Paper Group NANR 223
On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study. MITRE at SemEval-2019 Task 5: Transfer Learning for Multilingual Hate Speech Detection. Cross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging. Question Answering Using Hierarchical Attention on Top of BERT Features. Proceedings of the 13th L …
On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study
| Title | On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study |
| Authors | Damian Blasi, Ryan Cotterell, Lawrence Wolf-Sonkin, Sabine Stoll, Balthasar Bickel, Marco Baroni |
| Abstract | Embedding a clause inside another ({``}the girl [who likes cars [that run fast]] has arrived{''}) is a fundamental resource that has been argued to be a key driver of linguistic expressiveness. As such, it plays a central role in fundamental debates on what makes human language unique, and how they might have evolved. Empirical evidence on the prevalence and the limits of embeddings has however been based on either laboratory setups or corpus data of relatively limited size. We introduce here a collection of large, dependency-parsed written corpora in 17 languages, that allow us, for the first time, to capture clausal embedding through dependency graphs and assess their distribution. Our results indicate that there is no evidence for hard constraints on embedding depth: the tail of depth distributions is heavy. Moreover, although deeply embedded clauses tend to be shorter, suggesting processing load issues, complex sentences with many embeddings do not display a bias towards less deep embeddings. Taken together, the results suggest that deep embeddings are not disfavoured in written language. More generally, our study illustrates how resources and methods from latest-generation big-data NLP can provide new perspectives on fundamental questions in theoretical linguistics. | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1384/ |
| https://www.aclweb.org/anthology/P19-1384 | |
| PWC | https://paperswithcode.com/paper/on-the-distribution-of-deep-clausal |
| Repo | |
| Framework | |
MITRE at SemEval-2019 Task 5: Transfer Learning for Multilingual Hate Speech Detection
| Title | MITRE at SemEval-2019 Task 5: Transfer Learning for Multilingual Hate Speech Detection |
| Authors | Abigail Gertner, John Henderson, Elizabeth Merkhofer, Amy Marsh, Ben Wellner, Guido Zarrella |
| Abstract | This paper describes MITRE{'}s participation in SemEval-2019 Task 5, HatEval: Multilingual detection of hate speech against immigrants and women in Twitter. The techniques explored range from simple bag-of-ngrams classifiers to neural architectures with varied attention mechanisms. We describe several styles of transfer learning from auxiliary tasks, including a novel method for adapting pre-trained BERT models to Twitter data. Logistic regression ties the systems together into an ensemble submitted for evaluation. The resulting system was used to produce predictions for all four HatEval subtasks, achieving the best mean rank of all teams that participated in all four conditions. |
| Tasks | Hate Speech Detection, Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2080/ |
| https://www.aclweb.org/anthology/S19-2080 | |
| PWC | https://paperswithcode.com/paper/mitre-at-semeval-2019-task-5-transfer |
| Repo | |
| Framework | |
Cross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging
| Title | Cross-lingual Annotation Projection Is Effective for Neural Part-of-Speech Tagging |
| Authors | Matthias Huck, Diana Dutka, Alex Fraser, er |
| Abstract | We tackle the important task of part-of-speech tagging using a neural model in the zero-resource scenario, where we have no access to gold-standard POS training data. We compare this scenario with the low-resource scenario, where we have access to a small amount of gold-standard POS training data. Our experiments focus on Ukrainian as a representative of under-resourced languages. Russian is highly related to Ukrainian, so we exploit gold-standard Russian POS tags. We consider four techniques to perform Ukrainian POS tagging: zero-shot tagging and cross-lingual annotation projection (for the zero-resource scenario), and compare these with self-training and multilingual learning (for the low-resource scenario). We find that cross-lingual annotation projection works particularly well in the zero-resource scenario. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1425/ |
| https://www.aclweb.org/anthology/W19-1425 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-annotation-projection-is |
| Repo | |
| Framework | |
Question Answering Using Hierarchical Attention on Top of BERT Features
| Title | Question Answering Using Hierarchical Attention on Top of BERT Features |
| Authors | Reham Osama, Nagwa El-Makky, Marwan Torki |
| Abstract | The model submitted works as follows. When supplied a question and a passage it makes use of the BERT embedding along with the hierarchical attention model which consists of 2 parts, the co-attention and the self-attention, to locate a continuous span of the passage that is the answer to the question. |
| Tasks | Question Answering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5825/ |
| https://www.aclweb.org/anthology/D19-5825 | |
| PWC | https://paperswithcode.com/paper/question-answering-using-hierarchical |
| Repo | |
| Framework | |
Proceedings of the 13th Linguistic Annotation Workshop
