October 15, 2019

2607 words 13 mins read

Paper Group NANR 51

Paper Group NANR 51

The Coptic Universal Dependency Treebank. Linguistically-Based Deep Unstructured Question Answering. Deep Generative Models for Weakly-Supervised Multi-Label Classification. OLÉ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep Learning. Quality Signals in Generated Stories. Multi-Task Learning Framework for Mining Crowd Int …

The Coptic Universal Dependency Treebank

Title The Coptic Universal Dependency Treebank
Authors Amir Zeldes, Mitchell Abrams
Abstract This paper presents the Coptic Universal Dependency Treebank, the first dependency treebank within the Egyptian subfamily of the Afro-Asiatic languages. We discuss the composition of the corpus, challenges in adapting the UD annotation scheme to existing conventions for annotating Coptic, and evaluate inter-annotator agreement on UD annotation for the language. Some specific constructions are taken as a starting point for discussing several more general UD annotation guidelines, in particular for appositions, ambiguous passivization, incorporation and object-doubling.
Tasks
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6022/
PDF https://www.aclweb.org/anthology/W18-6022
PWC https://paperswithcode.com/paper/the-coptic-universal-dependency-treebank
Repo
Framework

Linguistically-Based Deep Unstructured Question Answering

Title Linguistically-Based Deep Unstructured Question Answering
Authors Ahmad Aghaebrahimian
Abstract In this paper, we propose a new linguistically-based approach to answering non-factoid open-domain questions from unstructured data. First, we elaborate on an architecture for textual encoding based on which we introduce a deep end-to-end neural model. This architecture benefits from a bilateral attention mechanism which helps the model to focus on a question and the answer sentence at the same time for phrasal answer extraction. Second, we feed the output of a constituency parser into the model directly and integrate linguistic constituents into the network to help it concentrate on chunks of an answer rather than on its single words for generating more natural output. By optimizing this architecture, we managed to obtain near-to-human-performance results and competitive to a state-of-the-art system on SQuAD and MS-MARCO datasets respectively.
Tasks Information Retrieval, Question Answering
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-1042/
PDF https://www.aclweb.org/anthology/K18-1042
PWC https://paperswithcode.com/paper/linguistically-based-deep-unstructured
Repo
Framework

Deep Generative Models for Weakly-Supervised Multi-Label Classification

Title Deep Generative Models for Weakly-Supervised Multi-Label Classification
Authors Hong-Min Chu, Chih-Kuan Yeh, Yu-Chiang Frank Wang
Abstract In order to train learning models for multi-label classification (MLC), it is typically desirable to have a large amount of fully annotated multi-label data. Since such annotation process is in general costly, we focus on the learning task of weakly-supervised multi-label classification (WS-MLC). In this paper, we tackle WS-MLC by learning deep generative models for describing the collected data. In particular, we introduce a sequential network architecture for constructing our generative model with the ability to approximate observed data posterior distributions. We show that how information of training data with missing labels or unlabeled ones can be exploited, which allows us to learn multi-label classifiers via scalable variational inferences. Empirical studies on various scales of datasets demonstrate the effectiveness of our proposed model, which performs favorably against state-of-the-art MLC algorithms.
Tasks Multi-Label Classification
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Hong-Min_Chu_Deep_Generative_Models_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Hong-Min_Chu_Deep_Generative_Models_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/deep-generative-models-for-weakly-supervised
Repo
Framework

