Paper Group NAWR 33
Convolutional Sequence Generation for Skeleton-Based Action Synthesis. Normalization Helps Training of Quantized LSTM. GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction. Learning Trilingual Dictionaries for Urdu – Roman Urdu – English. Fast Efficient Hyperparameter Tuning for Policy Gradient Methods. Heavy Rain …
Convolutional Sequence Generation for Skeleton-Based Action Synthesis
| Title | Convolutional Sequence Generation for Skeleton-Based Action Synthesis |
| Authors | Sijie Yan, Zhizhong Li, Yuanjun Xiong, Huahan Yan |
| Abstract | In this work, we aim to generate long actions represented as sequences of skeletons. The generated sequences must demonstrate continuous, meaningful human actions, while maintaining coherence among body parts. Instead of generating skeletons sequentially following an autoregressive model, we propose a framework that generates the entire sequence altogether by ransforming from a sequence of latent vectors sampled from a Gaussian process (GP). This framework, named Convolutional Sequence Generation Network (CSGN), jointly models structures in temporal and spatial dimensions. It captures the temporal structure at multiple scales through the GP prior and the temporal convolutions; and establishes the spatial connection between the latent vectors and the skeleton graphs via a novel graph refining scheme. It is noteworthy that CSGN allows bidirectional transforms between the latent and the observed spaces, thus enabling semantic manipulation of the action sequences in various forms. We conducted empirical studies on multiple datasets, including a set of high-quality dancing sequences collected by us. The results show that our framework can produce long action sequences that are coherent across time steps and among body parts. |
| Tasks | Human action generation |
| Published | 2019-10-27 |
| URL | http://yjxiong.me/papers/iccv19csgn.pdf |
| http://www.dahualin.org/publications/dhl19_csgn.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-sequence-generation-for |
| Repo | https://github.com/yysijie/CSGN |
| Framework | none |
Normalization Helps Training of Quantized LSTM
| Title | Normalization Helps Training of Quantized LSTM |
| Authors | Lu Hou, Jinhua Zhu, James Kwok, Fei Gao, Tao Qin, Tie-Yan Liu |
| Abstract | The long-short-term memory (LSTM), though powerful, is memory and computa\x02tion expensive. To alleviate this problem, one approach is to compress its weights by quantization. However, existing quantization methods usually have inferior performance when used on LSTMs. In this paper, we first show theoretically that training a quantized LSTM is difficult because quantization makes the exploding gradient problem more severe, particularly when the LSTM weight matrices are large. We then show that the popularly used weight/layer/batch normalization schemes can help stabilize the gradient magnitude in training quantized LSTMs. Empirical results show that the normalized quantized LSTMs achieve significantly better results than their unnormalized counterparts. Their performance is also comparable with the full-precision LSTM, while being much smaller in size. |
| Tasks | Quantization |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8954-normalization-helps-training-of-quantized-lstm |
| http://papers.nips.cc/paper/8954-normalization-helps-training-of-quantized-lstm.pdf | |
| PWC | https://paperswithcode.com/paper/normalization-helps-training-of-quantized |
| Repo | https://github.com/houlu369/Normalized-Quantized-LSTM |
| Framework | pytorch |
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction
| Title | GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction |
| Authors | Tsu-Jui Fu, Peng-Hsuan Li, Wei-Yun Ma |
| Abstract | In this paper, we present GraphRel, an end-to-end relation extraction model which uses graph convolutional networks (GCNs) to jointly learn named entities and relations. In contrast to previous baselines, we consider the interaction between named entities and relations via a 2nd-phase relation-weighted GCN to better extract relations. Linear and dependency structures are both used to extract both sequential and regional features of the text, and a complete word graph is further utilized to extract implicit features among all word pairs of the text. With the graph-based approach, the prediction for overlapping relations is substantially improved over previous sequential approaches. We evaluate GraphRel on two public datasets: NYT and WebNLG. Results show that GraphRel maintains high precision while increasing recall substantially. Also, GraphRel outperforms previous work by 3.2{%} and 5.8{%} (F1 score), achieving a new state-of-the-art for relation extraction. |
| Tasks | Joint Entity and Relation Extraction, Relation Extraction |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1136/ |
| https://www.aclweb.org/anthology/P19-1136 | |
