Paper Group NAWR 4
A modernised version of the Glossa corpus search system. Correcting Contradictions. Meta-Optimizing Semantic Evolutionary Search. Assessing Convincingness of Arguments in Online Debates with Limited Number of Features. Finnish resources for evaluating language model semantics. Toward Universal Dependencies for Ainu. Unsupervised Adaptation for Deep …
A modernised version of the Glossa corpus search system
| Title | A modernised version of the Glossa corpus search system |
| Authors | Anders N{\o}klestad, Kristin Hagen, Janne Bondi Johannessen, Micha{\l} Kosek, Joel Priestley |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0232/ |
| https://www.aclweb.org/anthology/W17-0232 | |
| PWC | https://paperswithcode.com/paper/a-modernised-version-of-the-glossa-corpus |
| Repo | https://github.com/textlab/cglossa |
| Framework | none |
Correcting Contradictions
| Title | Correcting Contradictions |
| Authors | Aikaterini-Lida Kalouli, Valeria de Paiva, Livy Real |
| Abstract | |
| Tasks | Common Sense Reasoning, Natural Language Inference, Semantic Textual Similarity |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7205/ |
| https://www.aclweb.org/anthology/W17-7205 | |
| PWC | https://paperswithcode.com/paper/correcting-contradictions |
| Repo | https://github.com/kkalouli/SICK-processing |
| Framework | none |
Meta-Optimizing Semantic Evolutionary Search
| Title | Meta-Optimizing Semantic Evolutionary Search |
| Authors | Moshe Looks |
| Abstract | I present MOSES (meta-optimizing semantic evolutionary search), a new probabilistic modeling (estimation of distribution) approach to program evolution. Distributions are not estimated over the entire space of programs. Rather, a novel representation-building procedure that exploits domain knowledge is used to dynamically select program subspaces for estimation over. This leads to a system of demes consisting of alternative representations (i.e. program subspaces) that are maintained simultaneously and managed by the overall system. Application of MOSES to solve the artificial ant and hierarchically composed parity-multiplexer problems is described, with results showing superior performance. An analysis of the probabilistic models constructed shows that representation-building allows MOSES to exploit linkages in solving these problems. |
| Tasks | Problem Decomposition |
| Published | 2017-07-11 |
| URL | https://wiki.opencog.org/w/Meta-Optimizing_Semantic_Evolutionary_Search |
| http://metacog.org/papers/gecco07b_full.pdf | |
| PWC | https://paperswithcode.com/paper/meta-optimizing-semantic-evolutionary-search |
| Repo | https://github.com/opencog/moses |
| Framework | none |
Assessing Convincingness of Arguments in Online Debates with Limited Number of Features
| Title | Assessing Convincingness of Arguments in Online Debates with Limited Number of Features |
| Authors | Lisa Andreevna Chalaguine, Claudia Schulz |
| Abstract | We propose a new method in the field of argument analysis in social media to determining convincingness of arguments in online debates, following previous research by Habernal and Gurevych (2016). Rather than using argument specific feature values, we measure feature values relative to the average value in the debate, allowing us to determine argument convincingness with fewer features (between 5 and 35) than normally used for natural language processing tasks. We use a simple forward-feeding neural network for this task and achieve an accuracy of 0.77 which is comparable to the accuracy obtained using 64k features and a support vector machine by Habernal and Gurevych. |
| Tasks | Argument Mining |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-4008/ |
| https://www.aclweb.org/anthology/E17-4008 | |
| PWC | https://paperswithcode.com/paper/assessing-convincingness-of-arguments-in |
| Repo | https://github.com/lisanka93/individualProject |
| Framework | none |
Finnish resources for evaluating language model semantics
| Title | Finnish resources for evaluating language model semantics |
| Authors | Viljami Venekoski, Jouko Vankka |
| Abstract | |
| Tasks | Language Modelling, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0228/ |
| https://www.aclweb.org/anthology/W17-0228 | |
| PWC | https://paperswithcode.com/paper/finnish-resources-for-evaluating-language |
| Repo | https://github.com/venekoski/FinSemEvl |
| Framework | none |
Toward Universal Dependencies for Ainu
| Title | Toward Universal Dependencies for Ainu |
| Authors | Hajime Senuma, Akiko Aizawa |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0417/ |
| https://www.aclweb.org/anthology/W17-0417 | |
| PWC | https://paperswithcode.com/paper/toward-universal-dependencies-for-ainu |
| Repo | https://github.com/hajimes/ud-ainu |
| Framework | none |
Unsupervised Adaptation for Deep Stereo
| Title | Unsupervised Adaptation for Deep Stereo |
| Authors | Alessio Tonioni, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano |
| Abstract | Recent ground-breaking works have shown that deep neural networks can be trained end-to-end to regress dense disparity maps directly from image pairs. Computer generated imagery is deployed to gather the large data corpus required to train such networks, an additional fine-tuning allowing to adapt the model to work well also on real and possibly diverse environments. Yet, besides a few public datasets such as Kitti, the ground-truth needed to adapt the network to a new scenario is hardly available in practice. In this paper we propose a novel unsupervised adaptation approach that enables to fine-tune a deep learning stereo model without any ground-truth information. We rely on off-the-shelf stereo algorithms together with state-of-the-art confidence measures, the latter able to ascertain upon correctness of the measurements yielded by former. Thus, we train the network based on a novel loss-function that penalizes predictions disagreeing with the highly confident disparities provided by the algorithm and enforces a smoothness constraint. Experiments on popular datasets (KITTI 2012, KITTI 2015 and Middlebury 2014) and other challenging test images demonstrate the effectiveness of our proposal. |
| Tasks | |
| Published | 2017-10-22 |
| URL | https://ieeexplore.ieee.org/document/8237440 |
| http://vision.disi.unibo.it/~mpoggi/papers/iccv2017_adaptation.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-adaptation-for-deep-stereo-1 |
| Repo | https://github.com/CVLAB-Unibo/Unsupervised-Adaptation-for-Deep-Stereo |
| Framework | tf |
Building a Non-Trivial Paraphrase Corpus Using Multiple Machine Translation Systems
| Title | Building a Non-Trivial Paraphrase Corpus Using Multiple Machine Translation Systems |
| Authors | Yui Suzuki, Tomoyuki Kajiwara, Mamoru Komachi |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Paraphrase Generation, Paraphrase Identification, Question Answering |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3007/ |
| https://www.aclweb.org/anthology/P17-3007 | |
| PWC | https://paperswithcode.com/paper/building-a-non-trivial-paraphrase-corpus |
| Repo | https://github.com/tmu-nlp/paraphrase-corpus |
| Framework | none |
Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing
| Title | Multilingual Back-and-Forth Conversion between Content and Function Head for Easy Dependency Parsing |
| Authors | Ryosuke Kohita, Hiroshi Noji, Yuji Matsumoto |
| Abstract | Universal Dependencies (UD) is becoming a standard annotation scheme cross-linguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words. To improve the parsability of UD, we propose a back-and-forth conversion algorithm, in which we preprocess the training treebank to increase parsability, and reconvert the parser outputs to follow the UD scheme as a postprocess. We show that this technique consistently improves LAS across languages even with a state-of-the-art parser, in particular on core dependency arcs such as nominal modifier. We also provide an in-depth analysis to understand why our method increases parsability. |
| Tasks | Dependency Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2001/ |
| https://www.aclweb.org/anthology/E17-2001 | |
| PWC | https://paperswithcode.com/paper/multilingual-back-and-forth-conversion |
| Repo | https://github.com/kohilin/MultiBFConv |
| Framework | none |
Collaborative Metric Learning
| Title | Collaborative Metric Learning |
| Authors | Cheng-Kang Hsieh, Longqi Yang, Yin Cui, Tsung-Yi Lin, Serge Belongie, Deborah Estrin |
| Abstract | Metric learning algorithms produce distance metrics that capture the important relationships among data. In this work we study the connection between metric learning and collaborative filtering. We propose Collaborative Metric Learning (CML) which learns a joint metric space to encode not only users’ preferences but also the user-user and item-item similarity. The proposed algorithm outperforms state-of-the-art collaborative filtering algorithms on a wide range of recommendation tasks and uncovers the underlying spectrum of users’ fine-grained preferences. CML also achieves significant speedup for Top-K recommendation tasks using off-the-shelf, approximate nearest-neighbor search, with negligible accuracy reduction. |
| Tasks | Metric Learning, Recommendation Systems |
| Published | 2017-04-01 |
| URL | https://ylongqi.com/publication/www17b/ |
| https://ylongqi.com/paper/HsiehYCLBE17.pdf | |
| PWC | https://paperswithcode.com/paper/collaborative-metric-learning |
| Repo | https://github.com/changun/CollMetric |
| Framework | tf |
Efficient Approximation Algorithms for Strings Kernel Based Sequence Classification
| Title | Efficient Approximation Algorithms for Strings Kernel Based Sequence Classification |
| Authors | Muhammad Farhan, Juvaria Tariq, Arif Zaman, Mudassir Shabbir, Imdad Ullah Khan |
| Abstract | Sequence classification algorithms, such as SVM, require a definition of distance (similarity) measure between two sequences. A commonly used notion of similarity is the number of matches between k-mers (k-length subsequences) in the two sequences. Extending this definition, by considering two k-mers to match if their distance is at most m, yields better classification performance. This, however, makes the problem computationally much more complex. Known algorithms to compute this similarity have computational complexity that render them applicable only for small values of k and m. In this work, we develop novel techniques to efficiently and accurately estimate the pairwise similarity score, which enables us to use much larger values of k and m, and get higher predictive accuracy. This opens up a broad avenue of applying this classification approach to audio, images, and text sequences. Our algorithm achieves excellent approximation performance with theoretical guarantees. In the process we solve an open combinatorial problem, which was posed as a major hindrance to the scalability of existing solutions. We give analytical bounds on quality and runtime of our algorithm and report its empirical performance on real world biological and music sequences datasets. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7269-efficient-approximation-algorithms-for-strings-kernel-based-sequence-classification |
