Paper Group NANR 4
Representing Movie Characters in Dialogues. Better Transfer Learning with Inferred Successor Maps. Improving Pre-Trained Multilingual Model with Vocabulary Expansion. Know-Center at SemEval-2019 Task 5: Multilingual Hate Speech Detection on Twitter using CNNs. Acoustic Characterization of Singaporean Children’s English: Comparisons to American and …
Representing Movie Characters in Dialogues
| Title | Representing Movie Characters in Dialogues |
| Authors | Mahmoud Azab, Noriyuki Kojima, Jia Deng, Rada Mihalcea |
| Abstract | We introduce a new embedding model to represent movie characters and their interactions in a dialogue by encoding in the same representation the language used by these characters as well as information about the other participants in the dialogue. We evaluate the performance of these new character embeddings on two tasks: (1) character relatedness, using a dataset we introduce consisting of a dense character interaction matrix for 4,378 unique character pairs over 22 hours of dialogue from eighteen movies; and (2) character relation classification, for fine- and coarse-grained relations, as well as sentiment relations. Our experiments show that our model significantly outperforms the traditional Word2Vec continuous bag-of-words and skip-gram models, demonstrating the effectiveness of the character embeddings we introduce. We further show how these embeddings can be used in conjunction with a visual question answering system to improve over previous results. |
| Tasks | Question Answering, Relation Classification, Visual Question Answering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1010/ |
| https://www.aclweb.org/anthology/K19-1010 | |
| PWC | https://paperswithcode.com/paper/representing-movie-characters-in-dialogues |
| Repo | |
| Framework | |
Better Transfer Learning with Inferred Successor Maps
| Title | Better Transfer Learning with Inferred Successor Maps |
| Authors | Tamas Madarasz, Tim Behrens |
| Abstract | Humans and animals show remarkable flexibility in adjusting their behaviour when their goals, or rewards in the environment change. While such flexibility is a hallmark of intelligent behaviour, these multi-task scenarios remain an important challenge for machine learning algorithms and neurobiological models alike. We investigated two approaches that could enable this flexibility: factorized representations, which abstract away general aspects of a task from those prone to change, and nonparametric, memory-based approaches, which can provide a principled way of using similarity to past experiences to guide current behaviour. In particular, we combine the successor representation (SR), that factors the value of actions into expected outcomes and corresponding rewards, with evaluating task similarity through clustering the space of rewards. The proposed algorithm inverts a generative model over tasks, and dynamically samples from a flexible number of distinct SR maps while accumulating evidence about the current task context through amortized inference. It improves SR’s transfer capabilities and outperforms competing algorithms and baselines in settings with both known and unsignalled rewards changes. Further, as a neurobiological model of spatial coding in the hippocampus, it explains important signatures of this representation, such as the “flickering” behaviour of hippocampal maps, and trajectory-dependent place cells (so-called splitter cells) and their dynamics. We thus provide a novel algorithmic approach for multi-task learning, as well as a common normative framework that links together these different characteristics of the brain’s spatial representation. |
| Tasks | Multi-Task Learning, Transfer Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9104-better-transfer-learning-with-inferred-successor-maps |
| http://papers.nips.cc/paper/9104-better-transfer-learning-with-inferred-successor-maps.pdf | |
| PWC | https://paperswithcode.com/paper/better-transfer-learning-with-inferred |
| Repo | |
| Framework | |
Improving Pre-Trained Multilingual Model with Vocabulary Expansion
| Title | Improving Pre-Trained Multilingual Model with Vocabulary Expansion |
| Authors | Hai Wang, Dian Yu, Kai Sun, Jianshu Chen, Dong Yu |
