Paper Group NANR 5
A Linguistically-Informed Search Engine to Identifiy Reading Material for Functional Illiteracy Classes. Hyperedge2vec: Distributed Representations for Hyperedges. Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane. Convergence rate of sign stochastic gradient descent for non-convex functions. The Boarnster …
A Linguistically-Informed Search Engine to Identifiy Reading Material for Functional Illiteracy Classes
| Title | A Linguistically-Informed Search Engine to Identifiy Reading Material for Functional Illiteracy Classes |
| Authors | Zarah Weiss, Sabrina Dittrich, Detmar Meurers |
| Abstract | |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-7109/ |
| https://www.aclweb.org/anthology/W18-7109 | |
| PWC | https://paperswithcode.com/paper/a-linguistically-informed-search-engine-to |
| Repo | |
| Framework | |
Hyperedge2vec: Distributed Representations for Hyperedges
| Title | Hyperedge2vec: Distributed Representations for Hyperedges |
| Authors | Ankit Sharma, Shafiq Joty, Himanshu Kharkwal, Jaideep Srivastava |
| Abstract | Data structured in form of overlapping or non-overlapping sets is found in a variety of domains, sometimes explicitly but often subtly. For example, teams, which are of prime importance in social science studies are \enquote{sets of individuals}; \enquote{item sets} in pattern mining are sets; and for various types of analysis in language studies a sentence can be considered as a \enquote{set or bag of words}. Although building models and inference algorithms for structured data has been an important task in the fields of machine learning and statistics, research on \enquote{set-like} data still remains less explored. Relationships between pairs of elements can be modeled as edges in a graph. However, modeling relationships that involve all members of a set, a hyperedge is a more natural representation for the set. In this work, we focus on the problem of embedding hyperedges in a hypergraph (a network of overlapping sets) to a low dimensional vector space. We propose a probabilistic deep-learning based method as well as a tensor-based algebraic model, both of which capture the hypergraph structure in a principled manner without loosing set-level information. Our central focus is to highlight the connection between hypergraphs (topology), tensors (algebra) and probabilistic models. We present a number of interesting baselines, some of which adapt existing node-level embedding models to the hyperedge-level, as well as sequence based language techniques which are adapted for set structured hypergraph topology. The performance is evaluated with a network of social groups and a network of word phrases. Our experiments show that accuracy wise our methods perform similar to those of baselines which are not designed for hypergraphs. Moreover, our tensor based method is quiet efficient as compared to deep-learning based auto-encoder method. We therefore, argue that we have proposed more general methods which are suited for hypergraphs (and therefore also for graphs) while maintaining accuracy and efficiency. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJ5C67-C- |
| https://openreview.net/pdf?id=rJ5C67-C- | |
| PWC | https://paperswithcode.com/paper/hyperedge2vec-distributed-representations-for |
| Repo | |
| Framework | |
Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane
| Title | Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane |
| Authors | Hao Cheng, Dongze Lian, Shenghua Gao, Yanlin Geng |
| Abstract | Inspired by the pioneering work of information bottleneck principle for Deep Neural Networks (DNNs) analysis, we design an information plane based framework to evaluate the capability of DNNs for image classification tasks, which not only helps understand the capability of DNNs, but also helps us choose a neural network which leads to higher classification accuracy more efficiently. Further, with experiments, the relationship among the model accuracy, I(X;T) and I(T;Y) are analyzed, where I(X;T) and I(T;Y) are the mutual information of DNN’s output T with input X and label Y. We also show the information plane is more informative than loss curve and apply mutual information to infer the model’s capability for recognizing objects of each class. Our studies would facilitate a better understanding of DNNs. |
