Paper Group NANR 127
Forecasting Firm Material Events from 8-K Reports. A Plea for Information Structure as a Part of Meaning Representation. Generative Adversarial Training for Weakly Supervised Cloud Matting. Compact and Robust Models for Japanese-English Character-level Machine Translation. Expectation and Locality Effects in the Prediction of Disfluent Fillers and …
Forecasting Firm Material Events from 8-K Reports
| Title | Forecasting Firm Material Events from 8-K Reports |
| Authors | Shuang (Sophie) Zhai, Zhu (Drew) Zhang |
| Abstract | In this paper, we show deep learning models can be used to forecast firm material event sequences based on the contents in the company{'}s 8-K Current Reports. Specifically, we exploit state-of-the-art neural architectures, including sequence-to-sequence (Seq2Seq) architecture and attention mechanisms, in the model. Our 8K-powered deep learning model demonstrates promising performance in forecasting firm future event sequences. The model is poised to benefit various stakeholders, including management and investors, by facilitating risk management and decision making. |
| Tasks | Decision Making |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5104/ |
| https://www.aclweb.org/anthology/D19-5104 | |
| PWC | https://paperswithcode.com/paper/forecasting-firm-material-events-from-8-k |
| Repo | |
| Framework | |
A Plea for Information Structure as a Part of Meaning Representation
| Title | A Plea for Information Structure as a Part of Meaning Representation |
| Authors | Eva Hajicova |
| Abstract | The view that the representation of information structure (IS) should be a part of (any type of) representation of meaning is based on the fact that IS is a semantically relevant phenomenon. In the contribution, three arguments supporting this view are briefly summarized, namely, the relation of IS to the interpretation of negation and presupposition, the relevance of IS to the understanding of discourse connectivity and for the establishment and interpretation of coreference relations. Afterwards, possible integration of the description of the main ingredient of IS into a meaning representation is illustrated. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3307/ |
| https://www.aclweb.org/anthology/W19-3307 | |
| PWC | https://paperswithcode.com/paper/a-plea-for-information-structure-as-a-part-of |
| Repo | |
| Framework | |
Generative Adversarial Training for Weakly Supervised Cloud Matting
| Title | Generative Adversarial Training for Weakly Supervised Cloud Matting |
| Authors | Zhengxia Zou, Wenyuan Li, Tianyang Shi, Zhenwei Shi, Jieping Ye |
| Abstract | The detection and removal of cloud in remote sensing images are essential for earth observation applications. Most previous methods consider cloud detection as a pixel-wise semantic segmentation process (cloud v.s. background), which inevitably leads to a category-ambiguity problem when dealing with semi-transparent clouds. We re-examine the cloud detection under a totally different point of view, i.e. to formulate it as a mixed energy separation process between foreground and background images, which can be equivalently implemented under an image matting paradigm with a clear physical significance. We further propose a generative adversarial framework where the training of our model neither requires any pixel-wise ground truth reference nor any additional user interactions. Our model consists of three networks, a cloud generator G, a cloud discriminator D, and a cloud matting network F, where G and D aim to generate realistic and physically meaningful cloud images by adversarial training, and F learns to predict the cloud reflectance and attenuation. Experimental results on a global set of satellite images demonstrate that our method, without ever using any pixel-wise ground truth during training, achieves comparable and even higher accuracy over other fully supervised methods, including some recent popular cloud detectors and some well-known semantic segmentation frameworks. |
| Tasks | Cloud Detection, Image Matting, Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zou_Generative_Adversarial_Training_for_Weakly_Supervised_Cloud_Matting_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zou_Generative_Adversarial_Training_for_Weakly_Supervised_Cloud_Matting_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-training-for-weakly |
| Repo | |
| Framework | |
Compact and Robust Models for Japanese-English Character-level Machine Translation
| Title | Compact and Robust Models for Japanese-English Character-level Machine Translation |
| Authors | Jinan Dai, Kazunori Yamaguchi |
