Paper Group NAWR 18
Inducing a Lexicon of Abusive Words â a Feature-Based Approach. Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning. Bigrams and BiLSTMs Two Neural Networks for Sequential Metaphor Detection. Pelee: A Real-Time Object Detection System on Mobile Devices. Detecting Tweets Mentioning Drug Name and Adverse Drug Reac …
Inducing a Lexicon of Abusive Words â a Feature-Based Approach
| Title | Inducing a Lexicon of Abusive Words â a Feature-Based Approach |
| Authors | Michael Wiegand, Josef Ruppenhofer, Anna Schmidt, Clayton Greenberg |
| Abstract | |
| Tasks | Emotion Classification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/papers/N18-1095/n18-1095 |
| https://www.aclweb.org/anthology/N18-1095 | |
| PWC | https://paperswithcode.com/paper/inducing-a-lexicon-of-abusive-words-a-a |
| Repo | https://github.com/miwieg/naacl2018 |
| Framework | none |
Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning
| Title | Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learning |
| Authors | Tyler Scott, Karl Ridgeway, Michael C. Mozer |
| Abstract | The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to facilitate learning in a related target domain, known as inductive transfer learning. Three active lines of research have independently explored transfer learning using neural networks. In weight transfer, a model trained on the source domain is used as an initialization point for a network to be trained on the target domain. In deep metric learning, the source domain is used to construct an embedding that captures class structure in both the source and target domains. In few-shot learning, the focus is on generalizing well in the target domain based on a limited number of labeled examples. We compare state-of-the-art methods from these three paradigms and also explore hybrid adapted-embedding methods that use limited target-domain data to fine tune embeddings constructed from source-domain data. We conduct a systematic comparison of methods in a variety of domains, varying the number of labeled instances available in the target domain (k), as well as the number of target-domain classes. We reach three principal conclusions: (1) Deep embeddings are far superior, compared to weight transfer, as a starting point for inter-domain transfer or model re-use (2) Our hybrid methods robustly outperform every few-shot learning and every deep metric learning method previously proposed, with a mean error reduction of 34% over state-of-the-art. (3) Among loss functions for discovering embeddings, the histogram loss (Ustinova & Lempitsky, 2016) is most robust. We hope our results will motivate a unification of research in weight transfer, deep metric learning, and few-shot learning. |
| Tasks | Few-Shot Learning, Metric Learning, Transfer Learning |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7293-adapted-deep-embeddings-a-synthesis-of-methods-for-k-shot-inductive-transfer-learning |
| http://papers.nips.cc/paper/7293-adapted-deep-embeddings-a-synthesis-of-methods-for-k-shot-inductive-transfer-learning.pdf | |
| PWC | https://paperswithcode.com/paper/adapted-deep-embeddings-a-synthesis-of |
| Repo | https://github.com/tylersco/adapted_deep_embeddings |
| Framework | tf |
Bigrams and BiLSTMs Two Neural Networks for Sequential Metaphor Detection
| Title | Bigrams and BiLSTMs Two Neural Networks for Sequential Metaphor Detection |
| Authors | Yuri Bizzoni, Mehdi Ghanimifard |
| Abstract | We present and compare two alternative deep neural architectures to perform word-level metaphor detection on text: a bi-LSTM model and a new structure based on recursive feed-forward concatenation of the input. We discuss different versions of such models and the effect that input manipulation - specifically, reducing the length of sentences and introducing concreteness scores for words - have on their performance. |
| Tasks | Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0911/ |
| https://www.aclweb.org/anthology/W18-0911 | |
| PWC | https://paperswithcode.com/paper/bigrams-and-bilstms-two-neural-networks-for |
| Repo | https://github.com/GU-CLASP/ocota |
| Framework | none |
Pelee: A Real-Time Object Detection System on Mobile Devices
| Title | Pelee: A Real-Time Object Detection System on Mobile Devices |
| Authors | Jun Wang, Tanner Bohn, Charles Ling |