| Tasks | Image Classification |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Hao_Cheng_Evaluating_Capability_of_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Hao_Cheng_Evaluating_Capability_of_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-capability-of-deep-neural-networks |
| Repo | |
| Framework | |
Convergence rate of sign stochastic gradient descent for non-convex functions
| Title | Convergence rate of sign stochastic gradient descent for non-convex functions |
| Authors | Jeremy Bernstein, Kamyar Azizzadenesheli, Yu-Xiang Wang, Anima Anandkumar |
| Abstract | The sign stochastic gradient descent method (signSGD) utilizes only the sign of the stochastic gradient in its updates. Since signSGD carries out one-bit quantization of the gradients, it is extremely practical for distributed optimization where gradients need to be aggregated from different processors. For the first time, we establish convergence rates for signSGD on general non-convex functions under transparent conditions. We show that the rate of signSGD to reach first-order critical points matches that of SGD in terms of number of stochastic gradient calls, up to roughly a linear factor in the dimension. We carry out simple experiments to explore the behaviour of sign gradient descent (without the stochasticity) close to saddle points and show that it often helps completely avoid them without using either stochasticity or curvature information. |
| Tasks | Distributed Optimization, Quantization |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HyxjwgbRZ |
| https://openreview.net/pdf?id=HyxjwgbRZ | |
| PWC | https://paperswithcode.com/paper/convergence-rate-of-sign-stochastic-gradient |
| Repo | |
| Framework | |
The Boarnsterhim Corpus: A Bilingual Frisian-Dutch Panel and Trend Study
| Title | The Boarnsterhim Corpus: A Bilingual Frisian-Dutch Panel and Trend Study |
| Authors | Marjoleine Sloos, Eduard Drenth, Wilbert Heeringa |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1232/ |
| https://www.aclweb.org/anthology/L18-1232 | |
| PWC | https://paperswithcode.com/paper/the-boarnsterhim-corpus-a-bilingual-frisian |
| Repo | |
| Framework | |
Arabic Dialect Identification in the Context of Bivalency and Code-Switching
| Title | Arabic Dialect Identification in the Context of Bivalency and Code-Switching |
| Authors | Mahmoud El-Haj, Paul Rayson, Mariam Aboelezz |
| Abstract | |
| Tasks | Language Identification, Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1573/ |
| https://www.aclweb.org/anthology/L18-1573 | |
| PWC | https://paperswithcode.com/paper/arabic-dialect-identification-in-the-context |
| Repo | |
| Framework | |
Occlusion-Aware Rolling Shutter Rectification of 3D Scenes
| Title | Occlusion-Aware Rolling Shutter Rectification of 3D Scenes |
| Authors | Subeesh Vasu, Mahesh Mohan M. R., A. N. Rajagopalan |
| Abstract | A vast majority of contemporary cameras employ rolling shutter (RS) mechanism to capture images. Due to the sequential mechanism, images acquired with a moving camera are subjected to rolling shutter effect which manifests as geometric distortions. In this work, we consider the specific scenario of a fast moving camera wherein the rolling shutter distortions not only are predominant but also become depth-dependent which in turn results in intra-frame occlusions. To this end, we develop a first-of-its-kind pipeline to recover the latent image of a 3D scene from a set of such RS distorted images. The proposed approach sequentially recovers both the camera motion and scene structure while accounting for RS and occlusion effects. Subsequently, we perform depth and occlusion-aware rectification of RS images to yield the desired latent image. Our experiments on synthetic and real image sequences reveal that the proposed approach achieves state-of-the-art results. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Vasu_Occlusion-Aware_Rolling_Shutter_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Vasu_Occlusion-Aware_Rolling_Shutter_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/occlusion-aware-rolling-shutter-rectification |
| Repo | |
| Framework | |
Bringing Order to Chaos: A Non-Sequential Approach for Browsing Large Sets of Found Audio Data
| Title | Bringing Order to Chaos: A Non-Sequential Approach for Browsing Large Sets of Found Audio Data |
| Authors | Per Fallgren, Zofia Malisz, Jens Edlund |
| Abstract | |
| Tasks | Dimensionality Reduction |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1680/ |