| Abstract | Character-level translation has been proved to be able to achieve preferable translation quality without explicit segmentation, but training a character-level model needs a lot of hardware resources. In this paper, we introduced two character-level translation models which are mid-gated model and multi-attention model for Japanese-English translation. We showed that the mid-gated model achieved the better performance with respect to BLEU scores. We also showed that a relatively narrow beam of width 4 or 5 was sufficient for the mid-gated model. As for unknown words, we showed that the mid-gated model could somehow translate the one containing Katakana by coining out a close word. We also showed that the model managed to produce tolerable results for heavily noised sentences, even though the model was trained with the dataset without noise. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5202/ |
| https://www.aclweb.org/anthology/D19-5202 | |
| PWC | https://paperswithcode.com/paper/compact-and-robust-models-for-japanese |
| Repo | |
| Framework | |
Expectation and Locality Effects in the Prediction of Disfluent Fillers and Repairs in English Speech
| Title | Expectation and Locality Effects in the Prediction of Disfluent Fillers and Repairs in English Speech |
| Authors | Samvit Dammalapati, Rajakrishnan Rajkumar, Sumeet Agarwal |
| Abstract | This study examines the role of three influential theories of language processing, \textit{viz.}, Surprisal Theory, Uniform Information Density (UID) hypothesis and Dependency Locality Theory (DLT), in predicting disfluencies in speech production. To this end, we incorporate features based on lexical surprisal, word duration and DLT integration and storage costs into logistic regression classifiers aimed to predict disfluencies in the Switchboard corpus of English conversational speech. We find that disfluencies occur in the face of upcoming difficulties and speakers tend to handle this by lessening cognitive load before disfluencies occur. Further, we see that reparandums behave differently from disfluent fillers possibly due to the lessening of the cognitive load also happening in the word choice of the reparandum, i.e., in the disfluency itself. While the UID hypothesis does not seem to play a significant role in disfluency prediction, lexical surprisal and DLT costs do give promising results in explaining language production. Further, we also find that as a means to lessen cognitive load for upcoming difficulties speakers take more time on words preceding disfluencies, making duration a key element in understanding disfluencies. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-3015/ |
| https://www.aclweb.org/anthology/N19-3015 | |
| PWC | https://paperswithcode.com/paper/expectation-and-locality-effects-in-the |
| Repo | |
| Framework | |
Designing the Business Conversation Corpus
| Title | Designing the Business Conversation Corpus |
| Authors | Mat{=\i}ss Rikters, Ryokan Ri, Tong Li, Toshiaki Nakazawa |
| Abstract | While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and dialogues remains challenging even for modern systems. In this paper, we aim to boost the machine translation quality of conversational texts by introducing a newly constructed Japanese-English business conversation parallel corpus. A detailed analysis of the corpus is provided along with challenging examples for automatic translation. We also experiment with adding the corpus in a machine translation training scenario and show how the resulting system benefits from its use. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5204/ |
| https://www.aclweb.org/anthology/D19-5204 | |
| PWC | https://paperswithcode.com/paper/designing-the-business-conversation-corpus |
| Repo | |
| Framework | |
Wasserstein GAN With Quadratic Transport Cost
| Title | Wasserstein GAN With Quadratic Transport Cost |
| Authors | Huidong Liu, Xianfeng Gu, Dimitris Samaras |
| Abstract | Wasserstein GANs are increasingly used in Computer Vision applications as they are easier to train. Previous WGAN variants mainly use the l_1 transport cost to compute the Wasserstein distance between the real and synthetic data distributions. The l_1 transport cost restricts the discriminator to be 1-Lipschitz. However, WGANs with l_1 transport cost were recently shown to not always converge. In this paper, we propose WGAN-QC, a WGAN with quadratic transport cost. Based on the quadratic transport cost, we propose an Optimal Transport Regularizer (OTR) to stabilize the training process of WGAN-QC. We prove that the objective of the discriminator during each generator update computes the exact quadratic Wasserstein distance between real and synthetic data distributions. We also prove that WGAN-QC converges to a local equilibrium point with finite discriminator updates per generator update. We show experimentally on a Dirac distribution that WGAN-QC converges, when many of the l_1 cost WGANs fail to [22]. Qualitative and quantitative results on the CelebA, CelebA-HQ, LSUN and the ImageNet dog datasets show that WGAN-QC is better than state-of-art GAN methods. WGAN-QC has much faster runtime than other WGAN variants. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Wasserstein_GAN_With_Quadratic_Transport_Cost_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Wasserstein_GAN_With_Quadratic_Transport_Cost_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/wasserstein-gan-with-quadratic-transport-cost |
