Paper Group NANR 12
BioRo: The Biomedical Corpus for the Romanian Language. Interactive Boundary Prediction for Object Selection. Predicting Discharge Disposition Using Patient Complaint Notes in Electronic Medical Records. Chinese Grammatical Error Diagnosis Based on Policy Gradient LSTM Model. DM_NLP at SemEval-2018 Task 8: neural sequence labeling with linguistic …
BioRo: The Biomedical Corpus for the Romanian Language
| Title | BioRo: The Biomedical Corpus for the Romanian Language |
| Authors | Maria Mitrofan, Dan Tufi{\c{s}} |
| Abstract | |
| Tasks | Lemmatization, Tokenization |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1191/ |
| https://www.aclweb.org/anthology/L18-1191 | |
| PWC | https://paperswithcode.com/paper/bioro-the-biomedical-corpus-for-the-romanian |
| Repo | |
| Framework | |
Interactive Boundary Prediction for Object Selection
| Title | Interactive Boundary Prediction for Object Selection |
| Authors | Hoang Le, Long Mai, Brian Price, Scott Cohen, Hailin Jin, Feng Liu |
| Abstract | Interactive image segmentation is critical for many image editing tasks. While recent advanced methods on interactive segmentation focus on the region-based paradigm, more traditional boundary-based methods such as Intelligent Scissor are still popular in practice as they allow users to have active control of the object boundaries. Existing methods for boundary-based segmentation solely rely on low-level image features, such as edges for boundary extraction, which limits their ability to adapt to high-level image content and user intention. In this paper, we introduce an interaction-aware method for boundary-based image segmentation. Instead of relying on pre-defined low-level image features, our method adaptively predicts object boundaries according to image content and user interactions. Therein, we develop a fully convolutional encoder-decoder network that takes both the image and user interactions (e.g. clicks on boundary points) as input and predicts semantically meaningful boundaries that match user intentions. Our method explicitly models the dependency of boundary extraction results on image content and user interactions. Experiments on two public interactive segmentation benchmarks show that our method significantly improves the boundary quality of segmentation results compared to state-of-the-art methods while requiring fewer user interactions. |
| Tasks | Interactive Segmentation, Semantic Segmentation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Hoang_Le_Interactive_Boundary_Prediction_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Hoang_Le_Interactive_Boundary_Prediction_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/interactive-boundary-prediction-for-object |
| Repo | |
| Framework | |
Predicting Discharge Disposition Using Patient Complaint Notes in Electronic Medical Records
| Title | Predicting Discharge Disposition Using Patient Complaint Notes in Electronic Medical Records |
| Authors | Mohamad Salimi, Alla Rozovskaya |
| Abstract | Overcrowding in emergency rooms is a major challenge faced by hospitals across the United States. Overcrowding can result in longer wait times, which, in turn, has been shown to adversely affect patient satisfaction, clinical outcomes, and procedure reimbursements. This paper presents research that aims to automatically predict discharge disposition of patients who received medical treatment in an emergency department. We make use of a corpus that consists of notes containing patient complaints, diagnosis information, and disposition, entered by health care providers. We use this corpus to develop a model that uses the complaint and diagnosis information to predict patient disposition. We show that the proposed model substantially outperforms the baseline of predicting the most common disposition type. The long-term goal of this research is to build a model that can be implemented as a real-time service in an application to predict disposition as patients arrive. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2316/ |
| https://www.aclweb.org/anthology/W18-2316 | |
| PWC | https://paperswithcode.com/paper/predicting-discharge-disposition-using |
| Repo | |
| Framework | |
Chinese Grammatical Error Diagnosis Based on Policy Gradient LSTM Model
| Title | Chinese Grammatical Error Diagnosis Based on Policy Gradient LSTM Model |
| Authors | Changliang Li, Ji Qi |
| Abstract | Chinese Grammatical Error Diagnosis (CGED) is a natural language processing task for the NLPTEA2018 workshop held during ACL2018. The goal of this task is to diagnose Chinese sentences containing four kinds of grammatical errors through the model and find out the sentence errors. Chinese grammatical error diagnosis system is a very important tool, which can help Chinese learners automatically diagnose grammatical errors in many scenarios. However, due to the limitations of the Chinese language{'}s own characteristics and datasets, the traditional model faces the problem of extreme imbalances in the positive and negative samples and the disappearance of gradients. In this paper, we propose a sequence labeling method based on the Policy Gradient LSTM model and apply it to this task to solve the above problems. The results show that our model can achieve higher precision scores in the case of lower False positive rate (FPR) and it is convenient to optimize the model on-line. |
