Paper Group NANR 26
3D-CODED: 3D Correspondences by Deep Deformation. Universal Morpho-Syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task. Research Challenges in Building a Voice-based Artificial Personal Shopper - Position Paper. Exploring Classifier Combinations for Language Variety Identification. CRF-S …
3D-CODED: 3D Correspondences by Deep Deformation
| Title | 3D-CODED: 3D Correspondences by Deep Deformation |
| Authors | Thibault Groueix, Matthew Fisher, Vladimir G. Kim, Bryan C. Russell, Mathieu Aubry |
| Abstract | We present a new deep learning approach for matching deformable shapes by introducing Shape Deformation Networks which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a template, that parameterizes the surface, and (ii) a learnt global feature vector that parameterizes the transformation of the template into the input surface. By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template. We show that these correspondences can be improved by an additional step which improves the shape feature by minimizing the Chamfer distance between the input and transformed template. We demonstrate that our simple approach improves on state-of-the-art results on the difficult FAUST-inter challenge, with an average correspondence error of 2.88cm. We show, on the TOSCA dataset, that our method is robust to many types of perturbations, and generalizes to non-human shapes. This robustness allows it to perform well on real unclean, meshes from the the SCAPE dataset. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Thibault_Groueix_Shape_correspondences_from_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Thibault_Groueix_Shape_correspondences_from_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/3d-coded-3d-correspondences-by-deep |
| Repo | |
| Framework | |
Universal Morpho-Syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task
| Title | Universal Morpho-Syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task |
| Authors | Amit Seker, Amir More, Reut Tsarfaty |
| Abstract | We present the contribution of the ONLP lab at the Open University of Israel to the UD shared task on multilingual parsing from raw text to Universal Dependencies. Our contribution is based on a transition-based parser called {}yap {--} yet another parser{'}, which includes a standalone morphological model, a standalone dependency model, and a joint morphosyntactic model. In the task we used \textit{yap}{}s standalone dependency parser to parse input morphologically disambiguated by UDPipe, and obtained the official score of 58.35 LAS. In our follow up investigation we use yap to show how the incorporation of morphological and lexical resources may improve the performance of end-to-end raw-to-dependencies parsing in the case of a \textit{morphologically-rich} and \textit{low-resource} language, Modern Hebrew. Our results on Hebrew underscore the importance of CoNLL-UL, a UD-compatible standard for accessing external lexical resources, for enhancing end-to-end UD parsing, in particular for morphologically rich and low-resource languages. We thus encourage the community to create, convert, or make available more such lexica in future tasks. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-2021/ |
| https://www.aclweb.org/anthology/K18-2021 | |
| PWC | https://paperswithcode.com/paper/universal-morpho-syntactic-parsing-and-the |
| Repo | |
| Framework | |
Research Challenges in Building a Voice-based Artificial Personal Shopper - Position Paper
| Title | Research Challenges in Building a Voice-based Artificial Personal Shopper - Position Paper |
| Authors | Nut Limsopatham, Oleg Rokhlenko, David Carmel |
| Abstract | Recent advances in automatic speech recognition lead toward enabling a voice conversation between a human user and an intelligent virtual assistant. This provides a potential foundation for developing artificial personal shoppers for e-commerce websites, such as Alibaba, Amazon, and eBay. Personal shoppers are valuable to the on-line shops as they enhance user engagement and trust by promptly dealing with customers{'} questions and concerns. Developing an artificial personal shopper requires the agent to leverage knowledge about the customer and products, while interacting with the customer in a human-like conversation. In this position paper, we motivate and describe \textit{the artificial personal shopper task}, and then address a research agenda for this task by adapting and advancing existing information retrieval and natural language processing technologies. |
| Tasks | Chatbot, Information Retrieval, Machine Translation, Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5706/ |
| https://www.aclweb.org/anthology/W18-5706 | |
| PWC | https://paperswithcode.com/paper/research-challenges-in-building-a-voice-based |
| Repo | |
| Framework | |
Exploring Classifier Combinations for Language Variety Identification
| Title | Exploring Classifier Combinations for Language Variety Identification |
| Authors | Tim Kreutz, Walter Daelemans |
| Abstract | This paper describes CLiPS{'}s submissions for the Discriminating between Dutch and Flemish in Subtitles (DFS) shared task at VarDial 2018. We explore different ways to combine classifiers trained on different feature groups. Our best system uses two Linear SVM classifiers; one trained on lexical features (word n-grams) and one trained on syntactic features (PoS n-grams). The final prediction for a document to be in Flemish Dutch or Netherlandic Dutch is made by the classifier that outputs the highest probability for one of the two labels. This confidence vote approach outperforms a meta-classifier on the development data and on the test data. |
