Paper Group NANR 17
Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing. CLARIN: Towards FAIR and Responsible Data Science Using Language Resources. Modelling and unsupervised learning of symmetric deformable object categories. Comprehensive Annotation of Various Types of Temporal Information on the Time Axis. Annotating Temporally-Anc …
Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing
| Title | Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing |
| Authors | Zuchao Li, Shexia He, Zhuosheng Zhang, Hai Zhao |
| Abstract | This paper describes the system of team LeisureX in the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Our system predicts the part-of-speech tag and dependency tree jointly. For the basic tasks, including tokenization, lemmatization and morphology prediction, we employ the official baseline model (UDPipe). To train the low-resource languages, we adopt a sampling method based on other richresource languages. Our system achieves a macro-average of 68.31{%} LAS F1 score, with an improvement of 2.51{%} compared with the UDPipe. |
| Tasks | Dependency Parsing, Lemmatization, Part-Of-Speech Tagging, Tokenization, Transition-Based Dependency Parsing |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-2006/ |
| https://www.aclweb.org/anthology/K18-2006 | |
| PWC | https://paperswithcode.com/paper/joint-learning-of-pos-and-dependencies-for |
| Repo | |
| Framework | |
CLARIN: Towards FAIR and Responsible Data Science Using Language Resources
| Title | CLARIN: Towards FAIR and Responsible Data Science Using Language Resources |
| Authors | Franciska de Jong, Bente Maegaard, Koenraad De Smedt, Darja Fi{\v{s}}er, Dieter Van Uytvanck |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1515/ |
| https://www.aclweb.org/anthology/L18-1515 | |
| PWC | https://paperswithcode.com/paper/clarin-towards-fair-and-responsible-data |
| Repo | |
| Framework | |
Modelling and unsupervised learning of symmetric deformable object categories
| Title | Modelling and unsupervised learning of symmetric deformable object categories |
| Authors | James Thewlis, Hakan Bilen, Andrea Vedaldi |
| Abstract | We propose a new approach to model and learn, without manual supervision, the symmetries of natural objects, such as faces or flowers, given only images as input. It is well known that objects that have a symmetric structure do not usually result in symmetric images due to articulation and perspective effects. This is often tackled by seeking the intrinsic symmetries of the underlying 3D shape, which is very difficult to do when the latter cannot be recovered reliably from data. We show that, if only raw images are given, it is possible to look instead for symmetries in the space of object deformations. We can then learn symmetries from an unstructured collection of images of the object as an extension of the recently-introduced object frame representation, modified so that object symmetries reduce to the obvious symmetry groups in the normalized space. We also show that our formulation provides an explanation of the ambiguities that arise in recovering the pose of symmetric objects from their shape or images and we provide a way of discounting such ambiguities in learning. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8040-modelling-and-unsupervised-learning-of-symmetric-deformable-object-categories |
| http://papers.nips.cc/paper/8040-modelling-and-unsupervised-learning-of-symmetric-deformable-object-categories.pdf | |
| PWC | https://paperswithcode.com/paper/modelling-and-unsupervised-learning-of |
| Repo | |
| Framework | |
Comprehensive Annotation of Various Types of Temporal Information on the Time Axis
| Title | Comprehensive Annotation of Various Types of Temporal Information on the Time Axis |
| Authors | Tomohiro Sakaguchi, Daisuke Kawahara, Sadao Kurohashi |
| Abstract | |
| Tasks | Common Sense Reasoning |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1050/ |
| https://www.aclweb.org/anthology/L18-1050 | |
| PWC | https://paperswithcode.com/paper/comprehensive-annotation-of-various-types-of |
| Repo | |
| Framework | |
Annotating Temporally-Anchored Spatial Knowledge by Leveraging Syntactic Dependencies
| Title | Annotating Temporally-Anchored Spatial Knowledge by Leveraging Syntactic Dependencies |
| Authors | Alakan Vempala, a, Eduardo Blanco |
| Abstract | |
| Tasks | Semantic Role Labeling |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1052/ |
| https://www.aclweb.org/anthology/L18-1052 | |
| PWC | https://paperswithcode.com/paper/annotating-temporally-anchored-spatial |
| Repo | |
| Framework | |
Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient Updates
| Title | Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient Updates |
| Authors | Krishnakumar Balasubramanian, Saeed Ghadimi |
| Abstract | In this paper, we propose and analyze zeroth-order stochastic approximation algorithms for nonconvex and convex optimization. Specifically, we propose generalizations of the conditional gradient algorithm achieving rates similar to the standard stochastic gradient algorithm using only zeroth-order information. Furthermore, under a structural sparsity assumption, we first illustrate an implicit regularization phenomenon where the standard stochastic gradient algorithm with zeroth-order information adapts to the sparsity of the problem at hand by just varying the step-size. Next, we propose a truncated stochastic gradient algorithm with zeroth-order information, whose rate of convergence depends only poly-logarithmically on the dimensionality. |
| Tasks | Stochastic Optimization |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7605-zeroth-order-non-convex-stochastic-optimization-via-conditional-gradient-and-gradient-updates |
