Paper Group NANR 91
Towards an open-source universal-dependency treebank for Erzya. Open-Domain Event Detection using Distant Supervision. Polish Corpus of Annotated Descriptions of Images. Unsupervised Deep Structure Learning by Recursive Dependency Analysis. Building and Learning Structures in a Situated Blocks World Through Deep Language Understanding. “Seeing is B …
Towards an open-source universal-dependency treebank for Erzya
| Title | Towards an open-source universal-dependency treebank for Erzya |
| Authors | Jack Rueter, Francis Tyers |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0210/ |
| https://www.aclweb.org/anthology/W18-0210 | |
| PWC | https://paperswithcode.com/paper/towards-an-open-source-universal-dependency |
| Repo | |
| Framework | |
Open-Domain Event Detection using Distant Supervision
| Title | Open-Domain Event Detection using Distant Supervision |
| Authors | Jun Araki, Teruko Mitamura |
| Abstract | This paper introduces open-domain event detection, a new event detection paradigm to address issues of prior work on restricted domains and event annotation. The goal is to detect all kinds of events regardless of domains. Given the absence of training data, we propose a distant supervision method that is able to generate high-quality training data. Using a manually annotated event corpus as gold standard, our experiments show that despite no direct supervision, the model outperforms supervised models. This result indicates that the distant supervision enables robust event detection in various domains, while obviating the need for human annotation of events. |
| Tasks | Open-Domain Question Answering, Question Answering |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1075/ |
| https://www.aclweb.org/anthology/C18-1075 | |
| PWC | https://paperswithcode.com/paper/open-domain-event-detection-using-distant |
| Repo | |
| Framework | |
Polish Corpus of Annotated Descriptions of Images
| Title | Polish Corpus of Annotated Descriptions of Images |
| Authors | Alina Wr{'o}blewska |
| Abstract | |
| Tasks | Image Classification, Image Generation, Image Retrieval, Text Generation, Text-to-Image Generation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1337/ |
| https://www.aclweb.org/anthology/L18-1337 | |
| PWC | https://paperswithcode.com/paper/polish-corpus-of-annotated-descriptions-of |
| Repo | |
| Framework | |
Unsupervised Deep Structure Learning by Recursive Dependency Analysis
| Title | Unsupervised Deep Structure Learning by Recursive Dependency Analysis |
| Authors | Raanan Y. Yehezkel Rohekar, Guy Koren, Shami Nisimov, Gal Novik |
| Abstract | We introduce an unsupervised structure learning algorithm for deep, feed-forward, neural networks. We propose a new interpretation for depth and inter-layer connectivity where a hierarchy of independencies in the input distribution is encoded in the network structure. This results in structures allowing neurons to connect to neurons in any deeper layer skipping intermediate layers. Moreover, neurons in deeper layers encode low-order (small condition sets) independencies and have a wide scope of the input, whereas neurons in the first layers encode higher-order (larger condition sets) independencies and have a narrower scope. Thus, the depth of the network is automatically determined—equal to the maximal order of independence in the input distribution, which is the recursion-depth of the algorithm. The proposed algorithm constructs two main graphical models: 1) a generative latent graph (a deep belief network) learned from data and 2) a deep discriminative graph constructed from the generative latent graph. We prove that conditional dependencies between the nodes in the learned generative latent graph are preserved in the class-conditional discriminative graph. Finally, a deep neural network structure is constructed based on the discriminative graph. We demonstrate on image classification benchmarks that the algorithm replaces the deepest layers (convolutional and dense layers) of common convolutional networks, achieving high classification accuracy, while constructing significantly smaller structures. The proposed structure learning algorithm requires a small computational cost and runs efficiently on a standard desktop CPU. |
| Tasks | Image Classification |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ryjw_eAaZ |
| https://openreview.net/pdf?id=ryjw_eAaZ | |
| PWC | https://paperswithcode.com/paper/unsupervised-deep-structure-learning-by |
| Repo | |
| Framework | |
Building and Learning Structures in a Situated Blocks World Through Deep Language Understanding
| Title | Building and Learning Structures in a Situated Blocks World Through Deep Language Understanding |
| Authors | Ian Perera, James Allen, Choh Man Teng, Lucian Galescu |
