Paper Group NANR 158
Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons. Consistency Analysis for Binary Classification Revisited. IJCNLP-2017 Task 4: Customer Feedback Analysis. Acoustic Model Compression with MAP adaptation. Combining CNNs and Pattern Matching for Question Interpretation in a Virtual Patient Dialogue System. USzeged: Identifying Verb …
Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons
| Title | Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons |
| Authors | Soheil Mohajer, Changho Suh, Adel Elmahdy |
| Abstract | We explore an active top-$K$ ranking problem based on pairwise comparisons that are collected possibly in a sequential manner as per our design choice. We consider two settings: (1) top-$K$ sorting in which the goal is to recover the top-$K$ items in order out of $n$ items; (2) top-$K$ partitioning where only the set of top-$K$ items is desired. Under a fairly general model which subsumes as special cases various models (e.g., Strong Stochastic Transitivity model, BTL model and uniform noise model), we characterize upper bounds on the sample size required for top-$K$ sorting as well as for top-$K$ partitioning. As a consequence, we demonstrate that active ranking can offer significant multiplicative gains in sample complexity over passive ranking. Depending on the underlying stochastic noise model, such gain varies from around $\frac{\log n}{\log \log n}$ to $\frac{ n^2 \log n }{\log \log n}$. We also present an algorithm that is applicable to both settings. |
| Tasks | Active Learning |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=819 |
| http://proceedings.mlr.press/v70/mohajer17a/mohajer17a.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-for-top-k-rank-aggregation |
| Repo | |
| Framework | |
Consistency Analysis for Binary Classification Revisited
| Title | Consistency Analysis for Binary Classification Revisited |
| Authors | Krzysztof Dembczyński, Wojciech Kotłowski, Oluwasanmi Koyejo, Nagarajan Natarajan |
| Abstract | Statistical learning theory is at an inflection point enabled by recent advances in understanding and optimizing a wide range of metrics. Of particular interest are non-decomposable metrics such as the F-measure and the Jaccard measure which cannot be represented as a simple average over examples. Non-decomposability is the primary source of difficulty in theoretical analysis, and interestingly has led to two distinct settings and notions of consistency. In this manuscript we analyze both settings, from statistical and algorithmic points of view, to explore the connections and to highlight differences between them for a wide range of metrics. The analysis complements previous results on this topic, clarifies common confusions around both settings, and provides guidance to the theory and practice of binary classification with complex metrics. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=787 |
| http://proceedings.mlr.press/v70/dembczynski17a/dembczynski17a.pdf | |
| PWC | https://paperswithcode.com/paper/consistency-analysis-for-binary |
| Repo | |
| Framework | |
IJCNLP-2017 Task 4: Customer Feedback Analysis
| Title | IJCNLP-2017 Task 4: Customer Feedback Analysis |
| Authors | Chao-Hong Liu, Yasufumi Moriya, Alberto Poncelas, Declan Groves |
| Abstract | This document introduces the IJCNLP 2017 Shared Task on Customer Feedback Analysis. In this shared task we have prepared corpora of customer feedback in four languages, i.e. English, French, Spanish and Japanese. They were annotated in a common meanings categorization, which was improved from an ADAPT-Microsoft pivot study on customer feedback. Twenty teams participated in the shared task and twelve of them have submitted prediction results. The results show that performance of prediction meanings of customer feedback is reasonable well in four languages. Nine system description papers are archived in the shared tasks proceeding. |
| Tasks | Machine Translation |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4004/ |
| https://www.aclweb.org/anthology/I17-4004 | |
| PWC | https://paperswithcode.com/paper/ijcnlp-2017-task-4-customer-feedback-analysis |
| Repo | |
| Framework | |
Acoustic Model Compression with MAP adaptation
| Title | Acoustic Model Compression with MAP adaptation |
| Authors | Katri Leino, Mikko Kurimo |
| Abstract | |
| Tasks | Model Compression, Quantization, Speech Recognition |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0208/ |
| https://www.aclweb.org/anthology/W17-0208 | |
| PWC | https://paperswithcode.com/paper/acoustic-model-compression-with-map |
| Repo | |
| Framework | |
Combining CNNs and Pattern Matching for Question Interpretation in a Virtual Patient Dialogue System
| Title | Combining CNNs and Pattern Matching for Question Interpretation in a Virtual Patient Dialogue System |
| Authors | Lifeng Jin, Michael White, Evan Jaffe, Laura Zimmerman, Douglas Danforth |
| Abstract | For medical students, virtual patient dialogue systems can provide useful training opportunities without the cost of employing actors to portray standardized patients. This work utilizes word- and character-based convolutional neural networks (CNNs) for question identification in a virtual patient dialogue system, outperforming a strong word- and character-based logistic regression baseline. While the CNNs perform well given sufficient training data, the best system performance is ultimately achieved by combining CNNs with a hand-crafted pattern matching system that is robust to label sparsity, providing a 10{%} boost in system accuracy and an error reduction of 47{%} as compared to the pattern-matching system alone. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5002/ |
| https://www.aclweb.org/anthology/W17-5002 | |
| PWC | https://paperswithcode.com/paper/combining-cnns-and-pattern-matching-for |
| Repo | |
| Framework | |
USzeged: Identifying Verbal Multiword Expressions with POS Tagging and Parsing Techniques
| Title | USzeged: Identifying Verbal Multiword Expressions with POS Tagging and Parsing Techniques |