| http://papers.nips.cc/paper/7605-zeroth-order-non-convex-stochastic-optimization-via-conditional-gradient-and-gradient-updates.pdf | |
| PWC | https://paperswithcode.com/paper/zeroth-order-non-convex-stochastic |
| Repo | |
| Framework | |
Identifying Locus of Control in Social Media Language
| Title | Identifying Locus of Control in Social Media Language |
| Authors | Masoud Rouhizadeh, Kokil Jaidka, Laura Smith, H. Andrew Schwartz, Anneke Buffone, Lyle Ungar |
| Abstract | Individuals express their locus of control, or {}control{''}, in their language when they identify whether or not they are in control of their circumstances. Although control is a core concept underlying rhetorical style, it is not clear whether control is expressed by how or by what authors write. We explore the roles of syntax and semantics in expressing users{'} sense of control {--}i.e. being {}controlled by{''} or {``}in control of{''} their circumstances{–} in a corpus of annotated Facebook posts. We present rich insights into these linguistic aspects and find that while the language signaling control is easy to identify, it is more challenging to label it is internally or externally controlled, with lexical features outperforming syntactic features at the task. Our findings could have important implications for studying self-expression in social media. | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1145/ |
| https://www.aclweb.org/anthology/D18-1145 | |
| PWC | https://paperswithcode.com/paper/identifying-locus-of-control-in-social-media |
| Repo | |
| Framework | |
Construction of English-French Multimodal Affective Conversational Corpus from TV Dramas
| Title | Construction of English-French Multimodal Affective Conversational Corpus from TV Dramas |
| Authors | Sashi Novitasari, Quoc Truong Do, Sakriani Sakti, Dessi Lestari, Satoshi Nakamura |
| Abstract | |
| Tasks | Emotion Recognition, Speech Recognition, Speech Synthesis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1468/ |
| https://www.aclweb.org/anthology/L18-1468 | |
| PWC | https://paperswithcode.com/paper/construction-of-english-french-multimodal |
| Repo | |
| Framework | |
Online Dictionary Learning for Approximate Archetypal Analysis
| Title | Online Dictionary Learning for Approximate Archetypal Analysis |
| Authors | Jieru Mei, Chunyu Wang, Wenjun Zeng |
| Abstract | Archetypal analysis is an unsupervised learning approach which represents data by convex combinations of a set of archetypes. The archetypes generally correspond to the extremal points in the dataset and are learned by requiring them to be convex combinations of the training data. In spite of its nice property of interpretability, the method is slow. We propose a variant of archetypal analysis which scales gracefully to large datasets. The core idea is to decouple the binding between data and archetypes and require them to be unit normalized. Geometrically, the method learns a convex hull inside the unit sphere and represents the data by their projections on the closest surfaces of the convex hull. By minimizing the representation error, the method pushes the convex hull surfaces close to the regions of the sphere where the data reside. The vertices of the convex hull are the learned archetypes. We apply the method to human faces and poses to validate its effectiveness in the context of reconstructions and classifications. |
| Tasks | Dictionary Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jieru_Mei_Online_Dictionary_Learning_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Jieru_Mei_Online_Dictionary_Learning_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/online-dictionary-learning-for-approximate |
| Repo | |
| Framework | |
Language adaptation experiments via cross-lingual embeddings for related languages
| Title | Language adaptation experiments via cross-lingual embeddings for related languages |
| Authors | Serge Sharoff |
| Abstract | |
| Tasks | Domain Adaptation, Information Retrieval, Machine Translation, Named Entity Recognition, Text Classification, Word Embeddings |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1135/ |
| https://www.aclweb.org/anthology/L18-1135 | |
| PWC | https://paperswithcode.com/paper/language-adaptation-experiments-via-cross |
| Repo | |
| Framework | |
Part of Speech Tagging in Luyia: A Bantu Macrolanguage
| Title | Part of Speech Tagging in Luyia: A Bantu Macrolanguage |
| Authors | Kenneth Steimel |
| Abstract | Luyia is a macrolanguage in central Kenya. The Luyia languages, like other Bantu languages, have a complex morphological system. This system can be leveraged to aid in part of speech tagging. Bag-of-characters taggers trained on a source Luyia language can be applied directly to another Luyia language with some degree of success. In addition, mixing data from the target language with data from the source language does produce more accurate predictive models compared to models trained on just the target language data when the training set size is small. However, for both of these tagging tasks, models involving the more distantly related language, Tiriki, are better at predicting part of speech tags for Wanga data. The models incorporating Bukusu data are not as successful despite the closer relationship between Bukusu and Wanga. Overlapping vocabulary between the Wanga and Tiriki corpora as well as a bias towards open class words help Tiriki outperform Bukusu. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3905/ |
| https://www.aclweb.org/anthology/W18-3905 | |
| PWC | https://paperswithcode.com/paper/part-of-speech-tagging-in-luyia-a-bantu |
| Repo | |
| Framework | |
HBE: Hand Branch Ensemble Network for Real-time 3D Hand Pose Estimation