| PWC | https://paperswithcode.com/paper/graphrel-modeling-text-as-relational-graphs |
| Repo | https://github.com/tsujuifu/pytorch_graph-rel |
| Framework | pytorch |
Learning Trilingual Dictionaries for Urdu – Roman Urdu – English
| Title | Learning Trilingual Dictionaries for Urdu – Roman Urdu – English |
| Authors | Moiz Rauf, Sebastian Pad{'o} |
| Abstract | In this paper, we present an effort to generate a joint Urdu, Roman Urdu and English trilingual lexicon using automated methods. We make a case for using statistical machine translation approaches and parallel corpora for dictionary creation. To this purpose, we use word alignment tools on the corpus and evaluate translations using human evaluators. Despite different writing script and considerable noise in the corpus our results show promise with over 85{%} accuracy of Roman Urdu{–}Urdu and 45{%} English{–}Urdu pairs. |
| Tasks | Machine Translation, Word Alignment |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3614/ |
| https://www.aclweb.org/anthology/W19-3614 | |
| PWC | https://paperswithcode.com/paper/learning-trilingual-dictionaries-for-urdu |
| Repo | https://github.com/MoizRauf/Urdu--Roman-Urdu--English--Dictionary |
| Framework | none |
Fast Efficient Hyperparameter Tuning for Policy Gradient Methods
| Title | Fast Efficient Hyperparameter Tuning for Policy Gradient Methods |
| Authors | Supratik Paul, Vitaly Kurin, Shimon Whiteson |
| Abstract | The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparameters are sample inefficient and computationally expensive. More advanced methods like Population Based Training that learn optimal schedules for hyperparameters instead of fixed settings can yield better results, but are also sample inefficient and computationally expensive. In this paper, we propose Hyperparameter Optimisation on the Fly (HOOF), a gradient-free algorithm that requires no more than one training run to automatically adapt the hyperparameter that affect the policy update directly through the gradient. The main idea is to use existing trajectories sampled by the policy gradient method to optimise a one-step improvement objective, yielding a sample and computationally efficient algorithm that is easy to implement. Our experimental results across multiple domains and algorithms show that using HOOF to learn these hyperparameter schedules leads to faster learning with improved performance. |
| Tasks | Policy Gradient Methods |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8710-fast-efficient-hyperparameter-tuning-for-policy-gradient-methods |
| http://papers.nips.cc/paper/8710-fast-efficient-hyperparameter-tuning-for-policy-gradient-methods.pdf | |
| PWC | https://paperswithcode.com/paper/fast-efficient-hyperparameter-tuning-for-1 |
| Repo | https://github.com/supratikp/HOOF |
| Framework | none |
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
| Title | Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning |
| Authors | Ruoteng Li, Loong-Fah Cheong, Robby T. Tan |
| Abstract | Most deraining works focus on rain streaks removal but they cannot deal adequately with heavy rain images. In heavy rain, streaks are strongly visible, dense rain accumulation or rain veiling effect significantly washes out the image, further scenes are relatively more blurry, etc. In this paper, we propose a novel method to address these problems. We put forth a 2-stage network: a physics-based backbone followed by a depth-guided GAN refinement. The first stage estimates the rain streaks, the transmission, and the atmospheric light governed by the underlying physics. To tease out these components more reliably, a guided filtering framework is used to decompose the image into its low- and high-frequency components. This filtering is guided by a rain-free residue image — its content is used to set the passbands for the two channels in a spatially-variant manner so that the background details do not get mixed up with the rain-streaks. For the second stage, the refinement stage, we put forth a depth-guided GAN to recover the background details failed to be retrieved by the first stage, as well as correcting artefacts introduced by that stage. We have evaluated our method against state of the art methods. Extensive experiments show that our method outperforms them on real rain image data, recovering visually clean images with good details. |
| Tasks | Image Restoration, Rain Removal |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Heavy_Rain_Image_Restoration_Integrating_Physics_Model_and_Conditional_Adversarial_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Heavy_Rain_Image_Restoration_Integrating_Physics_Model_and_Conditional_Adversarial_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/heavy-rain-image-restoration-integrating-1 |
| Repo | https://github.com/liruoteng/HeavyRainRemoval |
| Framework | pytorch |