| Title | Proceedings of the 13th Linguistic Annotation Workshop |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4000/ |
| https://www.aclweb.org/anthology/W19-4000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-linguistic-annotation |
| Repo | |
| Framework | |
Bridging the Defined and the Defining: Exploiting Implicit Lexical Semantic Relations in Definition Modeling
| Title | Bridging the Defined and the Defining: Exploiting Implicit Lexical Semantic Relations in Definition Modeling |
| Authors | Koki Washio, Satoshi Sekine, Tsuneaki Kato |
| Abstract | Definition modeling includes acquiring word embeddings from dictionary definitions and generating definitions of words. While the meanings of defining words are important in dictionary definitions, it is crucial to capture the lexical semantic relations between defined words and defining words. However, thus far, the utilization of such relations has not been explored for definition modeling. In this paper, we propose definition modeling methods that use lexical semantic relations. To utilize implicit semantic relations in definitions, we use unsupervisedly obtained pattern-based word-pair embeddings that represent semantic relations of word pairs. Experimental results indicate that our methods improve the performance in learning embeddings from definitions, as well as definition generation. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1357/ |
| https://www.aclweb.org/anthology/D19-1357 | |
| PWC | https://paperswithcode.com/paper/bridging-the-defined-and-the-defining |
| Repo | |
| Framework | |
Lexical Quantile-Based Text Complexity Measure
| Title | Lexical Quantile-Based Text Complexity Measure |
| Authors | Maksim Eremeev, Konstantin Vorontsov |
| Abstract | This paper introduces a new approach to estimating the text document complexity. Common readability indices are based on average length of sentences and words. In contrast to these methods, we propose to count the number of rare words occurring abnormally often in the document. We use the reference corpus of texts and the quantile approach in order to determine what words are rare, and what frequencies are abnormal. We construct a general text complexity model, which can be adjusted for the specific task, and introduce two special models. The experimental design is based on a set of thematically similar pairs of Wikipedia articles, labeled using crowdsourcing. The experiments demonstrate the competitiveness of the proposed approach. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1031/ |
| https://www.aclweb.org/anthology/R19-1031 | |
| PWC | https://paperswithcode.com/paper/lexical-quantile-based-text-complexity |
| Repo | |
| Framework | |
Projective Subspace Networks For Few-Shot Learning
| Title | Projective Subspace Networks For Few-Shot Learning |
| Authors | Christian Simon, Piotr Koniusz, Mehrtash Harandi |
| Abstract | Generalization from limited examples, usually studied under the umbrella of meta-learning, equips learning techniques with the ability to adapt quickly in dynamical environments and proves to be an essential aspect of lifelong learning. In this paper, we introduce the Projective Subspace Networks (PSN), a deep learning paradigm that learns non-linear embeddings from limited supervision. In contrast to previous studies, the embedding in PSN deems samples of a given class to form an affine subspace. We will show that such modeling leads to robust solutions, yielding competitive results on supervised and semi-supervised few-shot classification. Moreover, our PSN approach has the ability of end-to-end learning. In contrast to previous works, our projective subspace can be thought of as a richer representation capturing higher-order information datapoints for modeling new concepts. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkzfuiA9F7 |
| https://openreview.net/pdf?id=rkzfuiA9F7 | |
| PWC | https://paperswithcode.com/paper/projective-subspace-networks-for-few-shot |
| Repo | |
| Framework | |
Attribute-aware Sequence Network for Review Summarization
| Title | Attribute-aware Sequence Network for Review Summarization |
| Authors | Junjie Li, Xuepeng Wang, Dawei Yin, Chengqing Zong |
| Abstract | Review summarization aims to generate a condensed summary for a review or multiple reviews. Existing review summarization systems mainly generate summary only based on review content and neglect the authors{'} attributes (e.g., gender, age, and occupation). In fact, when summarizing a review, users with different attributes usually pay attention to specific aspects and have their own word-using habits or writing styles. Therefore, we propose an Attribute-aware Sequence Network (ASN) to take the aforementioned users{'} characteristics into account, which includes three modules: an attribute encoder encodes the attribute preferences over the words; an attribute-aware review encoder adopts an attribute-based selective mechanism to select the important information of a review; and an attribute-aware summary decoder incorporates attribute embedding and attribute-specific word-using habits into word prediction. To validate our model, we collect a new dataset TripAtt, comprising 495,440 attribute-review-summary triplets with three kinds of attribute information: gender, age, and travel status. Extensive experiments show that ASN achieves state-of-the-art performance on review summarization in both auto-metric ROUGE and human evaluation. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1297/ |