OLÉ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep Learning

Title OLÉ: Orthogonal Low-Rank Embedding - A Plug and Play Geometric Loss for Deep Learning
Authors José Lezama, Qiang Qiu, Pablo Musé, Guillermo Sapiro
Abstract Deep neural networks trained using a softmax layer at the top and the cross-entropy loss are ubiquitous tools for image classification. Yet, this does not naturally enforce intra-class similarity nor inter-class margin of the learned deep representations. To simultaneously achieve these two goals, different solutions have been proposed in the literature, such as the pairwise or triplet losses. However, these carry the extra task of selecting pairs or triplets, and the extra computational burden of computing and learning for many combinations of them. In this paper, we propose a plug-and-play loss term for deep networks that explicitly reduces intra-class variance and enforces inter-class margin simultaneously, in a simple and elegant geometric manner. For each class, the deep features are collapsed into a learned linear subspace, or union of them, and inter-class subspaces are pushed to be as orthogonal as possible. Our proposed Orthogonal Low-rank Embedding (OLE) does not require carefully crafting pairs or triplets of samples for training, and works standalone as a classification loss, being the first reported deep metric learning framework of its kind. Because of the improved margin between features of different classes, the resulting deep networks generalize better, are more discriminative, and more robust. We demonstrate improved classification performance in general object recognition, plugging the proposed loss term into existing off-the-shelf architectures. In particular, we show the advantage of the proposed loss in the small data/model scenario, and we significantly advance the state-of-the-art on the Stanford STL-10 benchmark.
Tasks Image Classification, Metric Learning, Object Recognition
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Lezama_OLE_Orthogonal_Low-Rank_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Lezama_OLE_Orthogonal_Low-Rank_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/ola-orthogonal-low-rank-embedding-a-plug-and
Repo
Framework

Quality Signals in Generated Stories

Title Quality Signals in Generated Stories
Authors Manasvi Sagarkar, John Wieting, Lifu Tu, Kevin Gimpel
Abstract We study the problem of measuring the quality of automatically-generated stories. We focus on the setting in which a few sentences of a story are provided and the task is to generate the next sentence ({``}continuation{''}) in the story. We seek to identify what makes a story continuation interesting, relevant, and have high overall quality. We crowdsource annotations along these three criteria for the outputs of story continuation systems, design features, and train models to predict the annotations. Our trained scorer can be used as a rich feature function for story generation, a reward function for systems that use reinforcement learning to learn to generate stories, and as a partial evaluation metric for story generation. |
Tasks Text Generation
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-2024/
PDF https://www.aclweb.org/anthology/S18-2024
PWC https://paperswithcode.com/paper/quality-signals-in-generated-stories
Repo
Framework

Multi-Task Learning Framework for Mining Crowd Intelligence towards Clinical Treatment

Title Multi-Task Learning Framework for Mining Crowd Intelligence towards Clinical Treatment
Authors Shweta Yadav, Asif Ekbal, Sriparna Saha, Pushpak Bhattacharyya, Amit Sheth
Abstract In recent past, social media has emerged as an active platform in the context of healthcare and medicine. In this paper, we present a study where medical user{'}s opinions on health-related issues are analyzed to capture the medical sentiment at a blog level. The medical sentiments can be studied in various facets such as medical condition, treatment, and medication that characterize the overall health status of the user. Considering these facets, we treat analysis of this information as a multi-task classification problem. In this paper, we adopt a novel adversarial learning approach for our multi-task learning framework to learn the sentiment{'}s strengths expressed in a medical blog. Our evaluation shows promising results for our target tasks.
Tasks Multi-Task Learning, Sentiment Analysis
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-2044/
PDF https://www.aclweb.org/anthology/N18-2044
PWC https://paperswithcode.com/paper/multi-task-learning-framework-for-mining
Repo
Framework

使用性別資訊於語者驗證系統之研究與實作 (A study and implementation on Speaker Verification System using Gender Information) [In Chinese]

Title 使用性別資訊於語者驗證系統之研究與實作 (A study and implementation on Speaker Verification System using Gender Information) [In Chinese]
Authors Yu-Jui Su, Jyh-Shing Roger Jang, Po-Cheng Chan
Abstract
Tasks Speaker Verification
Published 2018-10-01
URL https://www.aclweb.org/anthology/O18-1003/
PDF https://www.aclweb.org/anthology/O18-1003
PWC https://paperswithcode.com/paper/a12c-ae3e-14eaeeec3ca1c-cea-a12-a-study-and
Repo
Framework