Improving Sentiment Classification in Slovak Language
| Title | Improving Sentiment Classification in Slovak Language |
| Authors | Samuel Pecar, Marian Simko, Maria Bielikova |
| Abstract | Using different neural network architectures is widely spread for many different NLP tasks. Unfortunately, most of the research is performed and evaluated only in English language and minor languages are often omitted. We believe using similar architectures for other languages can show interesting results. In this paper, we present our study on methods for improving sentiment classification in Slovak language. We performed several experiments for two different datasets, one containing customer reviews, the other one general Twitter posts. We show comparison of performance of different neural network architectures and also different word representations. We show that another improvement can be achieved by using a model ensemble. We performed experiments utilizing different methods of model ensemble. Our proposed models achieved better results than previous models for both datasets. Our experiments showed also other potential research areas. |
| Tasks | Sentiment Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3716/ |
| https://www.aclweb.org/anthology/W19-3716 | |
| PWC | https://paperswithcode.com/paper/improving-sentiment-classification-in-slovak |
| Repo | https://github.com/SamuelPecar/Slovak-sentiment-analysis |
| Framework | pytorch |
CCG Parsing Algorithm with Incremental Tree Rotation
| Title | CCG Parsing Algorithm with Incremental Tree Rotation |
| Authors | Milo{\v{s}} Stanojevi{'c}, Mark Steedman |
| Abstract | The main obstacle to incremental sentence processing arises from right-branching constituent structures, which are present in the majority of English sentences, as well as optional constituents that adjoin on the right, such as right adjuncts and right conjuncts. In CCG, many right-branching derivations can be replaced by semantically equivalent left-branching incremental derivations. The problem of right-adjunction is more resistant to solution, and has been tackled in the past using revealing-based approaches that often rely either on the higher-order unification over lambda terms (Pareschi and Steedman,1987) or heuristics over dependency representations that do not cover the whole CCGbank (Ambati et al., 2015). We propose a new incremental parsing algorithm for CCG following the same revealing tradition of work but having a purely syntactic approach that does not depend on access to a distinct level of semantic representation. This algorithm can cover the whole CCGbank, with greater incrementality and accuracy than previous proposals. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1020/ |
| https://www.aclweb.org/anthology/N19-1020 | |
| PWC | https://paperswithcode.com/paper/ccg-parsing-algorithm-with-incremental-tree |
| Repo | https://github.com/stanojevic/Rotating-CCG |
| Framework | none |
Alignment over Heterogeneous Embeddings for Question Answering
| Title | Alignment over Heterogeneous Embeddings for Question Answering |
| Authors | Vikas Yadav, Steven Bethard, Mihai Surdeanu |
| Abstract | We propose a simple, fast, and mostly-unsupervised approach for non-factoid question answering (QA) called Alignment over Heterogeneous Embeddings (AHE). AHE simply aligns each word in the question and candidate answer with the most similar word in the retrieved supporting paragraph, and weighs each alignment score with the inverse document frequency of the corresponding question/answer term. AHE{'}s similarity function operates over embeddings that model the underlying text at different levels of abstraction: character (FLAIR), word (BERT and GloVe), and sentence (InferSent), where the latter is the only supervised component in the proposed approach. Despite its simplicity and lack of supervision, AHE obtains a new state-of-the-art performance on the {}Easy{''} partition of the AI2 Reasoning Challenge (ARC) dataset (64.6{\%} accuracy), top-two performance on the {}Challenge{''} partition of ARC (34.1{%}), and top-three performance on the WikiQA dataset (74.08{%} MRR), outperforming many other complex, supervised approaches. Our error analysis indicates that alignments over character, word, and sentence embeddings capture substantially different semantic information. We exploit this with a simple meta-classifier that learns how much to trust the predictions over each representation, which further improves the performance of unsupervised AHE. |
| Tasks | Question Answering, Sentence Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1274/ |
| https://www.aclweb.org/anthology/N19-1274 | |
| PWC | https://paperswithcode.com/paper/alignment-over-heterogeneous-embeddings-for |
| Repo | https://github.com/vikas95/AHE |
| Framework | none |
Beyond the Single Neuron Convex Barrier for Neural Network Certification