| Authors | Katalin Ilona Simk{'o}, Vikt{'o}ria Kov{'a}cs, Veronika Vincze |
| Abstract | The paper describes our system submitted for the Workshop on Multiword Expressions{'} shared task on automatic identification of verbal multiword expressions. It uses POS tagging and dependency parsing to identify single- and multi-token verbal MWEs in text. Our system is language independent and competed on nine of the eighteen languages. Our paper describes how our system works and gives its error analysis for the languages it was submitted for. |
| Tasks | Dependency Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1705/ |
| https://www.aclweb.org/anthology/W17-1705 | |
| PWC | https://paperswithcode.com/paper/uszeged-identifying-verbal-multiword |
| Repo | |
| Framework | |
Recognizing Insufficiently Supported Arguments in Argumentative Essays
| Title | Recognizing Insufficiently Supported Arguments in Argumentative Essays |
| Authors | Christian Stab, Iryna Gurevych |
| Abstract | In this paper, we propose a new task for assessing the quality of natural language arguments. The premises of a well-reasoned argument should provide enough evidence for accepting or rejecting its claim. Although this criterion, known as sufficiency, is widely adopted in argumentation theory, there are no empirical studies on its applicability to real arguments. In this work, we show that human annotators substantially agree on the sufficiency criterion and introduce a novel annotated corpus. Furthermore, we experiment with feature-rich SVMs and Convolutional Neural Networks and achieve 84{%} accuracy for automatically identifying insufficiently supported arguments. The final corpus as well as the annotation guideline are freely available for encouraging future research on argument quality. |
| Tasks | Information Retrieval |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1092/ |
| https://www.aclweb.org/anthology/E17-1092 | |
| PWC | https://paperswithcode.com/paper/recognizing-insufficiently-supported |
| Repo | |
| Framework | |
Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning
| Title | Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning |
| Authors | Noam Brown, Tuomas Sandholm |
| Abstract | Iterative algorithms such as Counterfactual Regret Minimization (CFR) are the most popular way to solve large zero-sum imperfect-information games. In this paper we introduce Best-Response Pruning (BRP), an improvement to iterative algorithms such as CFR that allows poorly-performing actions to be temporarily pruned. We prove that when using CFR in zero-sum games, adding BRP will asymptotically prune any action that is not part of a best response to some Nash equilibrium. This leads to provably faster convergence and lower space requirements. Experiments show that BRP results in a factor of 7 reduction in space, and the reduction factor increases with game size. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=862 |
| http://proceedings.mlr.press/v70/brown17a/brown17a.pdf | |
| PWC | https://paperswithcode.com/paper/reduced-space-and-faster-convergence-in |
| Repo | |
| Framework | |
Potential and Limitations of Cross-Domain Sentiment Classification
| Title | Potential and Limitations of Cross-Domain Sentiment Classification |
| Authors | Jan Milan Deriu, Martin Weilenmann, Dirk Von Gruenigen, Mark Cieliebak |
| Abstract | In this paper we investigate the cross-domain performance of a current state-of-the-art sentiment analysis systems. For this purpose we train a convolutional neural network (CNN) on data from different domains and evaluate its performance on other domains. Furthermore, we evaluate the usefulness of combining a large amount of different smaller annotated corpora to a large corpus. Our results show that more sophisticated approaches are required to train a system that works equally well on various domains. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1103/ |
| https://www.aclweb.org/anthology/W17-1103 | |
| PWC | https://paperswithcode.com/paper/potential-and-limitations-of-cross-domain |
| Repo | |
| Framework | |
Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction
| Title | Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction |
| Authors | Sharid Lo{'a}iciga, Sara Stymne, Preslav Nakov, Christian Hardmeier, J{"o}rg Tiedemann, Mauro Cettolo, Yannick Versley |
| Abstract | We describe the design, the setup, and the evaluation results of the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The task asked participants to predict a target-language pronoun given a source-language pronoun in the context of a sentence. We further provided a lemmatized target-language human-authored translation of the source sentence, and automatic word alignments between the source sentence words and the target-language lemmata. The aim of the task was to predict, for each target-language pronoun placeholder, the word that should replace it from a small, closed set of classes, using any type of information that can be extracted from the entire document. We offered four subtasks, each for a different language pair and translation direction: English-to-French, English-to-German, German-to-English, and Spanish-to-English. Five teams participated in the shared task, making submissions for all language pairs. The evaluation results show that most participating teams outperformed two strong n-gram-based language model-based baseline systems by a sizable margin. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4801/ |
| https://www.aclweb.org/anthology/W17-4801 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-2017-discomt-shared-task-on |
| Repo | |
| Framework | |
GradAscent at EmoInt-2017: Character and Word Level Recurrent Neural Network Models for Tweet Emotion Intensity Detection
| Title | GradAscent at EmoInt-2017: Character and Word Level Recurrent Neural Network Models for Tweet Emotion Intensity Detection |
| Authors | Egor Lakomkin, Ch Bothe, rakant, Stefan Wermter |