A Nil-Aware Answer Extraction Framework for Question Answering

Title A Nil-Aware Answer Extraction Framework for Question Answering
Authors Souvik Kundu, Hwee Tou Ng
Abstract Recently, there has been a surge of interest in reading comprehension-based (RC) question answering (QA). However, current approaches suffer from an impractical assumption that every question has a valid answer in the associated passage. A practical QA system must possess the ability to determine whether a valid answer exists in a given text passage. In this paper, we focus on developing QA systems that can extract an answer for a question if and only if the associated passage contains an answer. If the associated passage does not contain any valid answer, the QA system will correctly return Nil. We propose a novel nil-aware answer span extraction framework that is capable of returning Nil or a text span from the associated passage as an answer in a single step. We show that our proposed framework can be easily integrated with several recently proposed QA models developed for reading comprehension and can be trained in an end-to-end fashion. Our proposed nil-aware answer extraction neural network decomposes pieces of evidence into relevant and irrelevant parts and then combines them to infer the existence of any answer. Experiments on the NewsQA dataset show that the integration of our proposed framework significantly outperforms several strong baseline systems that use pipeline or threshold-based approaches.
Tasks Question Answering, Reading Comprehension
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1456/
PDF https://www.aclweb.org/anthology/D18-1456
PWC https://paperswithcode.com/paper/a-nil-aware-answer-extraction-framework-for
Repo
Framework

LTV: Labeled Topic Vector

Title LTV: Labeled Topic Vector
Authors Daniel Baumartz, Tolga Uslu, Alex Mehler, er
Abstract In this paper we present LTV, a website and API that generates labeled topic classifications based on the Dewey Decimal Classification (DDC), an international standard for topic classification in libraries. We introduce nnDDC, a largely language-independent natural network-based classifier for DDC, which we optimized using a wide range of linguistic features to achieve an F-score of 87.4{%}. To show that our approach is language-independent, we evaluate nnDDC using up to 40 different languages. We derive a topic model based on nnDDC, which generates probability distributions over semantic units for any input on sense-, word- and text-level. Unlike related approaches, however, these probabilities are estimated by means of nnDDC so that each dimension of the resulting vector representation is uniquely labeled by a DDC class. In this way, we introduce a neural network-based Classifier-Induced Semantic Space (nnCISS).
Tasks Semantic Textual Similarity
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-2031/
PDF https://www.aclweb.org/anthology/C18-2031
PWC https://paperswithcode.com/paper/ltv-labeled-topic-vector
Repo
Framework

Sequential Clique Optimization for Video Object Segmentation

Title Sequential Clique Optimization for Video Object Segmentation
Authors Yeong Jun Koh, Young-Yoon Lee, Chang-Su Kim
Abstract A novel algorithm to segment out objects in a video sequence is proposed in this work. First, we extract object instances in each frame. Then, we select a visually important object instance in each frame to construct the salient object track through the sequence. This can be formulated as finding the maximal weight clique in a complete k-partite graph, which is NP hard. Therefore, we develop the sequential clique optimization (SCO) technique to efficiently determine the cliques corresponding to salient object tracks. We convert these tracks into video object segmentation results. Experimental results show that the proposed algorithm significantly outperforms the state-of-the-art video object segmentation and video salient object detection algorithms on recent benchmark datasets.
Tasks Object Detection, Salient Object Detection, Semantic Segmentation, Video Object Segmentation, Video Salient Object Detection, Video Semantic Segmentation
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Yeong_Jun_Koh_Sequential_Clique_Optimization_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Yeong_Jun_Koh_Sequential_Clique_Optimization_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/sequential-clique-optimization-for-video
Repo
Framework

Beyond Multiword Expressions: Processing Idioms and Metaphors

Title Beyond Multiword Expressions: Processing Idioms and Metaphors
Authors Valia Kordoni
Abstract Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application. This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.
Tasks Sentiment Analysis
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-5005/
PDF https://www.aclweb.org/anthology/P18-5005
PWC https://paperswithcode.com/paper/beyond-multiword-expressions-processing
Repo
Framework