| Abstract | An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and MobileNetV2. However, all these models are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead. On ImageNet ILSVRC 2012 dataset, our proposed PeleeNet achieves a higher accuracy and 1.8 times faster speed than MobileNet and MobileNetV2 on NVIDIA TX2. Meanwhile, PeleeNet is only 66% of the model size of MobileNet. We then propose a real-time object detection system by combining PeleeNet with Single Shot MultiBox Detector (SSD) method and optimizing the architecture for fast speed. Our proposed detection system, named Pelee, achieves 76.4% mAP (mean average precision) on PASCAL VOC2007 and 22.4 mAP on MS COCO dataset at the speed of 23.6 FPS on iPhone 8 and 125 FPS on NVIDIA TX2. The result on COCO outperforms YOLOv2 in consideration of a higher precision, 13.6 times lower computational cost and 11.3 times smaller model size. The code and models are open sourced. |
| Tasks | Object Detection, Real-Time Object Detection |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7466-pelee-a-real-time-object-detection-system-on-mobile-devices |
| http://papers.nips.cc/paper/7466-pelee-a-real-time-object-detection-system-on-mobile-devices.pdf | |
| PWC | https://paperswithcode.com/paper/pelee-a-real-time-object-detection-system-on-1 |
| Repo | https://github.com/osmr/imgclsmob |
| Framework | mxnet |
Detecting Tweets Mentioning Drug Name and Adverse Drug Reaction with Hierarchical Tweet Representation and Multi-Head Self-Attention
| Title | Detecting Tweets Mentioning Drug Name and Adverse Drug Reaction with Hierarchical Tweet Representation and Multi-Head Self-Attention |
| Authors | Chuhan Wu, Fangzhao Wu, Junxin Liu, Sixing Wu, Yongfeng Huang, Xing Xie |
| Abstract | This paper describes our system for the first and third shared tasks of the third Social Media Mining for Health Applications (SMM4H) workshop, which aims to detect the tweets mentioning drug names and adverse drug reactions. In our system we propose a neural approach with hierarchical tweet representation and multi-head self-attention (HTR-MSA) for both tasks. Our system achieved the first place in both the first and third shared tasks of SMM4H with an F-score of 91.83{%} and 52.20{%} respectively. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5909/ |
| https://www.aclweb.org/anthology/W18-5909 | |
| PWC | https://paperswithcode.com/paper/detecting-tweets-mentioning-drug-name-and |
| Repo | https://github.com/wuch15/SMM4H_THU_NGN |
| Framework | none |
Identification of Emergency Blood Donation Request on Twitter
| Title | Identification of Emergency Blood Donation Request on Twitter |
| Authors | Puneet Mathur, Meghna Ayyar, Sahil Chopra, Simra Shahid, Laiba Mehnaz, Rajiv Shah |
| Abstract | Social media-based text mining in healthcare has received special attention in recent times due to the enhanced accessibility of social media sites like Twitter. The increasing trend of spreading important information in distress can help patients reach out to prospective blood donors in a time bound manner. However such manual efforts are mostly inefficient due to the limited network of a user. In a novel step to solve this problem, we present an annotated Emergency Blood Donation Request (EBDR) dataset to classify tweets referring to the necessity of urgent blood donation requirement. Additionally, we also present an automated feature-based SVM classification technique that can help selective EBDR tweets reach relevant personals as well as medical authorities. Our experiments also present a quantitative evidence that linguistic along with handcrafted heuristics can act as the most representative set of signals this task with an accuracy of 97.89{%}. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5907/ |
| https://www.aclweb.org/anthology/W18-5907 | |
| PWC | https://paperswithcode.com/paper/identification-of-emergency-blood-donation |
| Repo | https://github.com/pmathur5k10/EBDR |
| Framework | none |
GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model
| Title | GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model |
| Authors | Qile Zhu, Zheng Feng, Xiaolin Li |
| Abstract | Discovering the latent topics within texts has been a fundamental task for many applications. However, conventional topic models suffer different problems in different settings. The Latent Dirichlet Allocation (LDA) may not work well for short texts due to the data sparsity (i.e. the sparse word co-occurrence patterns in short documents). The Biterm Topic Model (BTM) learns topics by modeling the word-pairs named biterms in the whole corpus. This assumption is very strong when documents are long with rich topic information and do not exhibit the transitivity of biterms. In this paper, we propose a novel way called GraphBTM to represent biterms as graphs and design a Graph Convolutional Networks (GCNs) with residual connections to extract transitive features from biterms. To overcome the data sparsity of LDA and the strong assumption of BTM, we sample a fixed number of documents to form a mini-corpus as a sample. We also propose a dataset called All News extracted from 15 news publishers, in which documents are much longer than 20 Newsgroups. We present an amortized variational inference method for GraphBTM. Our method generates more coherent topics compared with previous approaches. Experiments show that the sampling strategy improves performance by a large margin. |