| Tasks | Language Identification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3922/ |
| https://www.aclweb.org/anthology/W18-3922 | |
| PWC | https://paperswithcode.com/paper/exploring-classifier-combinations-for |
| Repo | |
| Framework | |
CRF-Seq and CRF-DepTree at PARSEME Shared Task 2018: Detecting Verbal MWEs using Sequential and Dependency-Based Approaches
| Title | CRF-Seq and CRF-DepTree at PARSEME Shared Task 2018: Detecting Verbal MWEs using Sequential and Dependency-Based Approaches |
| Authors | Erwan Moreau, Ashjan Alsulaimani, Alfredo Maldonado, Carl Vogel |
| Abstract | This paper describes two systems for detecting Verbal Multiword Expressions (VMWEs) which both competed in the closed track at the PARSEME VMWE Shared Task 2018. CRF-DepTree-categs implements an approach based on the dependency tree, intended to exploit the syntactic and semantic relations between tokens; CRF-Seq-nocategs implements a robust sequential method which requires only lemmas and morphosyntactic tags. Both systems ranked in the top half of the ranking, the latter ranking second for token-based evaluation. The code for both systems is published under the GNU General Public License version 3.0 and is available at \url{http://github.com/erwanm/adapt-vmwe18}. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4926/ |
| https://www.aclweb.org/anthology/W18-4926 | |
| PWC | https://paperswithcode.com/paper/crf-seq-and-crf-deptree-at-parseme-shared |
| Repo | |
| Framework | |
Objective Function Learning to Match Human Judgements for Optimization-Based Summarization
| Title | Objective Function Learning to Match Human Judgements for Optimization-Based Summarization |
| Authors | Maxime Peyrard, Iryna Gurevych |
| Abstract | Supervised summarization systems usually rely on supervision at the sentence or n-gram level provided by automatic metrics like ROUGE, which act as noisy proxies for human judgments. In this work, we learn a summary-level scoring function $\theta$ including human judgments as supervision and automatically generated data as regularization. We extract summaries with a genetic algorithm using $\theta$ as a fitness function. We observe strong and promising performances across datasets in both automatic and manual evaluation. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2103/ |
| https://www.aclweb.org/anthology/N18-2103 | |
| PWC | https://paperswithcode.com/paper/objective-function-learning-to-match-human |
| Repo | |
| Framework | |
A Comparison Of Emotion Annotation Schemes And A New Annotated Data Set
| Title | A Comparison Of Emotion Annotation Schemes And A New Annotated Data Set |
| Authors | Ian Wood, John P. McCrae, Vladimir Andryushechkin, Paul Buitelaar |
| Abstract | |
| Tasks | Emotion Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1192/ |
| https://www.aclweb.org/anthology/L18-1192 | |
| PWC | https://paperswithcode.com/paper/a-comparison-of-emotion-annotation-schemes |
| Repo | |
| Framework | |
Survey of Higher Order Rigid Body Motion Interpolation Methods for Keyframe Animation and Continuous-Time Trajectory Estimation
| Title | Survey of Higher Order Rigid Body Motion Interpolation Methods for Keyframe Animation and Continuous-Time Trajectory Estimation |
| Authors | Adrian Haarbach, Tolga Birdal, Slobodan Ilic |
| Abstract | In this survey we carefully analyze the characteristics of higher order rigid body motion interpolation methods to obtain a continuous trajectory from a discrete set of poses. We first discuss the tradeoff between continuity, local control and approximation of classical Euclidean interpolation schemes such as Bezier and B-splines. The benefits of the manifold of unit quaternions SU(2), a double-cover of rotation matrices SO(3), as rotation parameterization are presented, which allow for an elegant formulation of higher order orientation interpolation with easy analytic derivatives, made possible through the Lie Algebra su(2) of pure quaternions and the cumulative form of cubic B-splines. The same construction scheme is then applied for joint interpolation in the full rigid body pose space, which had previously been done for the matrix representation SE(3) and its twists, but not for the more efficient unit dual quaternion DH1 and its screw motions. Both suffer from the effects of coupling translation and rotation that have mostly been ignored by previous work. We thus conclude that split interpolation in R3 × SU(2) is preferable for most applications. Our final runtime experiments show that joint interpolation in SE(3) is 2 times and in DH1 1.3 times slower - which furthermore justifies our suggestion from a practical point of view. |
| Tasks | |
| Published | 2018-09-05 |
| URL | http://www.adrian-haarbach.de/interpolation-methods/ |
| http://www.adrian-haarbach.de/interpolation-methods/doc/haarbach2018survey.pdf | |
| PWC | https://paperswithcode.com/paper/survey-of-higher-order-rigid-body-motion |
| Repo | |
| Framework | |
Symbolic Graph Reasoning Meets Convolutions
| Title | Symbolic Graph Reasoning Meets Convolutions |
| Authors | Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing |
| Abstract | Beyond local convolution networks, we explore how to harness various external human knowledge for endowing the networks with the capability of semantic global reasoning. Rather than using separate graphical models (e.g. CRF) or constraints for modeling broader dependencies, we propose a new Symbolic Graph Reasoning (SGR) layer, which performs reasoning over a group of symbolic nodes whose outputs explicitly represent different properties of each semantic in a prior knowledge graph. To cooperate with local convolutions, each SGR is constituted by three modules: a) a primal local-to-semantic voting module where the features of all symbolic nodes are generated by voting from local representations; b) a graph reasoning module propagates information over knowledge graph to achieve global semantic coherency; c) a dual semantic-to-local mapping module learns new associations of the evolved symbolic nodes with local representations, and accordingly enhances local features. The SGR layer can be injected between any convolution layers and instantiated with distinct prior graphs. Extensive experiments show incorporating SGR significantly improves plain ConvNets on three semantic segmentation tasks and one image classification task. More analyses show the SGR layer learns shared symbolic representations for domains/datasets with the different label set given a universal knowledge graph, demonstrating its superior generalization capability. |
| Tasks | Image Classification, Semantic Segmentation |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7456-symbolic-graph-reasoning-meets-convolutions |
| http://papers.nips.cc/paper/7456-symbolic-graph-reasoning-meets-convolutions.pdf | |
| PWC | https://paperswithcode.com/paper/symbolic-graph-reasoning-meets-convolutions |
| Repo | |
| Framework | |
Chats and Chunks: Annotation and Analysis of Multiparty Long Casual Conversations
| Title | Chats and Chunks: Annotation and Analysis of Multiparty Long Casual Conversations |
| Authors | Emer Gilmartin, Carl Vogel, Nick Campbell |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1309/ |
| https://www.aclweb.org/anthology/L18-1309 | |
| PWC | https://paperswithcode.com/paper/chats-and-chunks-annotation-and-analysis-of |
| Repo | |
| Framework | |
A Neural Network Based Model for Loanword Identification in Uyghur
| Title | A Neural Network Based Model for Loanword Identification in Uyghur |
| Authors | Chenggang Mi, Yating Yang, Lei Wang, Xi Zhou, Tonghai Jiang |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Part-Of-Speech Tagging |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1565/ |
| https://www.aclweb.org/anthology/L18-1565 | |
| PWC | https://paperswithcode.com/paper/a-neural-network-based-model-for-loanword |
| Repo | |
| Framework | |
Incorporating Contextual Information for Language-Independent, Dynamic Disambiguation Tasks
| Title | Incorporating Contextual Information for Language-Independent, Dynamic Disambiguation Tasks |
| Authors | Tobias Staron, {"O}zge Ala{\c{c}}am, Wolfgang Menzel |
| Abstract | |
| Tasks | Prepositional Phrase Attachment |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1567/ |
| https://www.aclweb.org/anthology/L18-1567 | |
| PWC | https://paperswithcode.com/paper/incorporating-contextual-information-for |
| Repo | |
| Framework | |
A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images
| Title | A Probabilistic Model for Joint Learning of Word Embeddings from Texts and Images |
| Authors | Melissa Ailem, Bowen Zhang, Aurelien Bellet, Pascal Denis, Fei Sha |
| Abstract | Several recent studies have shown the benefits of combining language and perception to infer word embeddings. These multimodal approaches either simply combine pre-trained textual and visual representations (e.g. features extracted from convolutional neural networks), or use the latter to bias the learning of textual word embeddings. In this work, we propose a novel probabilistic model to formalize how linguistic and perceptual inputs can work in concert to explain the observed word-context pairs in a text corpus. Our approach learns textual and visual representations jointly: latent visual factors couple together a skip-gram model for co-occurrence in linguistic data and a generative latent variable model for visual data. Extensive experimental studies validate the proposed model. Concretely, on the tasks of assessing pairwise word similarity and image/caption retrieval, our approach attains equally competitive or stronger results when compared to other state-of-the-art multimodal models. |
| Tasks | Coreference Resolution, Image Classification, Question Answering, Sentiment Analysis, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1177/ |
| https://www.aclweb.org/anthology/D18-1177 | |
| PWC | https://paperswithcode.com/paper/a-probabilistic-model-for-joint-learning-of |
| Repo | |
| Framework | |
Overcoming the Long Tail Problem: A Case Study on CO2-Footprint Estimation of Recipes using Information Retrieval
| Title | Overcoming the Long Tail Problem: A Case Study on CO2-Footprint Estimation of Recipes using Information Retrieval |
| Authors | Melanie Geiger, Martin Braschler |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1568/ |
| https://www.aclweb.org/anthology/L18-1568 | |
| PWC | https://paperswithcode.com/paper/overcoming-the-long-tail-problem-a-case-study |
| Repo | |
| Framework | |
Comparison of Pun Detection Methods Using Japanese Pun Corpus
| Title | Comparison of Pun Detection Methods Using Japanese Pun Corpus |
| Authors | Motoki Yatsu, Kenji Araki |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1569/ |
| https://www.aclweb.org/anthology/L18-1569 | |
| PWC | https://paperswithcode.com/paper/comparison-of-pun-detection-methods-using |
| Repo | |
| Framework | |