| https://www.aclweb.org/anthology/L18-1680 | |
| PWC | https://paperswithcode.com/paper/bringing-order-to-chaos-a-non-sequential |
| Repo | |
| Framework | |
A Pragmatic Approach for Classical Chinese Word Segmentation
| Title | A Pragmatic Approach for Classical Chinese Word Segmentation |
| Authors | Shilei Huang, Jiangqin Wu |
| Abstract | |
| Tasks | Chinese Word Segmentation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1186/ |
| https://www.aclweb.org/anthology/L18-1186 | |
| PWC | https://paperswithcode.com/paper/a-pragmatic-approach-for-classical-chinese |
| Repo | |
| Framework | |
Treatment Side Effect Prediction from Online User-generated Content
| Title | Treatment Side Effect Prediction from Online User-generated Content |
| Authors | Van Hoang Nguyen, Kazunari Sugiyama, Min-Yen Kan, Kishaloy Halder |
| Abstract | With Health 2.0, patients and caregivers increasingly seek information regarding possible drug side effects during their medical treatments in online health communities. These are helpful platforms for non-professional medical opinions, yet pose risk of being unreliable in quality and insufficient in quantity to cover the wide range of potential drug reactions. Existing approaches which analyze such user-generated content in online forums heavily rely on feature engineering of both documents and users, and often overlook the relationships between posts within a common discussion thread. Inspired by recent advancements, we propose a neural architecture that models the textual content of user-generated documents and user experiences in online communities to predict side effects during treatment. Experimental results show that our proposed architecture outperforms baseline models. |
| Tasks | Feature Engineering |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5602/ |
| https://www.aclweb.org/anthology/W18-5602 | |
| PWC | https://paperswithcode.com/paper/treatment-side-effect-prediction-from-online |
| Repo | |
| Framework | |
Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction
| Title | Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction |
| Authors | Chen Lin, Timothy Miller, Dmitriy Dligach, Hadi Amiri, Steven Bethard, Guergana Savova |
| Abstract | Neural network models are oftentimes restricted by limited labeled instances and resort to advanced architectures and features for cutting edge performance. We propose to build a recurrent neural network with multiple semantically heterogeneous embeddings within a self-training framework. Our framework makes use of labeled, unlabeled, and social media data, operates on basic features, and is scalable and generalizable. With this method, we establish the state-of-the-art result for both in- and cross-domain for a clinical temporal relation extraction task. |
| Tasks | Feature Engineering, Machine Translation, Question Answering, Relation Extraction, Speech Recognition, Temporal Information Extraction, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5619/ |
| https://www.aclweb.org/anthology/W18-5619 | |
| PWC | https://paperswithcode.com/paper/self-training-improves-recurrent-neural |
| Repo | |
| Framework | |
SMILEE: Symmetric Multi-modal Interactions with Language-gesture Enabled (AI) Embodiment
| Title | SMILEE: Symmetric Multi-modal Interactions with Language-gesture Enabled (AI) Embodiment |
| Authors | Sujeong Kim, David Salter, Luke DeLuccia, Kilho Son, Mohamed R. Amer, Amir Tamrakar |
| Abstract | We demonstrate an intelligent conversational agent system designed for advancing human-machine collaborative tasks. The agent is able to interpret a user{'}s communicative intent from both their verbal utterances and non-verbal behaviors, such as gestures. The agent is also itself able to communicate both with natural language and gestures, through its embodiment as an avatar thus facilitating natural symmetric multi-modal interactions. We demonstrate two intelligent agents with specialized skills in the Blocks World as use-cases of our system. |
| Tasks | Speech Recognition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-5018/ |
| https://www.aclweb.org/anthology/N18-5018 | |
| PWC | https://paperswithcode.com/paper/smilee-symmetric-multi-modal-interactions |
| Repo | |
| Framework | |
Predictive Approximate Bayesian Computation via Saddle Points
| Title | Predictive Approximate Bayesian Computation via Saddle Points |
| Authors | Yingxiang Yang, Bo Dai, Negar Kiyavash, Niao He |