| Tasks | Chinese Word Segmentation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3710/ |
| https://www.aclweb.org/anthology/W18-3710 | |
| PWC | https://paperswithcode.com/paper/chinese-grammatical-error-diagnosis-based-on-1 |
| Repo | |
| Framework | |
DM_NLP at SemEval-2018 Task 8: neural sequence labeling with linguistic features
| Title | DM_NLP at SemEval-2018 Task 8: neural sequence labeling with linguistic features |
| Authors | Chunping Ma, Huafei Zheng, Pengjun Xie, Chen Li, Linlin Li, Luo Si |
| Abstract | This paper describes our submissions for SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using NLP. The DM{_}NLP participated in two subtasks: SubTask 1 classifies if a sentence is useful for inferring malware actions and capabilities, and SubTask 2 predicts token labels ({}Action{''}, {}Entity{''}, {}Modifier{''} and {}Others{''}) for a given malware-related sentence. Since we leverage results of Subtask 2 directly to infer the result of Subtask 1, the paper focus on the system solving Subtask 2. By taking Subtask 2 as a sequence labeling task, our system relies on a recurrent neural network named BiLSTM-CNN-CRF with rich linguistic features, such as POS tags, dependency parsing labels, chunking labels, NER labels, Brown clustering. Our system achieved the highest F1 score in both token level and phrase level. |
| Tasks | Chinese Word Segmentation, Chunking, Dependency Parsing |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1114/ |
| https://www.aclweb.org/anthology/S18-1114 | |
| PWC | https://paperswithcode.com/paper/dm_nlp-at-semeval-2018-task-8-neural-sequence |
| Repo | |
| Framework | |
Evaluation of a Sequence Tagging Tool for Biomedical Texts
| Title | Evaluation of a Sequence Tagging Tool for Biomedical Texts |
| Authors | Julien Tourille, Matthieu Doutreligne, Olivier Ferret, Aur{'e}lie N{'e}v{'e}ol, Nicolas Paris, Xavier Tannier |
| Abstract | Many applications in biomedical natural language processing rely on sequence tagging as an initial step to perform more complex analysis. To support text analysis in the biomedical domain, we introduce Yet Another SEquence Tagger (YASET), an open-source multi purpose sequence tagger that implements state-of-the-art deep learning algorithms for sequence tagging. Herein, we evaluate YASET on part-of-speech tagging and named entity recognition in a variety of text genres including articles from the biomedical literature in English and clinical narratives in French. To further characterize performance, we report distributions over 30 runs and different sizes of training datasets. YASET provides state-of-the-art performance on the CoNLL 2003 NER dataset (F1=0.87), MEDPOST corpus (F1=0.97), MERLoT corpus (F1=0.99) and NCBI disease corpus (F1=0.81). We believe that YASET is a versatile and efficient tool that can be used for sequence tagging in biomedical and clinical texts. |
| Tasks | Named Entity Recognition, Part-Of-Speech Tagging, Relation Extraction, Text Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5622/ |
| https://www.aclweb.org/anthology/W18-5622 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-a-sequence-tagging-tool-for |
| Repo | |
| Framework | |
Argumentative Link Prediction using Residual Networks and Multi-Objective Learning
| Title | Argumentative Link Prediction using Residual Networks and Multi-Objective Learning |
| Authors | Andrea Galassi, Marco Lippi, Paolo Torroni |
| Abstract | We explore the use of residual networks for argumentation mining, with an emphasis on link prediction. The method we propose makes no assumptions on document or argument structure. We evaluate it on a challenging dataset consisting of user-generated comments collected from an online platform. Results show that our model outperforms an equivalent deep network and offers results comparable with state-of-the-art methods that rely on domain knowledge. |
| Tasks | Argument Mining, Boundary Detection, Link Prediction |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5201/ |
| https://www.aclweb.org/anthology/W18-5201 | |
| PWC | https://paperswithcode.com/paper/argumentative-link-prediction-using-residual |
| Repo | |
| Framework | |
Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model
| Title | Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model |
| Authors | Aaron Sidford, Mengdi Wang, Xian Wu, Lin Yang, Yinyu Ye |
| Abstract | In this paper we consider the problem of computing an $\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any state-action pair samples from the transition function in $O(1)$ time. Given such a DMDP with states $\states$, actions $\actions$, discount factor $\gamma\in(0,1)$, and rewards in range $[0, 1]$ we provide an algorithm which computes an $\epsilon$-optimal policy with probability $1 - \delta$ where {\it both} the run time spent and number of sample taken is upper bounded by [ O\left[\frac{\cS\cA}{(1-\gamma)^3 \epsilon^2} \log \left(\frac{\cS\cA}{(1-\gamma)\delta \epsilon} \right) \log\left(\frac{1}{(1-\gamma)\epsilon}\right)\right] ~. ] For fixed values of $\epsilon$, this improves upon the previous best known bounds by a factor of $(1 - \gamma)^{-1}$ and matches the sample complexity lower bounds proved in \cite{azar2013minimax} up to logarithmic factors. We also extend our method to computing $\epsilon$-optimal policies for finite-horizon MDP with a generative model and provide a nearly matching sample complexity lower bound. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7765-near-optimal-time-and-sample-complexities-for-solving-markov-decision-processes-with-a-generative-model |