| https://www.aclweb.org/anthology/D19-1297 | |
| PWC | https://paperswithcode.com/paper/attribute-aware-sequence-network-for-review |
| Repo | |
| Framework | |
Laplacian Networks: Bounding Indicator Function Smoothness for Neural Networks Robustness
| Title | Laplacian Networks: Bounding Indicator Function Smoothness for Neural Networks Robustness |
| Authors | Carlos Eduardo Rosar Kos Lassance, Vincent Gripon, Antonio Ortega |
| Abstract | For the past few years, Deep Neural Network (DNN) robustness has become a question of paramount importance. As a matter of fact, in sensitive settings misclassification can lead to dramatic consequences. Such misclassifications are likely to occur when facing adversarial attacks, hardware failures or limitations, and imperfect signal acquisition. To address this question, authors have proposed different approaches aiming at increasing the robustness of DNNs, such as adding regularizers or training using noisy examples. In this paper we propose a new regularizer built upon the Laplacian of similarity graphs obtained from the representation of training data at each layer of the DNN architecture. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes, and as such enforces smooth variations of the class boundaries. Since it is agnostic to the type of deformations that are expected when predicting with the DNN, the proposed regularizer can be combined with existing ad-hoc methods. We provide theoretical justification for this regularizer and demonstrate its effectiveness to improve robustness of DNNs on classical supervised learning vision datasets. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1e8wsCqYX |
| https://openreview.net/pdf?id=H1e8wsCqYX | |
| PWC | https://paperswithcode.com/paper/laplacian-networks-bounding-indicator-1 |
| Repo | |
| Framework | |
K-Nearest Neighbors Hashing
| Title | K-Nearest Neighbors Hashing |
| Authors | Xiangyu He, Peisong Wang, Jian Cheng |
| Abstract | Hashing based approximate nearest neighbor search embeds high dimensional data to compact binary codes, which enables efficient similarity search and storage. However, the non-isometry sign() function makes it hard to project the nearest neighbors in continuous data space into the closest codewords in discrete Hamming space. In this work, we revisit the sign() function from the perspective of space partitioning. In specific, we bridge the gap between k-nearest neighbors and binary hashing codes with Shannon entropy. We further propose a novel K-Nearest Neighbors Hashing (KNNH) method to learn binary representations from KNN within the subspaces generated by sign(). Theoretical and experimental results show that the KNN relation is of central importance to neighbor preserving embeddings, and the proposed method outperforms the state-of-the-arts on benchmark datasets. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/He_K-Nearest_Neighbors_Hashing_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/He_K-Nearest_Neighbors_Hashing_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/k-nearest-neighbors-hashing |
| Repo | |
| Framework | |
Proceedings of the Society for Computation in Linguistics (SCiL) 2019
| Title | Proceedings of the Society for Computation in Linguistics (SCiL) 2019 |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0100/ |
| https://www.aclweb.org/anthology/W19-0100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-society-for-computation-in-1 |
| Repo | |
| Framework | |
Interpreting and defining connections in a dependency structure
| Title | Interpreting and defining connections in a dependency structure |
| Authors | Sylvain Kahane |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7711/ |
| https://www.aclweb.org/anthology/W19-7711 | |
| PWC | https://paperswithcode.com/paper/interpreting-and-defining-connections-in-a |
| Repo | |
| Framework | |
Constraint breeding during on-line incremental learning
| Title | Constraint breeding during on-line incremental learning |
| Authors | Elliot Moreton |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0108/ |
| https://www.aclweb.org/anthology/W19-0108 | |
| PWC | https://paperswithcode.com/paper/constraint-breeding-during-on-line |
| Repo | |
| Framework | |
On Differentially Private Graph Sparsification and Applications
| Title | On Differentially Private Graph Sparsification and Applications |
| Authors | Raman Arora, Jalaj Upadhyay |
| Abstract | In this paper, we study private sparsification of graphs. In particular, we give an algorithm that given an input graph, returns a sparse graph which approximates the spectrum of the input graph while ensuring differential privacy. This allows one to solve many graph problems privately yet efficiently and accurately. This is exemplified with application of the proposed meta-algorithm to graph algorithms for privately answering cut-queries, as well as practical algorithms for computing {\scshape MAX-CUT} and {\scshape SPARSEST-CUT} with better accuracy than previously known. We also give the first efficient private algorithm to learn Laplacian eigenmap on a graph. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9494-on-differentially-private-graph-sparsification-and-applications |
| http://papers.nips.cc/paper/9494-on-differentially-private-graph-sparsification-and-applications.pdf | |
| PWC | https://paperswithcode.com/paper/on-differentially-private-graph |
| Repo | |
| Framework | |
