Paper Group NANR 83
Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution. How Training Data Affect the Accuracy and Robustness of Neural Networks for Image Classification. MoNERo: a Biomedical Gold Standard Corpus for the Romanian Language. Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain …
Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution
| Title | Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution |
| Authors | Shoichiro Takeda, Yasunori Akagi, Kazuki Okami, Megumi Isogai, Hideaki Kimata |
| Abstract | Video magnification methods can magnify and reveal subtle changes invisible to the naked eye. However, in such subtle changes, meaningful ones caused by physical and natural phenomena are mixed with non-meaningful ones caused by photographic noise. Therefore, current methods often produce noisy and misleading magnification outputs due to the non-meaningful subtle changes. For detecting only meaningful subtle changes, several methods have been proposed but require human manipulations, additional resources, or input video scene limitations. In this paper, we present a novel method using fractional anisotropy (FA) to detect only meaningful subtle changes without the aforementioned requirements. FA has been used in neuroscience to evaluate anisotropic diffusion of water molecules in the body. On the basis of our observation that temporal distribution of meaningful subtle changes more clearly indicates anisotropic diffusion than that of non-meaningful ones, we used FA to design a fractional anisotropic filter that passes only meaningful subtle changes. Using the filter enables our method to obtain better and more impressive magnification results than those obtained with state-of-the-art methods. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Takeda_Video_Magnification_in_the_Wild_Using_Fractional_Anisotropy_in_Temporal_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Takeda_Video_Magnification_in_the_Wild_Using_Fractional_Anisotropy_in_Temporal_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/video-magnification-in-the-wild-using |
| Repo | |
| Framework | |
How Training Data Affect the Accuracy and Robustness of Neural Networks for Image Classification
| Title | How Training Data Affect the Accuracy and Robustness of Neural Networks for Image Classification |
| Authors | Suhua Lei, Huan Zhang, Ke Wang, Zhendong Su |
| Abstract | Recent work has demonstrated the lack of robustness of well-trained deep neural networks (DNNs) to adversarial examples. For example, visually indistinguishable perturbations, when mixed with an original image, can easily lead deep learning models to misclassifications. In light of a recent study on the mutual influence between robustness and accuracy over 18 different ImageNet models, this paper investigates how training data affect the accuracy and robustness of deep neural networks. We conduct extensive experiments on four different datasets, including CIFAR-10, MNIST, STL-10, and Tiny ImageNet, with several representative neural networks. Our results reveal previously unknown phenomena that exist between the size of training data and characteristics of the resulting models. In particular, besides confirming that the model accuracy improves as the amount of training data increases, we also observe that the model robustness improves initially, but there exists a turning point after which robustness starts to decrease. How and when such turning points occur vary for different neural networks and different datasets. |
| Tasks | Image Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HklKWhC5F7 |
| https://openreview.net/pdf?id=HklKWhC5F7 | |
| PWC | https://paperswithcode.com/paper/how-training-data-affect-the-accuracy-and |
| Repo | |
| Framework | |
MoNERo: a Biomedical Gold Standard Corpus for the Romanian Language
| Title | MoNERo: a Biomedical Gold Standard Corpus for the Romanian Language |
| Authors | Maria Mitrofan, Verginica Barbu Mititelu, Grigorina Mitrofan |
| Abstract | In an era when large amounts of data are generated daily in various fields, the biomedical field among others, linguistic resources can be exploited for various tasks of Natural Language Processing. Moreover, increasing number of biomedical documents are available in languages other than English. To be able to extract information from natural language free text resources, methods and tools are needed for a variety of languages. This paper presents the creation of the MoNERo corpus, a gold standard biomedical corpus for Romanian, annotated with both part of speech tags and named entities. MoNERo comprises 154,825 morphologically annotated tokens and 23,188 entity annotations belonging to four entity semantic groups corresponding to UMLS Semantic Groups. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5008/ |
| https://www.aclweb.org/anthology/W19-5008 | |
| PWC | https://paperswithcode.com/paper/monero-a-biomedical-gold-standard-corpus-for |
| Repo | |
| Framework | |
Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain from Text
| Title | Inferential Machine Comprehension: Answering Questions by Recursively Deducing the Evidence Chain from Text |
| Authors | Jianxing Yu, Zhengjun Zha, Jian Yin |