| Abstract | The WASSA 2017 EmoInt shared task has the goal to predict emotion intensity values of tweet messages. Given the text of a tweet and its emotion category (anger, joy, fear, and sadness), the participants were asked to build a system that assigns emotion intensity values. Emotion intensity estimation is a challenging problem given the short length of the tweets, the noisy structure of the text and the lack of annotated data. To solve this problem, we developed an ensemble of two neural models, processing input on the character. and word-level with a lexicon-driven system. The correlation scores across all four emotions are averaged to determine the bottom-line competition metric, and our system ranks place forth in full intensity range and third in 0.5-1 range of intensity among 23 systems at the time of writing (June 2017). |
| Tasks | Language Modelling, Machine Translation, Sentiment Analysis, Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5222/ |
| https://www.aclweb.org/anthology/W17-5222 | |
| PWC | https://paperswithcode.com/paper/gradascent-at-emoint-2017-character-and-word-1 |
| Repo | |
| Framework | |
Practical Projective Structure From Motion (P2SfM)
| Title | Practical Projective Structure From Motion (P2SfM) |
| Authors | Ludovic Magerand, Alessio Del Bue |
| Abstract | This paper presents a solution to the Projective Structure from Motion (PSfM) problem able to deal efficiently with missing data, outliers and, for the first time, large scale 3D reconstruction scenarios. By embedding the projective depths into the projective parameters of the points and views, we decrease the number of unknowns to estimate and improve computational speed by optimizing standard linear Least Squares systems instead of homogeneous ones. In order to do so, we show that an extension of the linear constraints from the Generalized Projective Reconstruction Theorem can be transferred to the projective parameters, ensuring also a valid projective reconstruction in the process. We use an incremental approach that, starting from a solvable sub-problem, incrementally adds views and points until completion with a robust, outliers free, procedure. Experiments with simulated data shows that our approach is performing well, both in term of the quality of the reconstruction and the capacity to handle missing data and outliers with a reduced computational time. Finally, results on real datasets shows the ability of the method to be used in medium and large scale 3D reconstruction scenarios with high ratios of missing data (up to 98%). |
| Tasks | 3D Reconstruction |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Magerand_Practical_Projective_Structure_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Magerand_Practical_Projective_Structure_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/practical-projective-structure-from-motion |
| Repo | |
| Framework | |
REALEC learner treebank: annotation principles and evaluation of automatic parsing
| Title | REALEC learner treebank: annotation principles and evaluation of automatic parsing |
| Authors | Olga Lyashevskaya, Irina Panteleeva |
| Abstract | |
| Tasks | Dependency Parsing, Language Acquisition |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7612/ |
| https://www.aclweb.org/anthology/W17-7612 | |
| PWC | https://paperswithcode.com/paper/realec-learner-treebank-annotation-principles |
| Repo | |
| Framework | |
Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing
| Title | Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing |
| Authors | Tasha Nagamine, Nima Mesgarani |
| Abstract | Despite the recent success of deep learning, the nature of the transformations they apply to the input features remains poorly understood. This study provides an empirical framework to study the encoding properties of node activations in various layers of the network, and to construct the exact function applied to each data point in the form of a linear transform. These methods are used to discern and quantify properties of feed-forward neural networks trained to map acoustic features to phoneme labels. We show a selective and nonlinear warping of the feature space, achieved by forming prototypical functions to account for the possible variation of each class. This study provides a joint framework where the properties of node activations and the functions implemented by the network can be linked together. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=826 |
| http://proceedings.mlr.press/v70/nagamine17a/nagamine17a.pdf | |
| PWC | https://paperswithcode.com/paper/visualizing-and-understanding-multilayer |
| Repo | |
| Framework | |
Building Multiword Expressions Bilingual Lexicons for Domain Adaptation of an Example-Based Machine Translation System
| Title | Building Multiword Expressions Bilingual Lexicons for Domain Adaptation of an Example-Based Machine Translation System |
| Authors | Nasredine Semmar, Mariama Laib |
| Abstract | We describe in this paper a hybrid ap-proach to build automatically bilingual lexicons of Multiword Expressions (MWEs) from parallel corpora. We more specifically investigate the impact of using a domain-specific bilingual lexicon of MWEs on domain adaptation of an Example-Based Machine Translation (EBMT) system. We conducted experiments on the English-French language pair and two kinds of texts: in-domain texts from Europarl (European Parliament proceedings) and out-of-domain texts from Emea (European Medicines Agency documents) and Ecb (European Central Bank corpus). The obtained results indicate that integrating domain-specific bilingual lexicons of MWEs improves translation quality of the EBMT system when texts to translate are related to the specific domain and induces a relatively slight deterioration of translation quality when translating general-purpose texts. |
| Tasks | Domain Adaptation, Information Retrieval, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1085/ |
| https://doi.org/10.26615/978-954-452-049-6_085 | |
| PWC | https://paperswithcode.com/paper/building-multiword-expressions-bilingual |
| Repo | |
| Framework | |