| Tasks | Recommendation Systems, Topic Models |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1495/ |
| https://www.aclweb.org/anthology/D18-1495 | |
| PWC | https://paperswithcode.com/paper/graphbtm-graph-enhanced-autoencoded |
| Repo | https://github.com/valdersoul/GraphBTM |
| Framework | pytorch |
Authorless Topic Models: Biasing Models Away from Known Structure
| Title | Authorless Topic Models: Biasing Models Away from Known Structure |
| Authors | Laure Thompson, David Mimno |
| Abstract | Most previous work in unsupervised semantic modeling in the presence of metadata has assumed that our goal is to make latent dimensions more correlated with metadata, but in practice the exact opposite is often true. Some users want topic models that highlight differences between, for example, authors, but others seek more subtle connections across authors. We introduce three metrics for identifying topics that are highly correlated with metadata, and demonstrate that this problem affects between 30 and 50{%} of the topics in models trained on two real-world collections, regardless of the size of the model. We find that we can predict which words cause this phenomenon and that by selectively subsampling these words we dramatically reduce topic-metadata correlation, improve topic stability, and maintain or even improve model quality. |
| Tasks | Document Classification, Topic Models, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1329/ |
| https://www.aclweb.org/anthology/C18-1329 | |
| PWC | https://paperswithcode.com/paper/authorless-topic-models-biasing-models-away |
| Repo | https://github.com/laurejt/authorless-tms |
| Framework | none |
Identifying Emergent Research Trends by Key Authors and Phrases
| Title | Identifying Emergent Research Trends by Key Authors and Phrases |
| Authors | Shenhao Jiang, Animesh Prasad, Min-Yen Kan, Kazunari Sugiyama |
| Abstract | Identifying emergent research trends is a key issue for both primary researchers as well as secondary research managers. Such processes can uncover the historical development of an area, and yield insight on developing topics. We propose an embedded trend detection framework for this task which incorporates our bijunctive hypothesis that important phrases are written by important authors within a field and vice versa. By ranking both author and phrase information in a multigraph, our method jointly determines key phrases and authoritative authors. We represent this intermediate output as phrasal embeddings, and feed this to a recurrent neural network (RNN) to compute trend scores that identify research trends. Over two large datasets of scientific articles, we demonstrate that our approach successfully detects past trends from the field, outperforming baselines based solely on text centrality or citation. |
| Tasks | Information Retrieval, Topic Models |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1022/ |
| https://www.aclweb.org/anthology/C18-1022 | |
| PWC | https://paperswithcode.com/paper/identifying-emergent-research-trends-by-key |
| Repo | https://github.com/RichardeJiang/racode |
| Framework | tf |
Single Image Dehazing Using Color Ellipsoid Prior
| Title | Single Image Dehazing Using Color Ellipsoid Prior |
| Authors | Trung Minh Bui, Student Member, IEEE, and Wonha Kim, Senior Member, IEEE |
| Abstract | In this paper, we propose a new single-image dehazing method. The proposed method constructs color ellipsoids that are statistically fitted to haze pixel clusters in RGB space and then calculates the transmission values through color ellipsoid geometry. The transmission values generated by the proposed method maximize the contrast of dehazed pixels, while preventing over-saturated pixels. The values are also statistically robust because they are calculated from the averages of the haze pixel values. Furthermore, rather than apply a highly complex refinement process to reduce halo or unnatural artifacts, we embed a fuzzy segmentation process into the construction of the color ellipsoid so that the proposed method simultaneously executes the transmission calculation and the refinement process. The results of an experimental performance evaluation verify that compared with prevailing dehazing methods the proposed method performs effectively across a wide range of haze and noise levels without causing any visible artifacts. Moreover, the relatively low complexity of the proposed method will facilitate its real-time applications. |