| Abstract | We demonstrate a system for understanding natural language utterances for structure description and placement in a situated blocks world context. By relying on a rich, domain-specific adaptation of a generic ontology and a logical form structure produced by a semantic parser, we obviate the need for an intermediate, domain-specific representation and can produce a reasoner that grounds and reasons over concepts and constraints with real-valued data. This linguistic base enables more flexibility in interpreting natural language expressions invoking intrinsic concepts and features of structures and space. We demonstrate some of the capabilities of a system grounded in deep language understanding and present initial results in a structure learning task. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1402/ |
| https://www.aclweb.org/anthology/W18-1402 | |
| PWC | https://paperswithcode.com/paper/building-and-learning-structures-in-a |
| Repo | |
| Framework | |
“Seeing is Believing”: Pedestrian Trajectory Forecasting Using Visual Frustum of Attention
| Title | “Seeing is Believing”: Pedestrian Trajectory Forecasting Using Visual Frustum of Attention |
| Authors | Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Alessio Del Bue, Marco Cristani, Fabio Galasso |
| Abstract | In this paper we show the importance of the head pose estimation in the task of trajectory forecasting. This cue, when produced by an oracle and injected in a novel socially-based energy minimization approach, allows to get state-of-the-art performances on four different forecasting benchmarks, without relying on additional information such as expected destination and desired speed, which are supposed to be know beforehand for most of the current forecasting techniques. Our approach uses the head pose estimation for two aims: 1) to define a view frustum of attention, highlighting the people a given subject is more interested about, in order to avoid collisions; 2) to give a shorttime estimation of what would be the desired destination point. Moreover, we show that when the head pose estimation is given by a real detector, though the performance decreases, it still remains at the level of the top score forecasting systems |
| Tasks | Head Pose Estimation, Pose Estimation |
| Published | 2018-03-12 |
| URL | http://irtizahasan.com/ |
| http://irtizahasan.com/WACV_2018_Seeing_is_believing.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-is-believing-pedestrian-trajectory |
| Repo | |
| Framework | |
Neural Semantic Parsing
| Title | Neural Semantic Parsing |
| Authors | Matt Gardner, Pradeep Dasigi, Srinivasan Iyer, Alane Suhr, Luke Zettlemoyer |
| Abstract | Semantic parsing, the study of translating natural language utterances into machine-executable programs, is a well-established research area and has applications in question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically with the introduction of neural encoder-decoder methods that allow us to rethink many of the previous assumptions underlying semantic parsing. We aim to inform those already interested in semantic parsing research of these new developments in the field, as well as introduce the topic as an exciting research area to those who are unfamiliar with it. Current approaches for neural semantic parsing share several similarities with neural machine translation, but the key difference between the two fields is that semantic parsing translates natural language into a formal language, while machine translation translates it into a different natural language. The formal language used in semantic parsing allows for constrained decoding, where the model is constrained to only produce outputs that are valid formal statements. We will describe the various approaches researchers have taken to do this. We will also discuss the choice of formal languages used by semantic parsers, and describe why much recent work has chosen to use standard programming languages instead of more linguistically-motivated representations. We will then describe a particularly challenging setting for semantic parsing, where there is additional context or interaction that the parser must take into account when translating natural language to formal language, and give an overview of recent work in this direction. Finally, we will introduce some tools available in AllenNLP for doing semantic parsing research. |
| Tasks | Code Generation, Machine Translation, Question Answering, Semantic Parsing |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-5006/ |
| https://www.aclweb.org/anthology/P18-5006 | |
| PWC | https://paperswithcode.com/paper/neural-semantic-parsing |
| Repo | |
| Framework | |
Sentiment Expression Boundaries in Sentiment Polarity Classification
| Title | Sentiment Expression Boundaries in Sentiment Polarity Classification |
| Authors | Rasoul Kaljahi, Jennifer Foster |