| http://papers.nips.cc/paper/7269-efficient-approximation-algorithms-for-strings-kernel-based-sequence-classification.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-approximation-algorithms-for |
| Repo | https://github.com/mufarhan/sequence_class_NIPS_2017 |
| Framework | none |
Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks
| Title | Multilingual Lexicalized Constituency Parsing with Word-Level Auxiliary Tasks |
| Authors | Maximin Coavoux, Beno{^\i}t Crabb{'e} |
| Abstract | We introduce a constituency parser based on a bi-LSTM encoder adapted from recent work (Cross and Huang, 2016b; Kiperwasser and Goldberg, 2016), which can incorporate a lower level character biLSTM (Ballesteros et al., 2015; Plank et al., 2016). We model two important interfaces of constituency parsing with auxiliary tasks supervised at the word level: (i) part-of-speech (POS) and morphological tagging, (ii) functional label prediction. On the SPMRL dataset, our parser obtains above state-of-the-art results on constituency parsing without requiring either predicted POS or morphological tags, and outputs labelled dependency trees. |
| Tasks | Constituency Parsing, Morphological Analysis, Morphological Tagging |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2053/ |
| https://www.aclweb.org/anthology/E17-2053 | |
| PWC | https://paperswithcode.com/paper/multilingual-lexicalized-constituency-parsing |
| Repo | https://github.com/mcoavoux/mtg |
| Framework | none |
Anomaly Detection with Robust Deep Autoencoders
| Title | Anomaly Detection with Robust Deep Autoencoders |
| Authors | Chong Zhou, Randy C. Paffenroth |
| Abstract | Deep autoencoders, and other deep neural networks, have demonstrated their effectiveness in discovering non-linear features across many problem domains. However, in many real-world problems, large outliers and pervasive noise are commonplace, and one may not have access to clean training data as required by standard deep denoising autoencoders. Herein, we demonstrate novel extensions to deep autoencoders which not only maintain a deep autoencoders’ ability to discover high quality, non-linear features but can also eliminate outliers and noise without access to any clean training data. Our model is inspired by Robust Principal Component Analysis, and we split the input data X into two parts, $X = L_{D} + S$, where $L_{D}$ can be effectively reconstructed by a deep autoencoder and $S$ contains the outliers and noise in the original data X. Since such splitting increases the robustness of standard deep autoencoders, we name our model a “Robust Deep Autoencoder (RDA)". Further, we present generalizations of our results to grouped sparsity norms which allow one to distinguish random anomalies from other types of structured corruptions, such as a collection of features being corrupted across many instances or a collection of instances having more corruptions than their fellows. Such “Group Robust Deep Autoencoders (GRDA)” give rise to novel anomaly detection approaches whose superior performance we demonstrate on a selection of benchmark problems. |
| Tasks | Anomaly Detection, Denoising |
| Published | 2017-08-13 |
| URL | https://dl.acm.org/citation.cfm?id=3098052 |
| https://dl.acm.org/citation.cfm?id=3098052 | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-with-robust-deep |
| Repo | https://github.com/zc8340311/RobustAutoencoder |
| Framework | tf |
Exploring Diachronic Lexical Semantics with JeSemE
| Title | Exploring Diachronic Lexical Semantics with JeSemE |
| Authors | Johannes Hellrich, Udo Hahn |
| Abstract | |
| Tasks | Information Retrieval, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4006/ |
| https://www.aclweb.org/anthology/P17-4006 | |
| PWC | https://paperswithcode.com/paper/exploring-diachronic-lexical-semantics-with |
| Repo | https://github.com/hellrich/JeSemE |
| Framework | none |
ClassifierGuesser: A Context-based Classifier Prediction System for Chinese Language Learners
| Title | ClassifierGuesser: A Context-based Classifier Prediction System for Chinese Language Learners |
| Authors | Nicole Peinelt, Maria Liakata, Shu-Kai Hsieh |
| Abstract | Classifiers are function words that are used to express quantities in Chinese and are especially difficult for language learners. In contrast to previous studies, we argue that the choice of classifiers is highly contextual and train context-aware machine learning models based on a novel publicly available dataset, outperforming previous baselines. We further present use cases for our database and models in an interactive demo system. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3011/ |
| https://www.aclweb.org/anthology/I17-3011 | |
| PWC | https://paperswithcode.com/paper/classifierguesser-a-context-based-classifier |
| Repo | https://github.com/wuningxi/ChineseClassifierDataset |
| Framework | none |