| Abstract | This paper focuses on the topic of inferential machine comprehension, which aims to fully understand the meanings of given text to answer generic questions, especially the ones needed reasoning skills. In particular, we first encode the given document, question and options in a context aware way. We then propose a new network to solve the inference problem by decomposing it into a series of attention-based reasoning steps. The result of the previous step acts as the context of next step. To make each step can be directly inferred from the text, we design an operational cell with prior structure. By recursively linking the cells, the inferred results are synthesized together to form the evidence chain for reasoning, where the reasoning direction can be guided by imposing structural constraints to regulate interactions on the cells. Moreover, a termination mechanism is introduced to dynamically determine the uncertain reasoning depth, and the network is trained by reinforcement learning. Experimental results on 3 popular data sets, including MCTest, RACE and MultiRC, demonstrate the effectiveness of our approach. |
| Tasks | Reading Comprehension |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1217/ |
| https://www.aclweb.org/anthology/P19-1217 | |
| PWC | https://paperswithcode.com/paper/inferential-machine-comprehension-answering |
| Repo | |
| Framework | |
A High-Quality Multilingual Dataset for Structured Documentation Translation
| Title | A High-Quality Multilingual Dataset for Structured Documentation Translation |
| Authors | Kazuma Hashimoto, Raffaella Buschiazzo, James Bradbury, Teresa Marshall, Richard Socher, Caiming Xiong |
| Abstract | This paper presents a high-quality multilingual dataset for the documentation domain to advance research on localization of structured text. Unlike widely-used datasets for translation of plain text, we collect XML-structured parallel text segments from the online documentation for an enterprise software platform. These Web pages have been professionally translated from English into 16 languages and maintained by domain experts, and around 100,000 text segments are available for each language pair. We build and evaluate translation models for seven target languages from English, with several different copy mechanisms and an XML-constrained beam search. We also experiment with a non-English pair to show that our dataset has the potential to explicitly enable 17 {\mbox{$\times$}} 16 translation settings. Our experiments show that learning to translate with the XML tags improves translation accuracy, and the beam search accurately generates XML structures. We also discuss trade-offs of using the copy mechanisms by focusing on translation of numerical words and named entities. We further provide a detailed human analysis of gaps between the model output and human translations for real-world applications, including suitability for post-editing. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5212/ |
| https://www.aclweb.org/anthology/W19-5212 | |
| PWC | https://paperswithcode.com/paper/a-high-quality-multilingual-dataset-for |
| Repo | |
| Framework | |
Integration of Deep Learning and Traditional Machine Learning for Knowledge Extraction from Biomedical Literature
| Title | Integration of Deep Learning and Traditional Machine Learning for Knowledge Extraction from Biomedical Literature |
| Authors | Jihang Mao, Wanli Liu |
| Abstract | In this paper, we present our participation in the Bacteria Biotope (BB) task at BioNLP-OST 2019. Our system utilizes fine-tuned language representation models and machine learning approaches based on word embedding and lexical features for entities recognition, normalization and relation extraction. It achieves the state-of-the-art performance and is among the top two systems in five of all six subtasks. |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5724/ |
| https://www.aclweb.org/anthology/D19-5724 | |
| PWC | https://paperswithcode.com/paper/integration-of-deep-learning-and-traditional |
| Repo | |
| Framework | |
Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder
| Title | Transformer-based Automatic Post-Editing Model with Joint Encoder and Multi-source Attention of Decoder |
| Authors | WonKee Lee, Jaehun Shin, Jong-Hyeok Lee |
| Abstract | This paper describes POSTECH{'}s submission to the WMT 2019 shared task on Automatic Post-Editing (APE). In this paper, we propose a new multi-source APE model by extending Transformer. The main contributions of our study are that we 1) reconstruct the encoder to generate a joint representation of translation (mt) and its src context, in addition to the conventional src encoding and 2) suggest two types of multi-source attention layers to compute attention between two outputs of the encoder and the decoder state in the decoder. Furthermore, we train our model by applying various teacher-forcing ratios to alleviate exposure bias. Finally, we adopt the ensemble technique across variations of our model. Experiments on the WMT19 English-German APE data set show improvements in terms of both TER and BLEU scores over the baseline. Our primary submission achieves -0.73 in TER and +1.49 in BLEU compare to the baseline. |
| Tasks | Automatic Post-Editing |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5412/ |
| https://www.aclweb.org/anthology/W19-5412 | |
| PWC | https://paperswithcode.com/paper/transformer-based-automatic-post-editing |