| Title | Beyond the Single Neuron Convex Barrier for Neural Network Certification |
| Authors | Gagandeep Singh, Rupanshu Ganvir, Markus Püschel, Martin Vechev |
| Abstract | We propose a new parametric framework, called k-ReLU, for computing precise and scalable convex relaxations used to certify neural networks. The key idea is to approximate the output of multiple ReLUs in a layer jointly instead of separately. This joint relaxation captures dependencies between the inputs to different ReLUs in a layer and thus overcomes the convex barrier imposed by the single neuron triangle relaxation and its approximations. The framework is parametric in the number of k ReLUs it considers jointly and can be combined with existing verifiers in order to improve their precision. Our experimental results show that k-ReLU en- ables significantly more precise certification than existing state-of-the-art verifiers while maintaining scalability. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9646-beyond-the-single-neuron-convex-barrier-for-neural-network-certification |
| http://papers.nips.cc/paper/9646-beyond-the-single-neuron-convex-barrier-for-neural-network-certification.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-the-single-neuron-convex-barrier-for |
| Repo | https://github.com/eth-sri/eran |
| Framework | tf |
Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots
| Title | Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots |
| Authors | Chunyuan Yuan, Wei Zhou, Mingming Li, Shangwen Lv, Fuqing Zhu, Jizhong Han, Songlin Hu |
| Abstract | Multi-turn retrieval-based conversation is an important task for building intelligent dialogue systems. Existing works mainly focus on matching candidate responses with every context utterance on multiple levels of granularity, which ignore the side effect of using excessive context information. Context utterances provide abundant information for extracting more matching features, but it also brings noise signals and unnecessary information. In this paper, we will analyze the side effect of using too many context utterances and propose a multi-hop selector network (MSN) to alleviate the problem. Specifically, MSN firstly utilizes a multi-hop selector to select the relevant utterances as context. Then, the model matches the filtered context with the candidate response and obtains a matching score. Experimental results show that MSN outperforms some state-of-the-art methods on three public multi-turn dialogue datasets. |
| Tasks | Conversational Response Selection |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1011/ |
| https://www.aclweb.org/anthology/D19-1011 | |
| PWC | https://paperswithcode.com/paper/multi-hop-selector-network-for-multi-turn |
| Repo | https://github.com/chunyuanY/Dialogue |
| Framework | pytorch |
Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning
| Title | Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning |
| Authors | Zheyi Pan, Yuxuan Liang, Weifeng Wang, Yong Yu, Yu Zheng, Junbo Zhang |
| Abstract | Predicting urban traffic is of great importance to intelligent transportation systems and public safety, yet is very challenging because of two aspects: 1) complex spatio-temporal correlations of urban traffic, including spatial correlations between locations along with temporal correlations among timestamps; 2) diversity of such spatiotemporal correlations, which vary from location to location and depend on the surrounding geographical information, e.g., points of interests and road networks. To tackle these challenges, we proposed a deep-meta-learning based model, entitled ST-MetaNet, to collectively predict traffic in all location at once. ST-MetaNet employs a sequence-to-sequence architecture, consisting of an encoder to learn historical information and a decoder to make predictions step by step. In specific, the encoder and decoder have the same network structure, consisting of a recurrent neural network to encode the traffic, a meta graph attention network to capture diverse spatial correlations, and a meta recurrent neural network to consider diverse temporal correlations. Extensive experiments were conducted based on two real-world datasets to illustrate the effectiveness of ST-MetaNet beyond several state-of-the-art methods. |
| Tasks | Meta-Learning, Spatio-Temporal Forecasting, Time Series, Traffic Prediction |
| Published | 2019-07-25 |
| URL | https://www.kdd.org/kdd2019/accepted-papers/view/urban-traffic-prediction-from-spatio-temporal-data-using-deep-meta-learning |
| https://dl.acm.org/doi/pdf/10.1145/3292500.3330884?download=true | |
| PWC | https://paperswithcode.com/paper/urban-traffic-prediction-from-spatio-temporal |
| Repo | https://github.com/panzheyi/ST-MetaNet |
| Framework | mxnet |
Analyzing Input and Output Representations for Speech-Driven Gesture Generation
| Title | Analyzing Input and Output Representations for Speech-Driven Gesture Generation |
