Paper Group NANR 262
Embodied Amodal Recognition: Learning to Move to Perceive Objects. Neural Models for Detecting Binary Semantic Textual Similarity for Algerian and MSA. Visual TTR - Modelling Visual Question Answering in Type Theory with Records. Single-Document Summarization Using Sentence Embeddings and K-Means Clustering. Unsupervised Extraction of Partial Trans …
Embodied Amodal Recognition: Learning to Move to Perceive Objects
| Title | Embodied Amodal Recognition: Learning to Move to Perceive Objects |
| Authors | Jianwei Yang, Zhile Ren, Mingze Xu, Xinlei Chen, David J. Crandall, Devi Parikh, Dhruv Batra |
| Abstract | Passive visual systems typically fail to recognize objects in the amodal setting where they are heavily occluded. In contrast, humans and other embodied agents have the ability to move in the environment and actively control the viewing angle to better understand object shapes and semantics. In this work, we introduce the task of Embodied Amodel Recognition (EAR): an agent is instantiated in a 3D environment close to an occluded target object, and is free to move in the environment to perform object classification, amodal object localization, and amodal object segmentation. To address this problem, we develop a new model called Embodied Mask R-CNN for agents to learn to move strategically to improve their visual recognition abilities. We conduct experiments using a simulator for indoor environments. Experimental results show that: 1) agents with embodiment (movement) achieve better visual recognition performance than passive ones and 2) in order to improve visual recognition abilities, agents can learn strategic paths that are different from shortest paths. |
| Tasks | Object Classification, Object Localization, Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Yang_Embodied_Amodal_Recognition_Learning_to_Move_to_Perceive_Objects_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_Embodied_Amodal_Recognition_Learning_to_Move_to_Perceive_Objects_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/embodied-amodal-recognition-learning-to-move |
| Repo | |
| Framework | |
Neural Models for Detecting Binary Semantic Textual Similarity for Algerian and MSA
| Title | Neural Models for Detecting Binary Semantic Textual Similarity for Algerian and MSA |
| Authors | Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik |
| Abstract | We explore the extent to which neural networks can learn to identify semantically equivalent sentences from a small variable dataset using an end-to-end training. We collect a new noisy non-standardised user-generated Algerian (ALG) dataset and also translate it to Modern Standard Arabic (MSA) which serves as its regularised counterpart. We compare the performance of various models on both datasets and report the best performing configurations. The results show that relatively simple models composed of 2 LSTM layers outperform by far other more sophisticated attention-based architectures, for both ALG and MSA datasets. |
| Tasks | Semantic Textual Similarity |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4609/ |
| https://www.aclweb.org/anthology/W19-4609 | |
| PWC | https://paperswithcode.com/paper/neural-models-for-detecting-binary-semantic |
| Repo | |
| Framework | |
Visual TTR - Modelling Visual Question Answering in Type Theory with Records
| Title | Visual TTR - Modelling Visual Question Answering in Type Theory with Records |
| Authors | Ronja Utescher |
| Abstract | In this paper, I will describe a system that was developed for the task of Visual Question Answering. The system uses the rich type universe of Type Theory with Records (TTR) to model both the utterances about the image, the image itself and classifications made related to the two. At its most basic, the decision of whether any given predicate can be assigned to an object in the image is delegated to a CNN. Consequently, images can be judged as evidence for propositions. The end result is a model whose application of perceptual classifiers to a given image is guided by the accompanying utterance. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0602/ |
| https://www.aclweb.org/anthology/W19-0602 | |
| PWC | https://paperswithcode.com/paper/visual-ttr-modelling-visual-question |
| Repo | |
| Framework | |
Single-Document Summarization Using Sentence Embeddings and K-Means Clustering
| Title | Single-Document Summarization Using Sentence Embeddings and K-Means Clustering |
| Authors | Sanchit Agarwal, Nikhil Kumar Singh, Priyanka Meel |
| Abstract | This paper proposes a novel method for extractive single document summarization using K-Means clustering and Sentence Embeddings. Sentence embeddings were processed by K-Means algorithm into a number of clusters depending on the required summary size. Sentences in a given cluster contained similar information, and the most appropriate sentence was picked and included in the summary for each cluster by a ridge regression sentence scoring model. Experimental ROUGE score evaluation of summaries of various lengths for the DUC 2001 dataset demonstrated the effectiveness of the approach. |
| Tasks | Document Summarization, Sentence Embeddings |
| Published | 2019-07-01 |