| Abstract | Recently, pre-trained language models have achieved remarkable success in a broad range of natural language processing tasks. However, in multilingual setting, it is extremely resource-consuming to pre-train a deep language model over large-scale corpora for each language. Instead of exhaustively pre-training monolingual language models independently, an alternative solution is to pre-train a powerful multilingual deep language model over large-scale corpora in hundreds of languages. However, the vocabulary size for each language in such a model is relatively small, especially for low-resource languages. This limitation inevitably hinders the performance of these multilingual models on tasks such as sequence labeling, wherein in-depth token-level or sentence-level understanding is essential. In this paper, inspired by previous methods designed for monolingual settings, we investigate two approaches (i.e., joint mapping and mixture mapping) based on a pre-trained multilingual model BERT for addressing the out-of-vocabulary (OOV) problem on a variety of tasks, including part-of-speech tagging, named entity recognition, machine translation quality estimation, and machine reading comprehension. Experimental results show that using mixture mapping is more promising. To the best of our knowledge, this is the first work that attempts to address and discuss the OOV issue in multilingual settings. |
| Tasks | Language Modelling, Machine Reading Comprehension, Machine Translation, Named Entity Recognition, Part-Of-Speech Tagging, Reading Comprehension |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1030/ |
| https://www.aclweb.org/anthology/K19-1030 | |
| PWC | https://paperswithcode.com/paper/improving-pre-trained-multilingual-model-with |
| Repo | |
| Framework | |
Know-Center at SemEval-2019 Task 5: Multilingual Hate Speech Detection on Twitter using CNNs
| Title | Know-Center at SemEval-2019 Task 5: Multilingual Hate Speech Detection on Twitter using CNNs |
| Authors | Kevin Winter, Roman Kern |
| Abstract | This paper presents the Know-Center system submitted for task 5 of the SemEval-2019 workshop. Given a Twitter message in either English or Spanish, the task is to first detect whether it contains hateful speech and second, to determine the target and level of aggression used. For this purpose our system utilizes word embeddings and a neural network architecture, consisting of both dilated and traditional convolution layers. We achieved average F1-scores of 0.57 and 0.74 for English and Spanish respectively. |
| Tasks | Hate Speech Detection, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2076/ |
| https://www.aclweb.org/anthology/S19-2076 | |
| PWC | https://paperswithcode.com/paper/know-center-at-semeval-2019-task-5 |
| Repo | |
| Framework | |
Acoustic Characterization of Singaporean Children’s English: Comparisons to American and British Counterparts
| Title | Acoustic Characterization of Singaporean Children’s English: Comparisons to American and British Counterparts |
| Authors | Yuling Gu, Nancy Chen |
| Abstract | We investigate English pronunciation patterns in Singaporean children in relation to their American and British counterparts by conducting archetypal analysis on selected vowel pairs. Given that Singapore adopts British English as the institutional standard, one might expect Singaporean children to follow British pronunciation patterns, but we observe that Singaporean children also present similar patterns to Americans for TRAP-BATH spilt vowels: (1) British and Singaporean children both produce these vowels with a relatively lowered tongue height. (2) These vowels are more fronted for American and Singaporean children (p {\textless} 0.001). In addition, when comparing /{\ae}/ and /ε/ productions, British speakers show the clearest distinction between the two vowels; Singaporean and American speakers exhibit a higher and more fronted tongue position for /{\ae}/ (p {\textless} 0.001), causing /{\ae}/ to be acoustically more similar to /ε/. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3627/ |
| https://www.aclweb.org/anthology/W19-3627 | |
| PWC | https://paperswithcode.com/paper/acoustic-characterization-of-singaporean |
| Repo | |
| Framework | |
A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation
| Title | A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation |
| Authors | Jinxin Chang, Ruifang He, Longbiao Wang, Xiangyu Zhao, Ting Yang, Ruifang Wang |
| Abstract | Neural sequence-to-sequence models for dialog systems suffer from the problem of favoring uninformative and non replier-specific responses due to lack of the global and relevant information guidance. The existing methods model the generation process by leveraging the neural variational network with simple Gaussian. However, the sampled information from latent space usually becomes useless due to the KL divergence vanishing issue, and the highly abstractive global variables easily dilute the personal features of replier, leading to a non replier-specific response. Therefore, a novel Semi-Supervised Stable Variational Network (SSVN) is proposed to address these issues. We use a unit hypersperical distribution, namely the von Mises-Fisher (vMF), as the latent space of a semi-supervised model, which can obtain the stable KL performance by setting a fixed variance and hence enhance the global information representation. Meanwhile, an unsupervised extractor is introduced to automatically distill the replier-tailored feature which is then injected into a supervised generator to encourage the replier-consistency. Experimental results on two large conversation datasets show that our model outperforms the competitive baseline models significantly, and can generate diverse and replier-specific responses. |