| Repo | |
| Framework | |
Event Structure Representation: Between Verbs and Argument Structure Constructions
| Title | Event Structure Representation: Between Verbs and Argument Structure Constructions |
| Authors | Pavlina Kalm, Michael Regan, William Croft |
| Abstract | This paper proposes a novel representation of event structure by separating verbal semantics and the meaning of argument structure constructions that verbs occur in. Our model demonstrates how the two meaning representations interact. Our model thus effectively deals with various verb construals in different argument structure constructions, unlike purely verb-based approaches. However, unlike many constructionally-based approaches, we also provide a richer representation of the event structure evoked by the verb meaning. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3311/ |
| https://www.aclweb.org/anthology/W19-3311 | |
| PWC | https://paperswithcode.com/paper/event-structure-representation-between-verbs |
| Repo | |
| Framework | |
A string-to-graph constructive alignment algorithm for discrete and probabilistic language modeling
| Title | A string-to-graph constructive alignment algorithm for discrete and probabilistic language modeling |
| Authors | Andrey Shcherbakov, Ekaterina Vylomova |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1025/ |
| https://www.aclweb.org/anthology/U19-1025 | |
| PWC | https://paperswithcode.com/paper/a-string-to-graph-constructive-alignment |
| Repo | |
| Framework | |
A Multi-Hop Attention for RNN based Neural Machine Translation
| Title | A Multi-Hop Attention for RNN based Neural Machine Translation |
| Authors | Shohei Iida, Ryuichiro Kimura, Hongyi Cui, Po-Hsuan Hung, Takehito Utsuro, Masaaki Nagata |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7203/ |
| https://www.aclweb.org/anthology/W19-7203 | |
| PWC | https://paperswithcode.com/paper/a-multi-hop-attention-for-rnn-based-neural |
| Repo | |
| Framework | |
Language Discrimination and Transfer Learning for Similar Languages: Experiments with Feature Combinations and Adaptation
| Title | Language Discrimination and Transfer Learning for Similar Languages: Experiments with Feature Combinations and Adaptation |
| Authors | Nianheng Wu, Eric DeMattos, Kwok Him So, Pin-zhen Chen, {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin |
| Abstract | This paper describes the work done by team tearsofjoy participating in the VarDial 2019 Evaluation Campaign. We developed two systems based on Support Vector Machines: SVM with a flat combination of features and SVM ensembles. We participated in all language/dialect identification tasks, as well as the Moldavian vs. Romanian cross-dialect topic identification (MRC) task. Our team achieved first place in German Dialect identification (GDI) and MRC subtasks 2 and 3, second place in the simplified variant of Discriminating between Mainland and Taiwan variation of Mandarin Chinese (DMT) as well as Cuneiform Language Identification (CLI), and third and fifth place in DMT traditional and MRC subtask 1 respectively. In most cases, the SVM with a flat combination of features performed better than SVM ensembles. Besides describing the systems and the results obtained by them, we provide a tentative comparison between the feature combination methods, and present additional experiments with a method of adaptation to the test set, which may indicate potential pitfalls with some of the data sets. |
| Tasks | Language Identification, Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1406/ |
| https://www.aclweb.org/anthology/W19-1406 | |
| PWC | https://paperswithcode.com/paper/language-discrimination-and-transfer-learning |
| Repo | |
| Framework | |
Naive Bayes and BiLSTM Ensemble for Discriminating between Mainland and Taiwan Variation of Mandarin Chinese
| Title | Naive Bayes and BiLSTM Ensemble for Discriminating between Mainland and Taiwan Variation of Mandarin Chinese |
| Authors | Li Yang, Yang Xiang |
| Abstract | Automatic dialect identification is a more challengingctask than language identification, as it requires the ability to discriminate between varieties of one language. In this paper, we propose an ensemble based system, which combines traditional machine learning models trained on bag of n-gram fetures, with deep learning models trained on word embeddings, to solve the Discriminating between Mainland and Taiwan Variation of Mandarin Chinese (DMT) shared task at VarDial 2019. Our experiments show that a character bigram-trigram combination based Naive Bayes is a very strong model for identifying varieties of Mandarin Chinense. Through further ensemble of Navie Bayes and BiLSTM, our system (team: itsalexyang) achived an macro-averaged F1 score of 0.8530 and 0.8687 in two tracks. |