| Abstract | We investigate the effect of using sentiment expression boundaries in predicting sentiment polarity in aspect-level sentiment analysis. We manually annotate a freely available English sentiment polarity dataset with these boundaries and carry out a series of experiments which demonstrate that high quality sentiment expressions can boost the performance of polarity classification. Our experiments with neural architectures also show that CNN networks outperform LSTMs on this task and dataset. |
| Tasks | Aspect-Based Sentiment Analysis, Multi-Task Learning, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6222/ |
| https://www.aclweb.org/anthology/W18-6222 | |
| PWC | https://paperswithcode.com/paper/sentiment-expression-boundaries-in-sentiment |
| Repo | |
| Framework | |
Super-Resolution and Sparse View CT Reconstruction
| Title | Super-Resolution and Sparse View CT Reconstruction |
| Authors | Guangming Zang, Mohamed Aly, Ramzi Idoughi, Peter Wonka, Wolfgang Heidrich |
| Abstract | We present a flexible framework for robust computed tomography (CT) reconstruction with a specific emphasis on recovering thin 1D and 2D manifolds embedded in 3D volumes. To reconstruct such structures at resolutions below the Nyquist limit of the CT image sensor, we devise a new 3D structure tensor prior, which can be incorporated as a regularizer into more traditional proximal optimization methods for CT reconstruction. As a second, smaller contribution, we also show that when using such a proximal reconstruction framework, it is beneficial to employ the Simultaneous Algebraic Reconstruction Technique (SART) instead of the commonly used Conjugate Gradient (CG) method in the solution of the data term proximal operator. We show empirically that CG often does not converge to the global optimum for tomography problem even though the underlying problem is convex. We demonstrate that using SART provides better reconstruction results in sparse-view settings using fewer projection images. We provide extensive experimental results for both contributions on both simulated and real data. Moreover, our code will also be made publicly available. |
| Tasks | Computed Tomography (CT), Super-Resolution |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Guangming_Zang_Super-Resolution_and_Sparse_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Guangming_Zang_Super-Resolution_and_Sparse_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/super-resolution-and-sparse-view-ct |
| Repo | |
| Framework | |
Visual Tracking via Spatially Aligned Correlation Filters Network
| Title | Visual Tracking via Spatially Aligned Correlation Filters Network |
| Authors | Mengdan Zhang, Qiang Wang, Junliang Xing, Jin Gao, Peixi Peng, Weiming Hu, Steve Maybank |
| Abstract | Correlation filters based trackers rely on a periodic assumption of the search sample to efficiently distinguish the target from the background. This assumption however yields undesired boundary effects and restricts aspect ratios of search samples. To handle these issues, an end-to-end deep architecture is proposed to incorporate geometric transformations into a correlation filters based network. This architecture introduces a novel spatial alignment module, which provides continuous feedback for transforming the target from the border to the center with a normalized aspect ratio. It enables correlation filters to work on well-aligned samples for better tracking. The whole architecture not only learns a generic relationship between object geometric transformations and object appearances, but also learns robust representations coupled to correlation filters in case of various geometric transformations. This lightweight architecture permits real-time speed. Experiments show our tracker effectively handles boundary effects and aspect ratio variations, achieving state-of-the-art tracking results on three benchmarks. |
| Tasks | Visual Tracking |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/mengdan_zhang_Visual_Tracking_via_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/mengdan_zhang_Visual_Tracking_via_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/visual-tracking-via-spatially-aligned |
| Repo | |
| Framework | |
A Corpus of Metaphor Novelty Scores for Syntactically-Related Word Pairs
| Title | A Corpus of Metaphor Novelty Scores for Syntactically-Related Word Pairs |
| Authors | Natalie Parde, Rodney Nielsen |
| Abstract | |
| Tasks | Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1243/ |
| https://www.aclweb.org/anthology/L18-1243 | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-metaphor-novelty-scores-for |
| Repo | |
| Framework | |
A Unified RvNN Framework for End-to-End Chinese Discourse Parsing
| Title | A Unified RvNN Framework for End-to-End Chinese Discourse Parsing |
| Authors | Lin Chuan-An, Hen-Hsen Huang, Zi-Yuan Chen, Hsin-Hsi Chen |