| Tasks | Image Dehazing, Single Image Dehazing |
| Published | 2018-02-01 |
| URL | https://ieeexplore.ieee.org/document/8101508 |
| https://github.com/mtbui2010/CEP/blob/master/single%20image%20dehazing%20using%20color%20ellipsoid%20prior.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-dehazing-using-color-ellipsoid |
| Repo | https://github.com/mtbui2010/CEP |
| Framework | none |
Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning
| Title | Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning |
| Authors | Nicolas Coudray, Paolo Santiago Ocampo, Theodore Sakellaropoulos, Navneet Narula, Matija Snuderl, David Fenyö, Andre L. Moreira, Narges Razavian, Aristotelis Tsirigos |
| Abstract | Visual inspection of histopathology slides is one of the main methods used by pathologists to assess the stage, type and subtype of lung tumors. Adenocarcinoma (LUAD) and squamous cell carcinoma (LUSC) are the most prevalent subtypes of lung cancer, and their distinction requires visual inspection by an experienced pathologist. In this study, we trained a deep convolutional neural network (inception v3) on whole-slide images obtained from The Cancer Genome Atlas to accurately and automatically classify them into LUAD, LUSC or normal lung tissue. The performance of our method is comparable to that of pathologists, with an average area under the curve (AUC) of 0.97. Our model was validated on independent datasets of frozen tissues, formalin-fixed paraffin-embedded tissues and biopsies. Furthermore, we trained the network to predict the ten most commonly mutated genes in LUAD. We found that six of them—STK11, EGFR, FAT1, SETBP1, KRAS and TP53—can be predicted from pathology images, with AUCs from 0.733 to 0.856 as measured on a held-out population. These findings suggest that deep-learning models can assist pathologists in the detection of cancer subtype or gene mutations. Our approach can be applied to any cancer type, and the code is available at https://github.com/ncoudray/DeepPATH. |
| Tasks | |
| Published | 2018-09-17 |
| URL | https://www.nature.com/articles/s41591-018-0177-5 |
| https://www.biorxiv.org/content/biorxiv/early/2017/10/03/197574.full-text.pdf | |
| PWC | https://paperswithcode.com/paper/classification-and-mutation-prediction-from |
| Repo | https://github.com/ncoudray/DeepPATH |
| Framework | tf |
WARP-Text: a Web-Based Tool for Annotating Relationships between Pairs of Texts
| Title | WARP-Text: a Web-Based Tool for Annotating Relationships between Pairs of Texts |
| Authors | Venelin Kovatchev, M. Ant{`o}nia Mart{'\i}, Maria Salam{'o} |
| Abstract | We present WARP-Text, an open-source web-based tool for annotating relationships between pairs of texts. WARP-Text supports multi-layer annotation and custom definitions of inter-textual and intra-textual relationships. Annotation can be performed at different granularity levels (such as sentences, phrases, or tokens). WARP-Text has an intuitive user-friendly interface both for project managers and annotators. WARP-Text fills a gap in the currently available NLP toolbox, as open-source alternatives for annotation of pairs of text are not readily available. WARP-Text has already been used in several annotation tasks and can be of interest to the researchers working in the areas of Paraphrasing, Entailment, Simplification, and Summarization, among others. |
| Tasks | Machine Translation, Natural Language Inference, Question Answering, Text Simplification, Text Summarization |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2029/ |
| https://www.aclweb.org/anthology/C18-2029 | |
| PWC | https://paperswithcode.com/paper/warp-text-a-web-based-tool-for-annotating |
| Repo | https://github.com/venelink/WARP |
| Framework | none |
Estimating Linguistic Complexity for Science Texts
| Title | Estimating Linguistic Complexity for Science Texts |
| Authors | Farah Nadeem, Mari Ostendorf |