| Tasks | Language Identification, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1412/ |
| https://www.aclweb.org/anthology/W19-1412 | |
| PWC | https://paperswithcode.com/paper/naive-bayes-and-bilstm-ensemble-for |
| Repo | |
| Framework | |
Distributional Interaction of Concreteness and Abstractness in Verb–Noun Subcategorisation
| Title | Distributional Interaction of Concreteness and Abstractness in Verb–Noun Subcategorisation |
| Authors | Diego Frassinelli, Sabine Schulte im Walde |
| Abstract | In recent years, both cognitive and computational research has provided empirical analyses of contextual co-occurrence of concrete and abstract words, partially resulting in inconsistent pictures. In this work we provide a more fine-grained description of the distributional nature in the corpus-based interaction of verbs and nouns within subcategorisation, by investigating the concreteness of verbs and nouns that are in a specific syntactic relationship with each other, i.e., subject, direct object, and prepositional object. Overall, our experiments show consistent patterns in the distributional representation of subcategorising and subcategorised concrete and abstract words. At the same time, the studies reveal empirical evidence why contextual abstractness represents a valuable indicator for automatic non-literal language identification. |
| Tasks | Language Identification |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0506/ |
| https://www.aclweb.org/anthology/W19-0506 | |
| PWC | https://paperswithcode.com/paper/distributional-interaction-of-concreteness |
| Repo | |
| Framework | |
KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks onWAT 2019
| Title | KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks onWAT 2019 |
| Authors | Cheoneum Park, Young-Jun Jung, Kihoon Kim, Geonyeong Kim, Jae-Won Jeon, Seongmin Lee, Junseok Kim, Changki Lee |
| Abstract | In this paper, we describe the neural machine translation (NMT) system submitted by the Kangwon National University and HYUNDAI (KNU-HYUNDAI) team to the translation tasks of the 6th workshop on Asian Translation (WAT 2019). We participated in all tasks of ASPEC and JPC2, which included those of Chinese-Japanese, English-Japanese, and Korean-{\textgreater}Japanese. We submitted our transformer-based NMT system with built using the following methods: a) relative positioning method for pairwise relationships between the input elements, b) back-translation and multi-source translation for data augmentation, c) right-to-left (r2l)-reranking model robust against error propagation in autoregressive architectures such as decoders, and d) checkpoint ensemble models, which selected the top three models with the best validation bilingual evaluation understudy (BLEU) . We have reported the translation results on the two aforementioned tasks. We performed well in both the tasks and were ranked first in terms of the BLEU scores in all the JPC2 subtasks we participated in. |
| Tasks | Data Augmentation, Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5208/ |
| https://www.aclweb.org/anthology/D19-5208 | |
| PWC | https://paperswithcode.com/paper/knu-hyundais-nmt-system-for-scientific-paper |
| Repo | |
| Framework | |
Riemannian Stochastic Gradient Descent for Tensor-Train Recurrent Neural Networks
| Title | Riemannian Stochastic Gradient Descent for Tensor-Train Recurrent Neural Networks |
| Authors | Jun Qi, Chin-Hui Lee, Javier Tejedor |
| Abstract | The Tensor-Train factorization (TTF) is an efficient way to compress large weight matrices of fully-connected layers and recurrent layers in recurrent neural networks (RNNs). However, high Tensor-Train ranks for all the core tensors of parameters need to be element-wise fixed, which results in an unnecessary redundancy of model parameters. This work applies Riemannian stochastic gradient descent (RSGD) to train core tensors of parameters in the Riemannian Manifold before finding vectors of lower Tensor-Train ranks for parameters. The paper first presents the RSGD algorithm with a convergence analysis and then tests it on more advanced Tensor-Train RNNs such as bi-directional GRU/LSTM and Encoder-Decoder RNNs with a Tensor-Train attention model. The experiments on digit recognition and machine translation tasks suggest the effectiveness of the RSGD algorithm for Tensor-Train RNNs. |
| Tasks | Machine Translation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1fPYj0qt7 |
| https://openreview.net/pdf?id=B1fPYj0qt7 | |
| PWC | https://paperswithcode.com/paper/riemannian-stochastic-gradient-descent-for |
| Repo | |
| Framework | |