| Title | HBE: Hand Branch Ensemble Network for Real-time 3D Hand Pose Estimation |
| Authors | Yidan Zhou, Jian Lu, Kuo Du, Xiangbo Lin, Yi Sun, Xiaohong Ma |
| Abstract | The goal of this paper is to estimate the 3D coordinates of the hand joints from a single depth image. To give consideration to both the accuracy and the real time performance, we design a novel three-branch Convolutional Neural Networks named Hand Branch Ensemble network (HBE), where the three branches correspond to the three parts of a hand: the thumb, the index finger and the other fingers. The structural design inspiration of the HBE network comes from the understanding of the differences in the functional importance of different fingers. In addition, a feature ensemble layer along with a low-dimensional embedding layer ensures the overall hand shape constraints. The experimental results on three public datasets demonstrate that our approach achieves comparable or better performance to state-of-the-art methods with less training data, shorter training time and faster frame rate. |
| Tasks | Hand Pose Estimation, Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yidan_Zhou_HBE_Hand_Branch_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yidan_Zhou_HBE_Hand_Branch_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hbe-hand-branch-ensemble-network-for-real |
| Repo | |
| Framework | |
A Spatial Model for Extracting and Visualizing Latent Discourse Structure in Text
| Title | A Spatial Model for Extracting and Visualizing Latent Discourse Structure in Text |
| Authors | Shashank Srivastava, Nebojsa Jojic |
| Abstract | We present a generative probabilistic model of documents as sequences of sentences, and show that inference in it can lead to extraction of long-range latent discourse structure from a collection of documents. The approach is based on embedding sequences of sentences from longer texts into a 2- or 3-D spatial grids, in which one or two coordinates model smooth topic transitions, while the third captures the sequential nature of the modeled text. A significant advantage of our approach is that the learned models are naturally visualizable and interpretable, as semantic similarity and sequential structure are modeled along orthogonal directions in the grid. We show that the method is effective in capturing discourse structures in narrative text across multiple genres, including biographies, stories, and newswire reports. In particular, our method outperforms or is competitive with state-of-the-art generative approaches on tasks such as predicting the outcome of a story, and sentence ordering. |
| Tasks | Information Retrieval, Reading Comprehension, Semantic Similarity, Semantic Textual Similarity, Sentence Ordering, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1211/ |
| https://www.aclweb.org/anthology/P18-1211 | |
| PWC | https://paperswithcode.com/paper/a-spatial-model-for-extracting-and |
| Repo | |
| Framework | |
Cool English: a Grammatical Error Correction System Based on Large Learner Corpora
| Title | Cool English: a Grammatical Error Correction System Based on Large Learner Corpora |
| Authors | Yu-Chun Lo, Jhih-Jie Chen, Chingyu Yang, Jason Chang |
| Abstract | This paper presents a grammatical error correction (GEC) system that provides corrective feedback for essays. We apply the sequence-to-sequence model, which is frequently used in machine translation and text summarization, to this GEC task. The model is trained by EF-Cambridge Open Language Database (EFCAMDAT), a large learner corpus annotated with grammatical errors and corrections. Evaluation shows that our system achieves competitive performance on a number of publicly available testsets. |
| Tasks | Grammatical Error Correction, Machine Translation, Text Summarization |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2018/ |
| https://www.aclweb.org/anthology/C18-2018 | |
| PWC | https://paperswithcode.com/paper/cool-english-a-grammatical-error-correction |
| Repo | |
| Framework | |
Learning Translations via Images with a Massively Multilingual Image Dataset
| Title | Learning Translations via Images with a Massively Multilingual Image Dataset |
| Authors | John Hewitt, Daphne Ippolito, Brendan Callahan, Reno Kriz, Derry Tanti Wijaya, Chris Callison-Burch |
| Abstract | We conduct the most comprehensive study to date into translating words via images. To facilitate research on the task, we introduce a large-scale multilingual corpus of images, each labeled with the word it represents. Past datasets have been limited to only a few high-resource languages and unrealistically easy translation settings. In contrast, we have collected by far the largest available dataset for this task, with images for approximately 10,000 words in each of 100 languages. We run experiments on a dozen high resource languages and 20 low resources languages, demonstrating the effect of word concreteness and part-of-speech on translation quality. {%}We find that while image features work best for concrete nouns, they are sometimes effective on other parts of speech. To improve image-based translation, we introduce a novel method of predicting word concreteness from images, which improves on a previous state-of-the-art unsupervised technique. This allows us to predict when image-based translation may be effective, enabling consistent improvements to a state-of-the-art text-based word translation system. Our code and the Massively Multilingual Image Dataset (MMID) are available at \url{http://multilingual-images.org/}. |
| Tasks | Image Retrieval, Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1239/ |
| https://www.aclweb.org/anthology/P18-1239 | |
| PWC | https://paperswithcode.com/paper/learning-translations-via-images-with-a |
| Repo | |
| Framework | |