| Abstract | Evaluation of text difficulty is important both for downstream tasks like text simplification, and for supporting educators in classrooms. Existing work on automated text complexity analysis uses linear models with engineered knowledge-driven features as inputs. While this offers interpretability, these models have lower accuracy for shorter texts. Traditional readability metrics have the additional drawback of not generalizing to informational texts such as science. We propose a neural approach, training on science and other informational texts, to mitigate both problems. Our results show that neural methods outperform knowledge-based linear models for short texts, and have the capacity to generalize to genres not present in the training data. |
| Tasks | Feature Engineering, Reading Comprehension, Text Simplification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0505/ |
| https://www.aclweb.org/anthology/W18-0505 | |
| PWC | https://paperswithcode.com/paper/estimating-linguistic-complexity-for-science |
| Repo | https://github.com/Farahn/Liguistic-Complexity |
| Framework | tf |
Deep Adversarial Metric Learning
| Title | Deep Adversarial Metric Learning |
| Authors | Yueqi Duan, Wenzhao Zheng, Xudong Lin, Jiwen Lu, Jie Zhou |
| Abstract | Learning an effective distance metric between image pairs plays an important role in visual analysis, where the training procedure largely relies on hard negative samples. However, hard negatives in the training set usually account for the tiny minority, which may fail to fully describe the distribution of negative samples close to the margin. In this paper, we propose a deep adversarial metric learning (DAML) framework to generate synthetic hard negatives from the observed negative samples, which is widely applicable to supervised deep metric learning methods. Different from existing metric learning approaches which simply ignore numerous easy negatives, the proposed DAML exploits them to generate potential hard negatives adversary to the learned metric as complements. We simultaneously train the hard negative generator and feature embedding in an adversarial manner, so that more precise distance metrics can be learned with adequate and targeted synthetic hard negatives. Extensive experimental results on three benchmark datasets including CUB-200-2011, Cars196 and Stanford Online Products show that DAML effectively boosts the performance of existing deep metric learning approaches through adversarial learning. |
| Tasks | Metric Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Duan_Deep_Adversarial_Metric_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Duan_Deep_Adversarial_Metric_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-adversarial-metric-learning |
| Repo | https://github.com/duanyq14/DAML |
| Framework | none |
Contextual String Embeddings for Sequence Labeling
| Title | Contextual String Embeddings for Sequence Labeling |
| Authors | Alan Akbik, Duncan Blythe, Rol Vollgraf, |
| Abstract | Recent advances in language modeling using recurrent neural networks have made it viable to model language as distributions over characters. By learning to predict the next character on the basis of previous characters, such models have been shown to automatically internalize linguistic concepts such as words, sentences, subclauses and even sentiment. In this paper, we propose to leverage the internal states of a trained character language model to produce a novel type of word embedding which we refer to as contextual string embeddings. Our proposed embeddings have the distinct properties that they (a) are trained without any explicit notion of words and thus fundamentally model words as sequences of characters, and (b) are contextualized by their surrounding text, meaning that the same word will have different embeddings depending on its contextual use. We conduct a comparative evaluation against previous embeddings and find that our embeddings are highly useful for downstream tasks: across four classic sequence labeling tasks we consistently outperform the previous state-of-the-art. In particular, we significantly outperform previous work on English and German named entity recognition (NER), allowing us to report new state-of-the-art F1-scores on the CoNLL03 shared task. We release all code and pre-trained language models in a simple-to-use framework to the research community, to enable reproduction of these experiments and application of our proposed embeddings to other tasks: https://github.com/zalandoresearch/flair |
| Tasks | Chunking, Language Modelling, Named Entity Recognition, Part-Of-Speech Tagging, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1139/ |
| https://www.aclweb.org/anthology/C18-1139 | |
| PWC | https://paperswithcode.com/paper/contextual-string-embeddings-for-sequence |
| Repo | https://github.com/zalandoresearch/flair |
| Framework | pytorch |
