October 15, 2019

2378 words 12 mins read

Paper Group NANR 175

Paper Group NANR 175

NLP for Conversations: Sentiment, Summarization, and Group Dynamics. Lambda Twist: An Accurate Fast Robust Perspective Three Point (P3P) Solver. Object-centered image stitching. The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring. A Probabilistic Annotation Model for Crowdsourcing Coreference. A Hierarchical Model …

NLP for Conversations: Sentiment, Summarization, and Group Dynamics

Title NLP for Conversations: Sentiment, Summarization, and Group Dynamics
Authors Gabriel Murray, Giuseppe Carenini, Shafiq Joty
Abstract
Tasks Abstractive Text Summarization, Sentiment Analysis
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-3001/
PDF https://www.aclweb.org/anthology/C18-3001
PWC https://paperswithcode.com/paper/nlp-for-conversations-sentiment-summarization
Repo
Framework

Lambda Twist: An Accurate Fast Robust Perspective Three Point (P3P) Solver

Title Lambda Twist: An Accurate Fast Robust Perspective Three Point (P3P) Solver
Authors Mikael Persson, Klas Nordberg
Abstract We present Lambda Twist; a novel P3P solver which is accurate, fast and robust. Current state-of-the-art P3P solvers find all roots to a quartic and discard geometrically invalid and duplicate solutions in a post-processing step. Instead of solving a quartic, the proposed P3P solver exploits the underlying elliptic equations which can be solved by a fast and numerically accurate diagonalization. This diagonalization requires a single real root of a cubic which is then used to find the, up to four, P3P solutions. Unlike the direct quartic solvers our method never computes geometrically invalid or duplicate solutions. Extensive evaluation on synthetic data shows that the new solver has better numerical accuracy and is faster compared to the state-of-the-art P3P implementations. Implementation and benchmark are available on github.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Mikael_Persson_Lambda_Twist_An_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Mikael_Persson_Lambda_Twist_An_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/lambda-twist-an-accurate-fast-robust
Repo
Framework

Object-centered image stitching

Title Object-centered image stitching
Authors Charles Herrmann, Chen Wang, Richard Strong Bowen, Emil Keyder, Ramin Zabih
Abstract Image stitching is typically decomposed into three phases: registration, which aligns the source images with a common target image; seam finding, which determines for each target pixel the source image it should come from; and blending, which smooths transitions over the seams. As described in Szeliski’s tutorial on image stitching, the seam finding phase attempts to place seams between pixels where the transition between source images is not noticeable. Here, we observe that the most problematic failures of this approach occur when objects are cropped, omitted, or duplicated. We therefore take an object-centered approach to the problem, leveraging recent advances in object detection. We penalize candidate solutions with this class of error by modifying the energy function used in the seam finding stage. This produces substantially more realistic stitching results on challenging imagery. In addition, these methods can be used to determine when there is non-recoverable occlusion in the input data, and also suggest a simple evaluation metric that can be used to evaluate the output of stitching algorithms.
Tasks Image Stitching, Object Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Charles_Herrmann_Object-centered_image_stitching_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Charles_Herrmann_Object-centered_image_stitching_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/object-centered-image-stitching
Repo
Framework

The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring

Title The SUMMA Platform: A Scalable Infrastructure for Multi-lingual Multi-media Monitoring
Authors Ulrich Germann, Ren{=a}rs Liepins, Guntis Barzdins, Didzis Gosko, Mir, Sebasti{~a}o a, David Nogueira
Abstract The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes. The Platform offers a fully automated media ingestion pipeline capable of recording live broadcasts, detection and transcription of spoken content, translation of all text (original or transcribed) into English, recognition and linking of Named Entities, topic detection, clustering and cross-lingual multi-document summarization of related media items, and last but not least, extraction and storage of factual claims in these news items. Browser-based graphical user interfaces provide humans with aggregated information as well as structured access to individual news items stored in the Platform{'}s database. This paper describes the intended use cases and provides an overview over the system{'}s implementation.
Tasks Document Summarization, Multi-Document Summarization
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-4017/
PDF https://www.aclweb.org/anthology/P18-4017
PWC https://paperswithcode.com/paper/the-summa-platform-a-scalable-infrastructure
Repo
Framework