| Repo | |
| Framework | |
Negotiating Team Formation Using Deep Reinforcement Learning
| Title | Negotiating Team Formation Using Deep Reinforcement Learning |
| Authors | Yoram Bachrach, Richard Everett, Edward Hughes, Angeliki Lazaridou, Joel Leibo, Marc Lanctot, Mike Johanson, Wojtek Czarnecki, Thore Graepel |
| Abstract | When autonomous agents interact in the same environment, they must often cooperate to achieve their goals. One way for agents to cooperate effectively is to form a team, make a binding agreement on a joint plan, and execute it. However, when agents are self-interested, the gains from team formation must be allocated appropriately to incentivize agreement. Various approaches for multi-agent negotiation have been proposed, but typically only work for particular negotiation protocols. More general methods usually require human input or domain-specific data, and so do not scale. To address this, we propose a framework for training agents to negotiate and form teams using deep reinforcement learning. Importantly, our method makes no assumptions about the specific negotiation protocol, and is instead completely experience driven. We evaluate our approach on both non-spatial and spatially extended team-formation negotiation environments, demonstrating that our agents beat hand-crafted bots and reach negotiation outcomes consistent with fair solutions predicted by cooperative game theory. Additionally, we investigate how the physical location of agents influences negotiation outcomes. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJG0ojCcFm |
| https://openreview.net/pdf?id=HJG0ojCcFm | |
| PWC | https://paperswithcode.com/paper/negotiating-team-formation-using-deep |
| Repo | |
| Framework | |
Finite Automata Can be Linearly Decoded from Language-Recognizing RNNs
| Title | Finite Automata Can be Linearly Decoded from Language-Recognizing RNNs |
| Authors | Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Swarat Chaudhuri, Ankit B. Patel |
| Abstract | We study the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language. Specifically, we train an RNN on positive and negative examples from a regular language, and ask if there is a simple decoding function that maps states of this RNN to states of the minimal deterministic finite automaton (MDFA) for the language. Our experiments show that such a decoding function exists, that it is in fact linear, but that it maps states of the RNN not to MDFA states, but to states of an abstraction obtained by clustering small sets of MDFA states into “superstates”. A qualitative analysis reveals that the abstraction often has a simple interpretation. Overall, the results suggest a strong structural relationship between internal representations used by RNNs and finite automata, and explain the well-known ability of RNNs to recognize formal grammatical structure. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1zeHnA9KX |
| https://openreview.net/pdf?id=H1zeHnA9KX | |
| PWC | https://paperswithcode.com/paper/finite-automata-can-be-linearly-decoded-from |
| Repo | |
| Framework | |
CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks
| Title | CNNSAT: Fast, Accurate Boolean Satisfiability using Convolutional Neural Networks |
| Authors | Yu Wang, Fengjuan Gao, Amin Alipour, Linzhang Wang, Xuandong Li, Zhendong Su |
| Abstract | Boolean satisfiability (SAT) is one of the most well-known NP-complete problems and has been extensively studied. State-of-the-art solvers exist and have found a wide range of applications. However, they still do not scale well to formulas with hundreds of variables. To tackle this fundamental scalability challenge, we introduce CNNSAT, a fast and accurate statistical decision procedure for SAT based on convolutional neural networks. CNNSAT’s effectiveness is due to a precise and compact representation of Boolean formulas. On both real and synthetic formulas, CNNSAT is highly accurate and orders of magnitude faster than the state-of-the-art solver Z3. We also describe how to extend CNNSAT to predict satisfying assignments when it predicts a formula to be satisfiable. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryxhynC9KX |
| https://openreview.net/pdf?id=ryxhynC9KX | |
| PWC | https://paperswithcode.com/paper/cnnsat-fast-accurate-boolean-satisfiability |
| Repo | |
| Framework | |
Simple dynamic word embeddings for mapping perceptions in the public sphere
| Title | Simple dynamic word embeddings for mapping perceptions in the public sphere |
| Authors | Nabeel Gillani, Roger Levy |
| Abstract | Word embeddings trained on large-scale historical corpora can illuminate human biases and stereotypes that perpetuate social inequalities. These embeddings are often trained in separate vector space models defined according to different attributes of interest. In this paper, we introduce a single, unified dynamic embedding model that learns attribute-specific word embeddings and apply it to a novel dataset{—}talk radio shows from around the US{—}to analyze perceptions about refugees. We validate our model on a benchmark dataset and apply it to two corpora of talk radio shows averaging 117 million words produced over one month across 83 stations and 64 cities. Our findings suggest that dynamic word embeddings are capable of identifying nuanced differences in public discourse about contentious topics, suggesting their usefulness as a tool for better understanding how the public perceives and engages with different issues across time, geography, and other dimensions. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2111/ |