| Authors | Taras Kucherenko, Dai Hasegawa, Gustav Eje Henter, Naoshi Kaneko, Hedvig Kjellström |
| Abstract | This paper presents a novel framework for automatic speech-driven gesture generation, applicable to human-agent interaction including both virtual agents and robots. Specifically, we extend recent deep-learning-based, data-driven methods for speech-driven gesture generation by incorporating representation learning. Our model takes speech as input and produces gestures as output, in the form of a sequence of 3D coordinates. Our approach consists of two steps. First, we learn a lower-dimensional representation of human motion using a denoising autoencoder neural network, consisting of a motion encoder MotionE and a motion decoder MotionD. The learned representation preserves the most important aspects of the human pose variation while removing less relevant variation. Second, we train a novel encoder network SpeechE to map from speech to a corresponding motion representation with reduced dimensionality. At test time, the speech encoder and the motion decoder networks are combined: SpeechE predicts motion representations based on a given speech signal and MotionD then decodes these representations to produce motion sequences. We evaluate different representation sizes in order to find the most effective dimensionality for the representation. We also evaluate the effects of using different speech features as input to the model. We find that MFCCs, alone or combined with prosodic features, perform the best. The results of a subsequent user study confirm the benefits of the representation learning. |
| Tasks | Gesture Generation, Representation Learning, Speech-to-Gesture Translation |
| Published | 2019-03-08 |
| URL | https://arxiv.org/abs/1903.03369 |
| https://arxiv.org/pdf/1903.03369.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-input-and-output-representations |
| Repo | https://github.com/GestureGeneration/Speech_driven_gesture_generation_with_autoencoder |
| Framework | tf |
A Richer-but-Smarter Shortest Dependency Path with Attentive Augmentation for Relation Extraction
| Title | A Richer-but-Smarter Shortest Dependency Path with Attentive Augmentation for Relation Extraction |
| Authors | Duy-Cat Can, Hoang-Quynh Le, Quang-Thuy Ha, Nigel Collier |
| Abstract | To extract the relationship between two entities in a sentence, two common approaches are (1) using their shortest dependency path (SDP) and (2) using an attention model to capture a context-based representation of the sentence. Each approach suffers from its own disadvantage of either missing or redundant information. In this work, we propose a novel model that combines the advantages of these two approaches. This is based on the basic information in the SDP enhanced with information selected by several attention mechanisms with kernel filters, namely RbSP (Richer-but-Smarter SDP). To exploit the representation behind the RbSP structure effectively, we develop a combined deep neural model with a LSTM network on word sequences and a CNN on RbSP. Experimental results on the SemEval-2010 dataset demonstrate improved performance over competitive baselines. The data and source code are available at https://github.com/catcd/RbSP. |
| Tasks | Relation Extraction |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1298/ |
| https://www.aclweb.org/anthology/N19-1298 | |
| PWC | https://paperswithcode.com/paper/a-richer-but-smarter-shortest-dependency-path |
| Repo | https://github.com/catcd/RbSP |
| Framework | none |
Reversible GANs for Memory-Efficient Image-To-Image Translation
| Title | Reversible GANs for Memory-Efficient Image-To-Image Translation |
| Authors | Tycho F.A. van der Ouderaa, Daniel E. Worrall |
| Abstract | The pix2pix and CycleGAN losses have vastly improved the qualitative and quantitative visual quality of results in image-to-image translation tasks. We extend this framework by exploring approximately invertible architectures which are well suited to these losses. These architectures are approximately invertible by design and thus partially satisfy cycle-consistency before training even begins. Furthermore, since invertible architectures have constant memory complexity in depth, these models can be built arbitrarily deep. We are able to demonstrate superior quantitative output on the Cityscapes and Maps datasets at near constant memory budget. |
| Tasks | Image-to-Image Translation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/van_der_Ouderaa_Reversible_GANs_for_Memory-Efficient_Image-To-Image_Translation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/van_der_Ouderaa_Reversible_GANs_for_Memory-Efficient_Image-To-Image_Translation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/reversible-gans-for-memory-efficient-image-to-1 |
| Repo | https://github.com/tychovdo/RevGAN |
| Framework | pytorch |