A Probabilistic Annotation Model for Crowdsourcing Coreference

Title A Probabilistic Annotation Model for Crowdsourcing Coreference
Authors Silviu Paun, Jon Chamberlain, Udo Kruschwitz, Juntao Yu, Massimo Poesio
Abstract The availability of large scale annotated corpora for coreference is essential to the development of the field. However, creating resources at the required scale via expert annotation would be too expensive. Crowdsourcing has been proposed as an alternative; but this approach has not been widely used for coreference. This paper addresses one crucial hurdle on the way to make this possible, by introducing a new model of annotation for aggregating crowdsourced anaphoric annotations. The model is evaluated along three dimensions: the accuracy of the inferred mention pairs, the quality of the post-hoc constructed silver chains, and the viability of using the silver chains as an alternative to the expert-annotated chains in training a state of the art coreference system. The results suggest that our model can extract from crowdsourced annotations coreference chains of comparable quality to those obtained with expert annotation.
Tasks Coreference Resolution, Question Answering
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1218/
PDF https://www.aclweb.org/anthology/D18-1218
PWC https://paperswithcode.com/paper/a-probabilistic-annotation-model-for
Repo
Framework

A Hierarchical Model for Device Placement

Title A Hierarchical Model for Device Placement
Authors Azalia Mirhoseini, Anna Goldie, Hieu Pham, Benoit Steiner, Quoc V. Le, Jeff Dean
Abstract We introduce a hierarchical model for efficient placement of computational graphs onto hardware devices, especially in heterogeneous environments with a mixture of CPUs, GPUs, and other computational devices. Our method learns to assign graph operations to groups and to allocate those groups to available devices. The grouping and device allocations are learned jointly. The proposed method is trained with policy gradient and requires no human intervention. Experiments with widely-used computer vision and natural language models show that our algorithm can find optimized, non-trivial placements for TensorFlow computational graphs with over 80,000 operations. In addition, our approach outperforms placements by human experts as well as a previous state-of-the-art placement method based on deep reinforcement learning. Our method achieves runtime reductions of up to 60.6% per training step when applied to models such as Neural Machine Translation.
Tasks Machine Translation
Published 2018-01-01
URL https://openreview.net/forum?id=Hkc-TeZ0W
PDF https://openreview.net/pdf?id=Hkc-TeZ0W
PWC https://paperswithcode.com/paper/a-hierarchical-model-for-device-placement
Repo
Framework

Structured Dialogue Policy with Graph Neural Networks

Title Structured Dialogue Policy with Graph Neural Networks
Authors Lu Chen, Bowen Tan, Sishan Long, Kai Yu
Abstract Recently, deep reinforcement learning (DRL) has been used for dialogue policy optimization. However, many DRL-based policies are not sample-efficient. Most recent advances focus on improving DRL optimization algorithms to address this issue. Here, we take an alternative route of designing neural network structure that is better suited for DRL-based dialogue management. The proposed structured deep reinforcement learning is based on graph neural networks (GNN), which consists of some sub-networks, each one for a node on a directed graph. The graph is defined according to the domain ontology and each node can be considered as a sub-agent. During decision making, these sub-agents have internal message exchange between neighbors on the graph. We also propose an approach to jointly optimize the graph structure as well as the parameters of GNN. Experiments show that structured DRL significantly outperforms previous state-of-the-art approaches in almost all of the 18 tasks of the PyDial benchmark.
Tasks Decision Making, Dialogue Management, Speech Recognition, Spoken Language Understanding
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1107/
PDF https://www.aclweb.org/anthology/C18-1107
PWC https://paperswithcode.com/paper/structured-dialogue-policy-with-graph-neural
Repo
Framework

Adaptive Knowledge Sharing in Multi-Task Learning: Improving Low-Resource Neural Machine Translation