| URL | https://ieeexplore.ieee.org/document/8748762 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8748762 | |
| PWC | https://paperswithcode.com/paper/single-document-summarization-using-sentence |
| Repo | |
| Framework | |
Unsupervised Extraction of Partial Translations for Neural Machine Translation
| Title | Unsupervised Extraction of Partial Translations for Neural Machine Translation |
| Authors | Benjamin Marie, Atsushi Fujita |
| Abstract | In neural machine translation (NMT), monolingual data are usually exploited through a so-called back-translation: sentences in the target language are translated into the source language to synthesize new parallel data. While this method provides more training data to better model the target language, on the source side, it only exploits translations that the NMT system is already able to generate using a model trained on existing parallel data. In this work, we assume that new translation knowledge can be extracted from monolingual data, without relying at all on existing parallel data. We propose a new algorithm for extracting from monolingual data what we call partial translations: pairs of source and target sentences that contain sequences of tokens that are translations of each other. Our algorithm is fully unsupervised and takes only source and target monolingual data as input. Our empirical evaluation points out that our partial translations can be used in combination with back-translation to further improve NMT models. Furthermore, while partial translations are particularly useful for low-resource language pairs, they can also be successfully exploited in resource-rich scenarios to improve translation quality. |
| Tasks | Machine Translation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1384/ |
| https://www.aclweb.org/anthology/N19-1384 | |
| PWC | https://paperswithcode.com/paper/unsupervised-extraction-of-partial |
| Repo | |
| Framework | |
Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification
| Title | Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification |
| Authors | Hu Linmei, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li |
| Abstract | Short text classification has found rich and critical applications in news and tweet tagging to help users find relevant information. Due to lack of labeled training data in many practical use cases, there is a pressing need for studying semi-supervised short text classification. Most existing studies focus on long texts and achieve unsatisfactory performance on short texts due to the sparsity and limited labeled data. In this paper, we propose a novel heterogeneous graph neural network based method for semi-supervised short text classification, leveraging full advantage of few labeled data and large unlabeled data through information propagation along the graph. In particular, we first present a flexible HIN (heterogeneous information network) framework for modeling the short texts, which can integrate any type of additional information as well as capture their relations to address the semantic sparsity. Then, we propose Heterogeneous Graph ATtention networks (HGAT) to embed the HIN for short text classification based on a dual-level attention mechanism, including node-level and type-level attentions. The attention mechanism can learn the importance of different neighboring nodes as well as the importance of different node (information) types to a current node. Extensive experimental results have demonstrated that our proposed model outperforms state-of-the-art methods across six benchmark datasets significantly. |
| Tasks | Heterogeneous Node Classification, Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1488/ |
| https://www.aclweb.org/anthology/D19-1488 | |
| PWC | https://paperswithcode.com/paper/heterogeneous-graph-attention-networks-for |
| Repo | |
| Framework | |
Single Document Summarization as Tree Induction
| Title | Single Document Summarization as Tree Induction |
| Authors | Yang Liu, Ivan Titov, Mirella Lapata |
| Abstract | In this paper, we conceptualize single-document extractive summarization as a tree induction problem. In contrast to previous approaches which have relied on linguistically motivated document representations to generate summaries, our model induces a multi-root dependency tree while predicting the output summary. Each root node in the tree is a summary sentence, and the subtrees attached to it are sentences whose content relates to or explains the summary sentence. We design a new iterative refinement algorithm: it induces the trees through repeatedly refining the structures predicted by previous iterations. We demonstrate experimentally on two benchmark datasets that our summarizer performs competitively against state-of-the-art methods. |
| Tasks | Document Summarization |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1173/ |
| https://www.aclweb.org/anthology/N19-1173 | |
| PWC | https://paperswithcode.com/paper/single-document-summarization-as-tree |
| Repo | |
| Framework | |
Optimal Stochastic and Online Learning with Individual Iterates
| Title | Optimal Stochastic and Online Learning with Individual Iterates |
| Authors | Yunwen Lei, Peng Yang, Ke Tang, Ding-Xuan Zhou |