| http://papers.nips.cc/paper/7765-near-optimal-time-and-sample-complexities-for-solving-markov-decision-processes-with-a-generative-model.pdf | |
| PWC | https://paperswithcode.com/paper/near-optimal-time-and-sample-complexities-for |
| Repo | |
| Framework | |
A^2-Nets: Double Attention Networks
| Title | A^2-Nets: Double Attention Networks |
| Authors | Yunpeng Chen, Yannis Kalantidis, Jianshu Li, Shuicheng Yan, Jiashi Feng |
| Abstract | Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the “double attention block”, a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access features from the entire space efficiently. The component is designed with a double attention mechanism in two steps, where the first step gathers features from the entire space into a compact set through second-order attention pooling and the second step adaptively selects and distributes features to each location via another attention. The proposed double attention block is easy to adopt and can be plugged into existing deep neural networks conveniently. We conduct extensive ablation studies and experiments on both image and video recognition tasks for evaluating its performance. On the image recognition task, a ResNet-50 equipped with our double attention blocks outperforms a much larger ResNet-152 architecture on ImageNet-1k dataset with over 40% less the number of parameters and less FLOPs. On the action recognition task, our proposed model achieves the state-of-the-art results on the Kinetics and UCF-101 datasets with significantly higher efficiency than recent works. |
| Tasks | Temporal Action Localization, Video Recognition |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7318-a2-nets-double-attention-networks |
| http://papers.nips.cc/paper/7318-a2-nets-double-attention-networks.pdf | |
| PWC | https://paperswithcode.com/paper/a2-nets-double-attention-networks-1 |
| Repo | |
| Framework | |
Supervised Rhyme Detection with Siamese Recurrent Networks
| Title | Supervised Rhyme Detection with Siamese Recurrent Networks |
| Authors | Thomas Haider, Jonas Kuhn |
| Abstract | We present the first supervised approach to rhyme detection with Siamese Recurrent Networks (SRN) that offer near perfect performance (97{%} accuracy) with a single model on rhyme pairs for German, English and French, allowing future large scale analyses. SRNs learn a similarity metric on variable length character sequences that can be used as judgement on the distance of imperfect rhyme pairs and for binary classification. For training, we construct a diachronically balanced rhyme goldstandard of New High German (NHG) poetry. For further testing, we sample a second collection of NHG poetry and set of contemporary Hip-Hop lyrics, annotated for rhyme and assonance. We train several high-performing SRN models and evaluate them qualitatively on selected sonnetts. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4509/ |
| https://www.aclweb.org/anthology/W18-4509 | |
| PWC | https://paperswithcode.com/paper/supervised-rhyme-detection-with-siamese |
| Repo | |
| Framework | |
Exploiting Structure in Representation of Named Entities using Active Learning
| Title | Exploiting Structure in Representation of Named Entities using Active Learning |
| Authors | Nikita Bhutani, Kun Qian, Yunyao Li, H. V. Jagadish, Hern, Mauricio ez, Mitesh Vasa |
| Abstract | Fundamental to several knowledge-centric applications is the need to identify named entities from their textual mentions. However, entities lack a unique representation and their mentions can differ greatly. These variations arise in complex ways that cannot be captured using textual similarity metrics. However, entities have underlying structures, typically shared by entities of the same entity type, that can help reason over their name variations. Discovering, learning and manipulating these structures typically requires high manual effort in the form of large amounts of labeled training data and handwritten transformation programs. In this work, we propose an active-learning based framework that drastically reduces the labeled data required to learn the structures of entities. We show that programs for mapping entity mentions to their structures can be automatically generated using human-comprehensible labels. Our experiments show that our framework consistently outperforms both handwritten programs and supervised learning models. We also demonstrate the utility of our framework in relation extraction and entity resolution tasks. |
| Tasks | Active Learning, Entity Linking, Entity Resolution, Question Answering, Relation Extraction, Text Summarization |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1058/ |
| https://www.aclweb.org/anthology/C18-1058 | |
| PWC | https://paperswithcode.com/paper/exploiting-structure-in-representation-of |
| Repo | |