Title Adaptive Knowledge Sharing in Multi-Task Learning: Improving Low-Resource Neural Machine Translation
Authors Poorya Zaremoodi, Wray Buntine, Gholamreza Haffari
Abstract Neural Machine Translation (NMT) is notorious for its need for large amounts of bilingual data. An effective approach to compensate for this requirement is Multi-Task Learning (MTL) to leverage different linguistic resources as a source of inductive bias. Current MTL architectures are based on the Seq2Seq transduction, and (partially) share different components of the models among the tasks. However, this MTL approach often suffers from task interference and is not able to fully capture commonalities among subsets of tasks. We address this issue by extending the recurrent units with multiple {}blocks{''} along with a trainable {}routing network{''}. The routing network enables adaptive collaboration by dynamic sharing of blocks conditioned on the task at hand, input, and model state. Empirical evaluation of two low-resource translation tasks, English to Vietnamese and Farsi, show +1 BLEU score improvements compared to strong baselines.
Tasks Low-Resource Neural Machine Translation, Machine Translation, Multi-Task Learning
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-2104/
PDF https://www.aclweb.org/anthology/P18-2104
PWC https://paperswithcode.com/paper/adaptive-knowledge-sharing-in-multi-task
Repo
Framework

DERE: A Task and Domain-Independent Slot Filling Framework for Declarative Relation Extraction

Title DERE: A Task and Domain-Independent Slot Filling Framework for Declarative Relation Extraction
Authors Heike Adel, Laura Ana Maria Bostan, Sean Papay, Sebastian Pad{'o}, Roman Klinger
Abstract Most machine learning systems for natural language processing are tailored to specific tasks. As a result, comparability of models across tasks is missing and their applicability to new tasks is limited. This affects end users without machine learning experience as well as model developers. To address these limitations, we present DERE, a novel framework for declarative specification and compilation of template-based information extraction. It uses a generic specification language for the task and for data annotations in terms of spans and frames. This formalism enables the representation of a large variety of natural language processing challenges. The backend can be instantiated by different models, following different paradigms. The clear separation of frame specification and model backend will ease the implementation of new models and the evaluation of different models across different tasks. Furthermore, it simplifies transfer learning, joint learning across tasks and/or domains as well as the assessment of model generalizability. DERE is available as open-source software.
Tasks Relation Extraction, Semantic Role Labeling, Sentiment Analysis, Slot Filling, Transfer Learning
Published 2018-11-01
URL https://www.aclweb.org/anthology/D18-2008/
PDF https://www.aclweb.org/anthology/D18-2008
PWC https://paperswithcode.com/paper/dere-a-task-and-domain-independent-slot
Repo
Framework

WordNet Embeddings

Title WordNet Embeddings
Authors Chakaveh Saedi, Ant{'o}nio Branco, Jo{~a}o Ant{'o}nio Rodrigues, Jo{~a}o Silva
Abstract Semantic networks and semantic spaces have been two prominent approaches to represent lexical semantics. While a unified account of the lexical meaning relies on one being able to convert between these representations, in both directions, the conversion direction from semantic networks into semantic spaces started to attract more attention recently. In this paper we present a methodology for this conversion and assess it with a case study. When it is applied over WordNet, the performance of the resulting embeddings in a mainstream semantic similarity task is very good, substantially superior to the performance of word embeddings based on very large collections of texts like word2vec.
Tasks Representation Learning, Semantic Similarity, Semantic Textual Similarity, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3016/
PDF https://www.aclweb.org/anthology/W18-3016
PWC https://paperswithcode.com/paper/wordnet-embeddings
Repo
Framework

Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes

Title Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes
Authors Weihong Ren, Di Kang, Yandong Tang, Antoni B. Chan
Abstract While people tracking has been greatly improved over the recent years, crowd scenes remain particularly challenging for people tracking due to heavy occlusions, high crowd density, and significant appearance variation. To address these challenges, we first design a Sparse Kernelized Correlation Filter (S-KCF) to suppress target response variations caused by occlusions and illumination changes, and spurious responses due to similar distractor objects. We then propose a people tracking framework that fuses the S-KCF response map with an estimated crowd density map using a convolutional neural network (CNN), yielding a refined response map. To train the fusion CNN, we propose a two-stage strategy to gradually optimize the parameters. The first stage is to train a preliminary model in batch mode with image patches selected around the targets, and the second stage is to fine-tune the preliminary model using the real frame-by-frame tracking process. Our density fusion framework can significantly improves people tracking in crowd scenes, and can also be combined with other trackers to improve the tracking performance. We validate our framework on two crowd video datasets: UCSD and PETS2009.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Ren_Fusing_Crowd_Density_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Ren_Fusing_Crowd_Density_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/fusing-crowd-density-maps-and-visual-object
Repo
Framework

SUD or Surface-Syntactic Universal Dependencies: An annotation scheme near-isomorphic to UD

Title SUD or Surface-Syntactic Universal Dependencies: An annotation scheme near-isomorphic to UD
Authors Kim Gerdes, Bruno Guillaume, Sylvain Kahane, Guy Perrier
Abstract This article proposes a surface-syntactic annotation scheme called SUD that is near-isomorphic to the Universal Dependencies (UD) annotation scheme while following distributional criteria for defining the dependency tree structure and the naming of the syntactic functions. Rule-based graph transformation grammars allow for a bi-directional transformation of UD into SUD. The back-and-forth transformation can serve as an error-mining tool to assure the intra-language and inter-language coherence of the UD treebanks.
Tasks
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6008/
PDF https://www.aclweb.org/anthology/W18-6008
PWC https://paperswithcode.com/paper/sud-or-surface-syntactic-universal
Repo
Framework

Image Reassembly Combining Deep Learning and Shortest Path Problem

Title Image Reassembly Combining Deep Learning and Shortest Path Problem
Authors Marie-Morgane Paumard, David Picard, Hedi Tabia
Abstract This paper addresses the problem of reassembling images from disjointed fragments. More specifically, given an unordered set of fragments, we aim at reassembling one or several possibly incomplete images. The main contributions of this work are: 1) several deep neural architectures to predict the relative position of image fragments that outperform the previous state of the art; 2) casting the reassembly problem into the shortest path in a graph problem for which we provide several construction algorithms depending on available information; 3) a new dataset of images taken from the Metropolitan Museum of Art (MET) dedicated to image reassembly for which we provide a clear setup and a strong baseline.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Marie-Morgane_Paumard_Image_Reassembly_Combining_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Marie-Morgane_Paumard_Image_Reassembly_Combining_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/image-reassembly-combining-deep-learning-and-1
Repo
Framework

Diminishing Returns Shape Constraints for Interpretability and Regularization

Title Diminishing Returns Shape Constraints for Interpretability and Regularization
Authors Maya Gupta, Dara Bahri, Andrew Cotter, Kevin Canini
Abstract We investigate machine learning models that can provide diminishing returns and accelerating returns guarantees to capture prior knowledge or policies about how outputs should depend on inputs. We show that one can build flexible, nonlinear, multi-dimensional models using lattice functions with any combination of concavity/convexity and monotonicity constraints on any subsets of features, and compare to new shape-constrained neural networks. We demonstrate on real-world examples that these shape constrained models can provide tuning-free regularization and improve model understandability.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7916-diminishing-returns-shape-constraints-for-interpretability-and-regularization
PDF http://papers.nips.cc/paper/7916-diminishing-returns-shape-constraints-for-interpretability-and-regularization.pdf
PWC https://paperswithcode.com/paper/diminishing-returns-shape-constraints-for
Repo
Framework

PyRATA, Python Rule-based feAture sTructure Analysis

Title PyRATA, Python Rule-based feAture sTructure Analysis
Authors Hern, Nicolas ez, Amir Hazem
Abstract
Tasks Feature Engineering
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1330/
PDF https://www.aclweb.org/anthology/L18-1330
PWC https://paperswithcode.com/paper/pyrata-python-rule-based-feature-structure
Repo
Framework
comments powered by Disqus