| Abstract | Stochastic composite mirror descent (SCMD) is a simple and efficient method able to capture both geometric and composite structures of optimization problems in machine learning. Existing strategies require to take either an average or a random selection of iterates to achieve optimal convergence rates, which, however, can either destroy the sparsity of solutions or slow down the practical training speed. In this paper, we propose a theoretically sound strategy to select an individual iterate of the vanilla SCMD, which is able to achieve optimal rates for both convex and strongly convex problems in a non-smooth learning setting. This strategy of outputting an individual iterate can preserve the sparsity of solutions which is crucial for a proper interpretation in sparse learning problems. We report experimental comparisons with several baseline methods to show the effectiveness of our method in achieving a fast training speed as well as in outputting sparse solutions. |
| Tasks | Sparse Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8781-optimal-stochastic-and-online-learning-with-individual-iterates |
| http://papers.nips.cc/paper/8781-optimal-stochastic-and-online-learning-with-individual-iterates.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-stochastic-and-online-learning-with |
| Repo | |
| Framework | |
Extracting Kinship from Obituary to Enhance Electronic Health Records for Genetic Research
| Title | Extracting Kinship from Obituary to Enhance Electronic Health Records for Genetic Research |
| Authors | Kai He, Jialun Wu, Xiaoyong Ma, Chong Zhang, Ming Huang, Chen Li, Lixia Yao |
| Abstract | Claims database and electronic health records database do not usually capture kinship or family relationship information, which is imperative for genetic research. We identify online obituaries as a new data source and propose a special named entity recognition and relation extraction solution to extract names and kinships from online obituaries. Built on 1,809 annotated obituaries and a novel tagging scheme, our joint neural model achieved macro-averaged precision, recall and F measure of 72.69{%}, 78.54{%} and 74.93{%}, and micro-averaged precision, recall and F measure of 95.74{%}, 98.25{%} and 96.98{%} using 57 kinships with 10 or more examples in a 10-fold cross-validation experiment. The model performance improved dramatically when trained with 34 kinships with 50 or more examples. Leveraging additional information such as age, death date, birth date and residence mentioned by obituaries, we foresee a promising future of supplementing EHR databases with comprehensive and accurate kinship information for genetic research. |
| Tasks | Named Entity Recognition, Relation Extraction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3201/ |
| https://www.aclweb.org/anthology/W19-3201 | |
| PWC | https://paperswithcode.com/paper/extracting-kinship-from-obituary-to-enhance |
| Repo | |
| Framework | |
The Second Cross-Lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic Languages
| Title | The Second Cross-Lingual Challenge on Recognition, Normalization, Classification, and Linking of Named Entities across Slavic Languages |
| Authors | Jakub Piskorski, Laska Laskova, Micha{\l} Marci{'n}czuk, Lidia Pivovarova, Pavel P{\v{r}}ib{'a}{\v{n}}, Josef Steinberger, Roman Yangarber |
| Abstract | We describe the Second Multilingual Named Entity Challenge in Slavic languages. The task is recognizing mentions of named entities in Web documents, their normalization, and cross-lingual linking. The Challenge was organized as part of the 7th Balto-Slavic Natural Language Processing Workshop, co-located with the ACL-2019 conference. Eight teams participated in the competition, which covered four languages and five entity types. Performance for the named entity recognition task reached 90{%} F-measure, much higher than reported in the first edition of the Challenge. Seven teams covered all four languages, and five teams participated in the cross-lingual entity linking task. Detailed evaluation information is available on the shared task web page. |
| Tasks | Cross-Lingual Entity Linking, Entity Linking, Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3709/ |
| https://www.aclweb.org/anthology/W19-3709 | |
| PWC | https://paperswithcode.com/paper/the-second-cross-lingual-challenge-on |
| Repo | |
| Framework | |
Exploring the Use of Lexicons to aid Deep Learning towards the Detection of Abusive Language
| Title | Exploring the Use of Lexicons to aid Deep Learning towards the Detection of Abusive Language |
| Authors | Anna Koufakou, Jason Scott |
| Abstract | Detecting abusive language is a significant research topic, which has received a lot of attention recently. Our work focused on detecting personal attacks in online conversations. State-of-the-art research on this task has largely used deep learning with word embeddings. We explored the use of sentiment lexicons as well as semantic lexicons towards improving the accuracy of the baseline Convolutional Neural Network (CNN) using regular word embeddings. This is a work in progress, limited by time constraints and appropriate infrastructure. Our preliminary results showed promise for utilizing lexicons, especially semantic lexicons, for the task of detecting abusive language. |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3640/ |