| Abstract | Approximate Bayesian computation (ABC) is an important methodology for Bayesian inference when the likelihood function is intractable. Sampling-based ABC algorithms such as rejection- and K2-ABC are inefficient when the parameters have high dimensions, while the regression-based algorithms such as K- and DR-ABC are hard to scale. In this paper, we introduce an optimization-based ABC framework that addresses these deficiencies. Leveraging a generative model for posterior and joint distribution matching, we show that ABC can be framed as saddle point problems, whose objectives can be accessed directly with samples. We present the predictive ABC algorithm (P-ABC), and provide a probabilistically approximately correct (PAC) bound that guarantees its learning consistency. Numerical experiment shows that P-ABC outperforms both K2- and DR-ABC significantly. |
| Tasks | Bayesian Inference |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8228-predictive-approximate-bayesian-computation-via-saddle-points |
| http://papers.nips.cc/paper/8228-predictive-approximate-bayesian-computation-via-saddle-points.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-approximate-bayesian-computation |
| Repo | |
| Framework | |
Identifying Domain Independent Update Intents in Task Based Dialogs
| Title | Identifying Domain Independent Update Intents in Task Based Dialogs |
| Authors | Prakhar Biyani, Cem Akkaya, Kostas Tsioutsiouliklis |
| Abstract | One important problem in task-based conversations is that of effectively updating the belief estimates of user-mentioned slot-value pairs. Given a user utterance, the intent of a slot-value pair is captured using dialog acts (DA) expressed in that utterance. However, in certain cases, DA{'}s fail to capture the actual update intent of the user. In this paper, we describe such cases and propose a new type of semantic class for user intents. This new type, Update Intents (UI), is directly related to the type of update a user intends to perform for a slot-value pair. We define five types of UI{'}s, which are independent of the domain of the conversation. We build a multi-class classification model using LSTM{'}s to identify the type of UI in user utterances in the Restaurant and Shopping domains. Experimental results show that our models achieve strong classification performance in terms of F-1 score. |
| Tasks | Spoken Language Understanding |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5049/ |
| https://www.aclweb.org/anthology/W18-5049 | |
| PWC | https://paperswithcode.com/paper/identifying-domain-independent-update-intents |
| Repo | |
| Framework | |
Feasible Annotation Scheme for Capturing Policy Argument Reasoning using Argument Templates
| Title | Feasible Annotation Scheme for Capturing Policy Argument Reasoning using Argument Templates |
| Authors | Paul Reisert, Naoya Inoue, Tatsuki Kuribayashi, Kentaro Inui |
| Abstract | Most of the existing works on argument mining cast the problem of argumentative structure identification as classification tasks (e.g. attack-support relations, stance, explicit premise/claim). This paper goes a step further by addressing the task of automatically identifying reasoning patterns of arguments using predefined templates, which is called \textit{argument template (AT) instantiation}. The contributions of this work are three-fold. First, we develop a simple, yet expressive set of easily annotatable ATs that can represent a majority of writer{'}s reasoning for texts with diverse policy topics while maintaining the computational feasibility of the task. Second, we create a small, but highly reliable annotated corpus of instantiated ATs on top of reliably annotated support and attack relations and conduct an annotation study. Third, we formulate the task of AT instantiation as structured prediction constrained by a feasible set of templates. Our evaluation demonstrates that we can annotate ATs with a reasonably high inter-annotator agreement, and the use of template-constrained inference is useful for instantiating ATs with only partial reasoning comprehension clues. |
| Tasks | Argument Mining, Document Summarization, Structured Prediction |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5210/ |
| https://www.aclweb.org/anthology/W18-5210 | |
| PWC | https://paperswithcode.com/paper/feasible-annotation-scheme-for-capturing |
| Repo | |
| Framework | |