| Tasks | Dialogue Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1200/ |
| https://www.aclweb.org/anthology/D19-1200 | |
| PWC | https://paperswithcode.com/paper/a-semi-supervised-stable-variational-network |
| Repo | |
| Framework | |
Analysing concatenation approaches to document-level NMT in two different domains
| Title | Analysing concatenation approaches to document-level NMT in two different domains |
| Authors | Yves Scherrer, J{"o}rg Tiedemann, Sharid Lo{'a}iciga |
| Abstract | In this paper, we investigate how different aspects of discourse context affect the performance of recent neural MT systems. We describe two popular datasets covering news and movie subtitles and we provide a thorough analysis of the distribution of various document-level features in their domains. Furthermore, we train a set of context-aware MT models on both datasets and propose a comparative evaluation scheme that contrasts coherent context with artificially scrambled documents and absent context, arguing that the impact of discourse-aware MT models will become visible in this way. Our results show that the models are indeed affected by the manipulation of the test data, providing a different view on document-level translation quality than absolute sentence-level scores. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6506/ |
| https://www.aclweb.org/anthology/D19-6506 | |
| PWC | https://paperswithcode.com/paper/analysing-concatenation-approaches-to |
| Repo | |
| Framework | |
Neural Unsupervised Parsing Beyond English
| Title | Neural Unsupervised Parsing Beyond English |
| Authors | Katharina Kann, Anhad Mohananey, Samuel R. Bowman, Kyunghyun Cho |
| Abstract | Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results. However, earlier work on unsupervised parsing shows large performance differences between non-neural models trained on corpora in different languages, even for comparable amounts of data. With that in mind, we train instances of the PRPN architecture (Shen et al., 2018){—}one of these unsupervised neural network parsers{—}for Arabic, Chinese, English, and German. We find that (i) the model strongly outperforms trivial baselines and, thus, acquires at least some parsing ability for all languages; (ii) good hyperparameter values seem to be universal; (iii) how the model benefits from larger training set sizes depends on the corpus, with the model achieving the largest performance gains when increasing the number of sentences from 2,500 to 12,500 for English. In addition, we show that, by sharing parameters between the related languages German and English, we can improve the model{'}s unsupervised parsing F1 score by up to 4{%} in the low-resource setting. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6123/ |
| https://www.aclweb.org/anthology/D19-6123 | |
| PWC | https://paperswithcode.com/paper/neural-unsupervised-parsing-beyond-english |
| Repo | |
| Framework | |
A Syntactically Expressive Morphological Analyzer for Turkish
| Title | A Syntactically Expressive Morphological Analyzer for Turkish |
| Authors | Adnan Ozturel, Tolga Kayadelen, Isin Demirsahin |
| Abstract | We present a broad coverage model of Turkish morphology and an open-source morphological analyzer that implements it. The model captures intricacies of Turkish morphology-syntax interface, thus could be used as a baseline that guides language model development. It introduces a novel fine part-of-speech tagset, a fine-grained affix inventory and represents morphotactics without zero-derivations. The morphological analyzer is freely available. It consists of modular reusable components of human-annotated gold standard lexicons, implements Turkish morphotactics as finite-state transducers using OpenFst and morphophonemic processes as Thrax grammars. |
| Tasks | Language Modelling |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-3110/ |
| https://www.aclweb.org/anthology/W19-3110 | |
| PWC | https://paperswithcode.com/paper/a-syntactically-expressive-morphological |
| Repo | |
| Framework | |
HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching
| Title | HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching |
| Authors | Florian Bernard, Johan Thunberg, Paul Swoboda, Christian Theobalt |
| Abstract | The matching of multiple objects (e.g. shapes or images) is a fundamental problem in vision and graphics. In order to robustly handle ambiguities, noise and repetitive patterns in challenging real-world settings, it is essential to take geometric consistency between points into account. Computationally, the multi-matching problem is difficult. It can be phrased as simultaneously solving multiple (NP-hard) quadratic assignment problems (QAPs) that are coupled via cycle-consistency constraints. The main limitations of existing multi-matching methods are that they either ignore geometric consistency and thus have limited robustness, or they are restricted to small-scale problems due to their (relatively) high computational cost. We address these shortcomings by introducing a Higher-order Projected Power Iteration method, which is (i) efficient and scales to tens of thousands of points, (ii) straightforward to implement, (iii) able to incorporate geometric consistency, (iv) guarantees cycle-consistent multi-matchings, and (iv) comes with theoretical convergence guarantees. Experimentally we show that our approach is superior to existing methods. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Bernard_HiPPI_Higher-Order_Projected_Power_Iterations_for_Scalable_Multi-Matching_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Bernard_HiPPI_Higher-Order_Projected_Power_Iterations_for_Scalable_Multi-Matching_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hippi-higher-order-projected-power-iterations |
| Repo | |
| Framework | |
ArbEngVec : Arabic-English Cross-Lingual Word Embedding Model
| Title | ArbEngVec : Arabic-English Cross-Lingual Word Embedding Model |
| Authors | Raki Lachraf, El Moatez Billah Nagoudi, Youcef Ayachi, Ahmed Abdelali, Didier Schwab |
| Abstract | Word Embeddings (WE) are getting increasingly popular and widely applied in many Natural Language Processing (NLP) applications due to their effectiveness in capturing semantic properties of words; Machine Translation (MT), Information Retrieval (IR) and Information Extraction (IE) are among such areas. In this paper, we propose an open source ArbEngVec which provides several Arabic-English cross-lingual word embedding models. To train our bilingual models, we use a large dataset with more than 93 million pairs of Arabic-English parallel sentences. In addition, we perform both extrinsic and intrinsic evaluations for the different word embedding model variants. The extrinsic evaluation assesses the performance of models on the cross-language Semantic Textual Similarity (STS), while the intrinsic evaluation is based on the Word Translation (WT) task. |
| Tasks | Information Retrieval, Machine Translation, Semantic Textual Similarity, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4605/ |
| https://www.aclweb.org/anthology/W19-4605 | |
| PWC | https://paperswithcode.com/paper/arbengvec-arabic-english-cross-lingual-word |
| Repo | |
| Framework | |
Fast Computation of Content-Sensitive Superpixels and Supervoxels Using Q-Distances
| Title | Fast Computation of Content-Sensitive Superpixels and Supervoxels Using Q-Distances |
| Authors | Zipeng Ye, Ran Yi, Minjing Yu, Yong-Jin Liu, Ying He |
| Abstract | State-of-the-art researches model the data of images and videos as low-dimensional manifolds and generate superpixels/supervoxels in a content-sensitive way, which is achieved by computing geodesic centroidal Voronoi tessellation (GCVT) on manifolds. However, computing exact GCVTs is slow due to computationally expensive geodesic distances. In this paper, we propose a much faster queue-based graph distance (called q-distance). Our key idea is that for manifold regions in which q-distances are different from geodesic distances, GCVT is prone to placing more generators in them, and therefore after few iterations, the q-distance-induced tessellation is an exact GCVT. This idea works well in practice and we also prove it theoretically under moderate assumption. Our method is simple and easy to implement. It runs 6-8 times faster than state-of-the-art GCVT computation, and has an optimal approximation ratio O(1) and a linear time complexity O(N) for N-pixel images or N-voxel videos. A thorough evaluation of 31 superpixel methods on five image datasets and 8 supervoxel methods on four video datasets shows that our method consistently achieves the best over-segmentation accuracy. We also demonstrate the advantage of our method on one image and two video applications. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Ye_Fast_Computation_of_Content-Sensitive_Superpixels_and_Supervoxels_Using_Q-Distances_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Ye_Fast_Computation_of_Content-Sensitive_Superpixels_and_Supervoxels_Using_Q-Distances_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fast-computation-of-content-sensitive |
