
Interactive Submodular Bandit
| Title | Interactive Submodular Bandit |
| Authors | Lin Chen, Andreas Krause, Amin Karbasi |
| Abstract | In many machine learning applications, submodular functions have been used as a model for evaluating the utility or payoff of a set such as news items to recommend, sensors to deploy in a terrain, nodes to influence in a social network, to name a few. At the heart of all these applications is the assumption that the underlying utility/payoff function is known a priori, hence maximizing it is in principle possible. In real life situations, however, the utility function is not fully known in advance and can only be estimated via interactions. For instance, whether a user likes a movie or not can be reliably evaluated only after it was shown to her. Or, the range of influence of a user in a social network can be estimated only after she is selected to advertise the product. We model such problems as an interactive submodular bandit optimization, where in each round we receive a context (e.g., previously selected movies) and have to choose an action (e.g., propose a new movie). We then receive a noisy feedback about the utility of the action (e.g., ratings) which we model as a submodular function over the context-action space. We develop SM-UCB that efficiently trades off exploration (collecting more data) and exploration (proposing a good action given gathered data) and achieves a $O(\sqrt{T})$ regret bound after $T$ rounds of interaction. Given a bounded-RKHS norm kernel over the context-action-payoff space that governs the smoothness of the utility function, SM-UCB keeps an upper-confidence bound on the payoff function that allows it to asymptotically achieve no-regret. Finally, we evaluate our results on four concrete applications, including movie recommendation (on the MovieLense data set), news recommendation (on Yahoo! Webscope dataset), interactive influence maximization (on a subset of the Facebook network), and personalized data summarization (on Reuters Corpus). In all these applications, we observe that SM-UCB consistently outperforms the prior art. |
| Tasks | Data Summarization |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6619-interactive-submodular-bandit |
| http://papers.nips.cc/paper/6619-interactive-submodular-bandit.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-submodular-bandit |
| Repo | |
| Framework | |
Methodical Evaluation of Arabic Word Embeddings
| Title | Methodical Evaluation of Arabic Word Embeddings |
| Authors | Mohammed Elrazzaz, Shady Elbassuoni, Khaled Shaban, Chadi Helwe |
| Abstract | Many unsupervised learning techniques have been proposed to obtain meaningful representations of words from text. In this study, we evaluate these various techniques when used to generate Arabic word embeddings. We first build a benchmark for the Arabic language that can be utilized to perform intrinsic evaluation of different word embeddings. We then perform additional extrinsic evaluations of the embeddings based on two NLP tasks. |
| Tasks | Document Classification, Learning Word Embeddings, Named Entity Recognition, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2072/ |
| https://www.aclweb.org/anthology/P17-2072 | |
| PWC | https://paperswithcode.com/paper/methodical-evaluation-of-arabic-word |
| Repo | |
| Framework | |
Bilexical Embeddings for Quality Estimation
| Title | Bilexical Embeddings for Quality Estimation |
| Authors | Fr{'e}d{'e}ric Blain, Carolina Scarton, Lucia Specia |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4760/ |
| https://www.aclweb.org/anthology/W17-4760 | |
| PWC | https://paperswithcode.com/paper/bilexical-embeddings-for-quality-estimation |
| Repo | |
| Framework | |
Improving Machine Translation Quality Estimation with Neural Network Features
| Title | Improving Machine Translation Quality Estimation with Neural Network Features |
| Authors | Zhiming Chen, Yiming Tan, Chenlin Zhang, Qingyu Xiang, Lilin Zhang, Maoxi Li, Mingwen Wang |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Sentence Embedding, Speech Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4761/ |
| https://www.aclweb.org/anthology/W17-4761 | |
| PWC | https://paperswithcode.com/paper/improving-machine-translation-quality |
| Repo | |
| Framework | |