| Framework | |
Pattern-revising Enhanced Simple Question Answering over Knowledge Bases
| Title | Pattern-revising Enhanced Simple Question Answering over Knowledge Bases |
| Authors | Yanchao Hao, Hao Liu, Shizhu He, Kang Liu, Jun Zhao |
| Abstract | Question Answering over Knowledge Bases (KB-QA), which automatically answer natural language questions based on the facts contained by a knowledge base, is one of the most important natural language processing (NLP) tasks. Simple questions constitute a large part of questions queried on the web, still being a challenge to QA systems. In this work, we propose to conduct pattern extraction and entity linking first, and put forward pattern revising procedure to mitigate the error propagation problem. In order to learn to rank candidate subject-predicate pairs to enable the relevant facts retrieval given a question, we propose to do joint fact selection enhanced by relation detection. Multi-level encodings and multi-dimension information are leveraged to strengthen the whole procedure. The experimental results demonstrate that our approach sets a new record in this task, outperforming the current state-of-the-art by an absolute large margin. |
| Tasks | Entity Linking, Question Answering |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1277/ |
| https://www.aclweb.org/anthology/C18-1277 | |
| PWC | https://paperswithcode.com/paper/pattern-revising-enhanced-simple-question |
| Repo | |
| Framework | |
The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation
| Title | The INCEpTION Platform: Machine-Assisted and Knowledge-Oriented Interactive Annotation |
| Authors | Jan-Christoph Klie, Michael Bugert, Beto Boullosa, Richard Eckart de Castilho, Iryna Gurevych |
| Abstract | We introduce INCEpTION, a new annotation platform for tasks including interactive and semantic annotation (e.g., concept linking, fact linking, knowledge base population, semantic frame annotation). These tasks are very time consuming and demanding for annotators, especially when knowledge bases are used. We address these issues by developing an annotation platform that incorporates machine learning capabilities which actively assist and guide annotators. The platform is both generic and modular. It targets a range of research domains in need of semantic annotation, such as digital humanities, bioinformatics, or linguistics. INCEpTION is publicly available as open-source software. |
| Tasks | Active Learning, Entity Linking, Knowledge Base Population |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2002/ |
| https://www.aclweb.org/anthology/C18-2002 | |
| PWC | https://paperswithcode.com/paper/the-inception-platform-machine-assisted-and |
| Repo | |
| Framework | |
Training Structured Prediction Energy Networks with Indirect Supervision
| Title | Training Structured Prediction Energy Networks with Indirect Supervision |
| Authors | Amirmohammad Rooshenas, Aishwarya Kamath, Andrew McCallum |
| Abstract | This paper introduces rank-based training of structured prediction energy networks (SPENs). Our method samples from output structures using gradient descent and minimizes the ranking violation of the sampled structures with respect to a scalar scoring function defined with domain knowledge. We have successfully trained SPEN for citation field extraction without any labeled data instances, where the only source of supervision is a simple human-written scoring function. Such scoring functions are often easy to provide; the SPEN then furnishes an efficient structured prediction inference procedure. |
| Tasks | Semantic Segmentation, Structured Prediction |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2021/ |
| https://www.aclweb.org/anthology/N18-2021 | |
| PWC | https://paperswithcode.com/paper/training-structured-prediction-energy |
| Repo | |
| Framework | |
Automatic Question Generation using Relative Pronouns and Adverbs
| Title | Automatic Question Generation using Relative Pronouns and Adverbs |
| Authors | Payal Khullar, Konigari Rachna, Mukul Hase, Manish Shrivastava |
| Abstract | This paper presents a system that automatically generates multiple, natural language questions using relative pronouns and relative adverbs from complex English sentences. Our system is syntax-based, runs on dependency parse information of a single-sentence input, and achieves high accuracy in terms of syntactic correctness, semantic adequacy, fluency and uniqueness. One of the key advantages of our system, in comparison with other rule-based approaches, is that we nearly eliminate the chances of getting a wrong wh-word in the generated question, by fetching the requisite wh-word from the input sentence itself. Depending upon the input, we generate both factoid and descriptive type questions. To the best of our information, the exploitation of wh-pronouns and wh-adverbs to generate questions is novel in the Automatic Question Generation task. |
| Tasks | Dialogue Generation, Information Retrieval, Question Answering, Question Generation, Reading Comprehension |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-3022/ |
| https://www.aclweb.org/anthology/P18-3022 | |
| PWC | https://paperswithcode.com/paper/automatic-question-generation-using-relative |
| Repo | |
| Framework | |