| https://www.aclweb.org/anthology/W19-3640 | |
| PWC | https://paperswithcode.com/paper/exploring-the-use-of-lexicons-to-aid-deep |
| Repo | |
| Framework | |
PointAE: Point Auto-Encoder for 3D Statistical Shape and Texture Modelling
| Title | PointAE: Point Auto-Encoder for 3D Statistical Shape and Texture Modelling |
| Authors | Hang Dai, Ling Shao |
| Abstract | The outcome of standard statistical shape modelling is a vector space representation of objects. Any convex combination of vectors of a set of object class examples generates a real and valid example. In this paper, we propose a Point Auto-Encoder (PointAE) with skip-connection, attention blocks for 3D statistical shape modelling directly on 3D points. The proposed PointAE is able to refine the correspondence with a correspondence refinement block. The data with refined correspondence can be fed to the PointAE again and bootstrap the constructed statistical models. Instead of two seperate models, PointAE can simultaneously model the shape and texture variation. The extensive evaluation in three open-sourced datasets demonstrates that the proposed method achieves better performance in representation ability of the shape variations. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Dai_PointAE_Point_Auto-Encoder_for_3D_Statistical_Shape_and_Texture_Modelling_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Dai_PointAE_Point_Auto-Encoder_for_3D_Statistical_Shape_and_Texture_Modelling_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pointae-point-auto-encoder-for-3d-statistical |
| Repo | |
| Framework | |
Investigating Correlations Between Human Translation and MT Output
| Title | Investigating Correlations Between Human Translation and MT Output |
| Authors | Samar A. Almazroei, Haruka Ogawa, Devin Gilbert |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7006/ |
| https://www.aclweb.org/anthology/W19-7006 | |
| PWC | https://paperswithcode.com/paper/investigating-correlations-between-human |
| Repo | |
| Framework | |
Parallel Corpus of Croatian-Italian Administrative Texts
| Title | Parallel Corpus of Croatian-Italian Administrative Texts |
| Authors | Marija Brkic Bakaric, Ivana Lalli Pacelat |
| Abstract | Parallel corpora constitute a unique re-source for providing assistance to human translators. The selection and preparation of the parallel corpora also conditions the quality of the resulting MT engine. Since Croatian is a national language and Italian is officially recognized as a minority lan-guage in seven cities and twelve munici-palities of Istria County, a large amount of parallel texts is produced on a daily basis. However, there have been no attempts in using these texts for compiling a parallel corpus. A domain-specific sentence-aligned parallel Croatian-Italian corpus of administrative texts would be of high value in creating different language tools and resources. The aim of this paper is, therefore, to explore the value of parallel documents which are publicly available mostly in pdf format and to investigate the use of automatically-built dictionaries in corpus compilation. The effects that a document format and, consequently sentence splitting, and the dictionary input have on the sentence alignment process are manually evaluated. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8702/ |
| https://www.aclweb.org/anthology/W19-8702 | |
| PWC | https://paperswithcode.com/paper/parallel-corpus-of-croatian-italian |
| Repo | |
| Framework | |
Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning
| Title | Using Customer Service Dialogues for Satisfaction Analysis with Context-Assisted Multiple Instance Learning |
| Authors | Kaisong Song, Lidong Bing, Wei Gao, Jun Lin, Lujun Zhao, Jiancheng Wang, Changlong Sun, Xiaozhong Liu, Qiong Zhang |
| Abstract | Customers ask questions and customer service staffs answer their questions, which is the basic service model via multi-turn customer service (CS) dialogues on E-commerce platforms. Existing studies fail to provide comprehensive service satisfaction analysis, namely satisfaction polarity classification (e.g., well satisfied, met and unsatisfied) and sentimental utterance identification (e.g., positive, neutral and negative). In this paper, we conduct a pilot study on the task of service satisfaction analysis (SSA) based on multi-turn CS dialogues. We propose an extensible Context-Assisted Multiple Instance Learning (CAMIL) model to predict the sentiments of all the customer utterances and then aggregate those sentiments into service satisfaction polarity. After that, we propose a novel Context Clue Matching Mechanism (CCMM) to enhance the representations of all customer utterances with their matched context clues, i.e., sentiment and reasoning clues. We construct two CS dialogue datasets from a top E-commerce platform. Extensive experimental results are presented and contrasted against a few previous models to demonstrate the efficacy of our model. |
| Tasks | Multiple Instance Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1019/ |
| https://www.aclweb.org/anthology/D19-1019 | |
| PWC | https://paperswithcode.com/paper/using-customer-service-dialogues-for |
| Repo | |
| Framework | |