| https://www.aclweb.org/anthology/W19-2111 | |
| PWC | https://paperswithcode.com/paper/simple-dynamic-word-embeddings-for-mapping |
| Repo | |
| Framework | |
An NLG System for Constituent Correspondence: Personality, Affect, and Alignment
| Title | An NLG System for Constituent Correspondence: Personality, Affect, and Alignment |
| Authors | William Kolkey, Jian Dong, Greg Bybee |
| Abstract | Roughly 30{%} of congressional staffers in the United States report spending a {``}great deal{''} of time writing responses to constituent letters. Letters often solicit an update on the status of legislation and a description of a congressman{'}s vote record or vote intention {—} structurable data that can be leveraged by a natural language generation (NLG) system to create a coherent letter response. This paper describes how PoliScribe, a pipeline-architectured NLG platform, constructs personalized responses to constituents inquiring about legislation. Emphasis will be placed on adapting NLG methodologies to the political domain, which entails special attention to affect, discursive variety, and rhetorical strategies that align a speaker with their interlocutor, even in cases of policy disagreement. | |
| Tasks | Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8631/ |
| https://www.aclweb.org/anthology/W19-8631 | |
| PWC | https://paperswithcode.com/paper/an-nlg-system-for-constituent-correspondence |
| Repo | |
| Framework | |
Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings
| Title | Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings |
| Authors | Marimuthu Kalimuthu, Michael Barz, Daniel Sonntag |
| Abstract | We study the problem of incremental domain adaptation of a generic neural machine translation model with limited resources (e.g., budget and time) for human translations or model training. In this paper, we propose a novel query strategy for selecting {``}unlabeled{''} samples from a new domain based on sentence embeddings for Arabic. We accelerate the fine-tuning process of the generic model to the target domain. Specifically, our approach estimates the informativeness of instances from the target domain by comparing the distance of their sentence embeddings to embeddings from the generic domain. We perform machine translation experiments (Ar-to-En direction) for comparing a random sampling baseline with our new approach, similar to active learning, using two small update sets for simulating the work of human translators. For the prescribed setting we can save more than 50{%} of the annotation costs without loss in quality, demonstrating the effectiveness of our approach. | |
| Tasks | Active Learning, Domain Adaptation, Machine Translation, Sentence Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4601/ |
| https://www.aclweb.org/anthology/W19-4601 | |
| PWC | https://paperswithcode.com/paper/incremental-domain-adaptation-for-neural |
| Repo | |
| Framework | |
Multilingual Dynamic Topic Model
| Title | Multilingual Dynamic Topic Model |
| Authors | Elaine Zosa, Mark Granroth-Wilding |
| Abstract | Dynamic topic models (DTMs) capture the evolution of topics and trends in time series data.Current DTMs are applicable only to monolingual datasets. In this paper we present the multilingual dynamic topic model (ML-DTM), a novel topic model that combines DTM with an existing multilingual topic modeling method to capture cross-lingual topics that evolve across time. We present results of this model on a parallel German-English corpus of news articles and a comparable corpus of Finnish and Swedish news articles. We demonstrate the capability of ML-DTM to track significant events related to a topic and show that it finds distinct topics and performs as well as existing multilingual topic models in aligning cross-lingual topics. |
| Tasks | Time Series, Topic Models |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1159/ |
| https://www.aclweb.org/anthology/R19-1159 | |
| PWC | https://paperswithcode.com/paper/multilingual-dynamic-topic-model |
| Repo | |
| Framework | |
Leveraging Meta Information in Short Text Aggregation
| Title | Leveraging Meta Information in Short Text Aggregation |
| Authors | He Zhao, Lan Du, Guanfeng Liu, Wray Buntine |
| Abstract | Short texts such as tweets often contain insufficient word co-occurrence information for training conventional topic models. To deal with the insufficiency, we propose a generative model that aggregates short texts into clusters by leveraging the associated meta information. Our model can generate more interpretable topics as well as document clusters. We develop an effective Gibbs sampling algorithm favoured by the fully local conjugacy in the model. Extensive experiments demonstrate that our model achieves better performance in terms of document clustering and topic coherence. |
| Tasks | Topic Models |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1396/ |
| https://www.aclweb.org/anthology/P19-1396 | |
| PWC | https://paperswithcode.com/paper/leveraging-meta-information-in-short-text |
| Repo | |
| Framework | |