| Abstract | This paper demonstrates an end-to-end Chinese discourse parser. We propose a unified framework based on recursive neural network (RvNN) to jointly model the subtasks including elementary discourse unit (EDU) segmentation, tree structure construction, center labeling, and sense labeling. Experimental results show our parser achieves the state-of-the-art performance in the Chinese Discourse Treebank (CDTB) dataset. We release the source code with a pre-trained model for the NLP community. To the best of our knowledge, this is the first open source toolkit for Chinese discourse parsing. The standalone toolkit can be integrated into subsequent applications without the need of external resources such as syntactic parser. |
| Tasks | Information Retrieval, Text Categorization |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2016/ |
| https://www.aclweb.org/anthology/C18-2016 | |
| PWC | https://paperswithcode.com/paper/a-unified-rvnn-framework-for-end-to-end |
| Repo | |
| Framework | |
Deep State Space Models for Time Series Forecasting
| Title | Deep State Space Models for Time Series Forecasting |
| Authors | Syama Sundar Rangapuram, Matthias W. Seeger, Jan Gasthaus, Lorenzo Stella, Yuyang Wang, Tim Januschowski |
| Abstract | We present a novel approach to probabilistic time series forecasting that combines state space models with deep learning. By parametrizing a per-time-series linear state space model with a jointly-learned recurrent neural network, our method retains desired properties of state space models such as data efficiency and interpretability, while making use of the ability to learn complex patterns from raw data offered by deep learning approaches. Our method scales gracefully from regimes where little training data is available to regimes where data from millions of time series can be leveraged to learn accurate models. We provide qualitative as well as quantitative results with the proposed method, showing that it compares favorably to the state-of-the-art. |
| Tasks | Time Series, Time Series Forecasting |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8004-deep-state-space-models-for-time-series-forecasting |
| http://papers.nips.cc/paper/8004-deep-state-space-models-for-time-series-forecasting.pdf | |
| PWC | https://paperswithcode.com/paper/deep-state-space-models-for-time-series |
| Repo | |
| Framework | |
Learning Thematic Similarity Metric from Article Sections Using Triplet Networks
| Title | Learning Thematic Similarity Metric from Article Sections Using Triplet Networks |
| Authors | Liat Ein Dor, Yosi Mass, Alon Halfon, Elad Venezian, Ilya Shnayderman, Ranit Aharonov, Noam Slonim |
| Abstract | In this paper we suggest to leverage the partition of articles into sections, in order to learn thematic similarity metric between sentences. We assume that a sentence is thematically closer to sentences within its section than to sentences from other sections. Based on this assumption, we use Wikipedia articles to automatically create a large dataset of weakly labeled sentence triplets, composed of a pivot sentence, one sentence from the same section and one from another section. We train a triplet network to embed sentences from the same section closer. To test the performance of the learned embeddings, we create and release a sentence clustering benchmark. We show that the triplet network learns useful thematic metrics, that significantly outperform state-of-the-art semantic similarity methods and multipurpose embeddings on the task of thematic clustering of sentences. We also show that the learned embeddings perform well on the task of sentence semantic similarity prediction. |
| Tasks | Document Summarization, Multi-Document Summarization, Semantic Similarity, Semantic Textual Similarity, Text Clustering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2009/ |
| https://www.aclweb.org/anthology/P18-2009 | |
| PWC | https://paperswithcode.com/paper/learning-thematic-similarity-metric-from |
| Repo | |
| Framework | |
LSTM Hypertagging
| Title | LSTM Hypertagging |
| Authors | Reid Fu, Michael White |
| Abstract | Hypertagging, or supertagging for surface realization, is the process of assigning lexical categories to nodes in an input semantic graph. Previous work has shown that hypertagging significantly increases realization speed and quality by reducing the search space of the realizer. Building on recent work using LSTMs to improve accuracy on supertagging for parsing, we develop an LSTM hypertagging method for OpenCCG, an open source NLP toolkit for CCG. Our results show significant improvements in both hypertagging accuracy and downstream realization performance. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6528/ |
| https://www.aclweb.org/anthology/W18-6528 | |
| PWC | https://paperswithcode.com/paper/lstm-hypertagging |
| Repo | |
| Framework | |