| Repo | |
| Framework | |
Cross-Family Similarity Learning for Cognate Identification in Low-Resource Languages
| Title | Cross-Family Similarity Learning for Cognate Identification in Low-Resource Languages |
| Authors | Eliel Soisalon-Soininen, Mark Granroth-Wilding |
| Abstract | We address the problem of cognate identification across vocabulary pairs of any set of languages. In particular, we focus on the case where the examined pair of languages are low-resource to the extent that no training data whatsoever in these languages, or even closely related ones, are available for the task. We investigate the extent to which training data from another, unrelated language family can be used instead. Our approach consists of learning a similarity metric from example cognates in Indo-European languages and applying it to low-resource Sami languages of the Uralic family. We apply two models following previous work: a Siamese convolutional neural network (S-CNN) and a support vector machine (SVM), and compare them with a Levenshtein-distance baseline. We test performance on three Sami languages and find that the S-CNN outperforms the other approaches, suggesting that it is better able to learn such general characteristics of cognateness that carry over across language families. We also experiment with fine-tuning the S-CNN model with data from within the language family in order to quantify how well this model can make use of a small amount of target-domain data to adapt. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1129/ |
| https://www.aclweb.org/anthology/R19-1129 | |
| PWC | https://paperswithcode.com/paper/cross-family-similarity-learning-for-cognate |
| Repo | |
| Framework | |
Example-Guided Style-Consistent Image Synthesis From Semantic Labeling
| Title | Example-Guided Style-Consistent Image Synthesis From Semantic Labeling |
| Authors | Miao Wang, Guo-Ye Yang, Ruilong Li, Run-Ze Liang, Song-Hai Zhang, Peter M. Hall, Shi-Min Hu |
| Abstract | Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style. We use the term “style” in this problem to refer to implicit characteristics of images, for example: in portraits “style” includes gender, racial identity, age, hairstyle; in full body pictures it includes clothing; in street scenes it refers to weather and time of day and such like. A semantic label map in these cases indicates facial expression, full body pose, or scene segmentation. We propose a solution to the example-guided image synthesis problem using conditional generative adversarial networks with style consistency. Our key contributions are (i) a novel style consistency discriminator to determine whether a pair of images are consistent in style; (ii) an adaptive semantic consistency loss; and (iii) a training data sampling strategy, for synthesizing style-consistent results to the exemplar. We demonstrate the efficiency of our method on face, dance and street view synthesis tasks. |
| Tasks | Image Generation, Scene Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Example-Guided_Style-Consistent_Image_Synthesis_From_Semantic_Labeling_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Example-Guided_Style-Consistent_Image_Synthesis_From_Semantic_Labeling_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/example-guided-style-consistent-image |
| Repo | |
| Framework | |
Priming vs. Inhibition of Optional Infinitival ``to’’
| Title | Priming vs. Inhibition of Optional Infinitival ``to’’ | |
| Authors | Robin Melnick, Thomas Wasow |
| Abstract | The word {}to{''} that precedes verbs in English infinitives is optional in at least two environments: in what Wasow et al. (2015) previously called the {}do-be{''} construction, and in the complement of {}help{''}, which we explore in the present work. In the {}do-be{''} construction, Wasow et al. found that a preceding infinitival {}to{''} increases the use of following optional {}to{''}, but the use of {}to{''} in the complement of help is reduced following {}to help{''}. We examine two hypotheses regarding why the same function word is primed by prior use in one construction and inhibited in another. We then test predictions made by the two hypotheses, finding support for one of them. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2902/ |
| https://www.aclweb.org/anthology/W19-2902 | |
| PWC | https://paperswithcode.com/paper/priming-vs-inhibition-of-optional-infinitival |
| Repo | |
| Framework | |