Dave the debater: a retrieval-based and generative argumentative dialogue agent

Title Dave the debater: a retrieval-based and generative argumentative dialogue agent
Authors Dieu Thu Le, Cam-Tu Nguyen, Kim Anh Nguyen
Abstract In this paper, we explore the problem of developing an argumentative dialogue agent that can be able to discuss with human users on controversial topics. We describe two systems that use retrieval-based and generative models to make argumentative responses to the users. The experiments show promising results although they have been trained on a small dataset.
Tasks Argument Mining, Stance Detection
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5215/
PDF https://www.aclweb.org/anthology/W18-5215
PWC https://paperswithcode.com/paper/dave-the-debater-a-retrieval-based-and
Repo
Framework

Factual'' or Emotional’': Stylized Image Captioning with Adaptive Learning and Attention

Title Factual'' or Emotional’': Stylized Image Captioning with Adaptive Learning and Attention
Authors Tianlang Chen, Zhongping Zhang, Quanzeng You, Chen Fang, Zhaowen Wang, Hailin Jin, Jiebo Luo
Abstract Generating stylized captions for an image is an emerging topic in image captioning. Given an image as input, it requires the system to generate a caption that has a specific style (e.g., humorous, romantic, positive, and negative) while describing the image content semantically accurately. In this paper, we propose a novel stylized image captioning model that effectively takes both requirements into consideration. To this end, we first devise a new variant of LSTM, named style-factual LSTM, as the building block of our model. It uses two groups of matrices to capture the factual and stylized knowledge, respectively, and automatically learns the word-level weights of the two groups based on previous context. In addition, when we train the model to capture stylized elements, we propose an adaptive learning approach based on a reference factual model, it provides factual knowledge to the model as the model learns from stylized caption labels, and can adaptively compute how much information to supply at each time step. We evaluate our model on two stylized image captioning datasets, which contain humorous/romantic captions and positive/negative captions, respectively. Experiments shows that our proposed model outperforms the state-of-the-art approaches, without using extra ground truth supervision.
Tasks Image Captioning
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Tianlang_Chen_Factual_or_Emotional_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Tianlang_Chen_Factual_or_Emotional_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/factual-or-emotional-stylized-image-1
Repo
Framework

Leveraging Syntactic Constructions for Metaphor Identification

Title Leveraging Syntactic Constructions for Metaphor Identification
Authors Kevin Stowe, Martha Palmer
Abstract Identification of metaphoric language in text is critical for generating effective semantic representations for natural language understanding. Computational approaches to metaphor identification have largely relied on heuristic based models or feature-based machine learning, using hand-crafted lexical resources coupled with basic syntactic information. However, recent work has shown the predictive power of syntactic constructions in determining metaphoric source and target domains (Sullivan 2013). Our work intends to explore syntactic constructions and their relation to metaphoric language. We undertake a corpus-based analysis of predicate-argument constructions and their metaphoric properties, and attempt to effectively represent syntactic constructions as features for metaphor processing, both in identifying source and target domains and in distinguishing metaphoric words from non-metaphoric.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0903/
PDF https://www.aclweb.org/anthology/W18-0903
PWC https://paperswithcode.com/paper/leveraging-syntactic-constructions-for
Repo
Framework

Lifelong Learning with Output Kernels

Title Lifelong Learning with Output Kernels
Authors Keerthiram Murugesan, Jaime Carbonell
Abstract Lifelong learning poses considerable challenges in terms of effectiveness (minimizing prediction errors for all tasks) and overall computational tractability for real-time performance. This paper addresses continuous lifelong multitask learning by jointly re-estimating the inter-task relations (\textit{output} kernel) and the per-task model parameters at each round, assuming data arrives in a streaming fashion. We propose a novel algorithm called \textit{Online Output Kernel Learning Algorithm} (OOKLA) for lifelong learning setting. To avoid the memory explosion, we propose a robust budget-limited versions of the proposed algorithm that efficiently utilize the relationship between the tasks to bound the total number of representative examples in the support set. In addition, we propose a two-stage budgeted scheme for efficiently tackling the task-specific budget constraints in lifelong learning. Our empirical results over three datasets indicate superior AUC performance for OOKLA and its budget-limited cousins over strong baselines.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=H1Ww66x0-
PDF https://openreview.net/pdf?id=H1Ww66x0-
PWC https://paperswithcode.com/paper/lifelong-learning-with-output-kernels
Repo
Framework
comments powered by Disqus