Paper Group NANR 268
Evaluating Composition Models for Verb Phrase Elliptical Sentence Embeddings. Two Discourse Tree - Based Approaches to Indexing Answers. DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German. Using Unknown Occluders to Recover Hidden Scenes. Self-Supervised Neural Machine Translation. Neural Network-based Models w …
Evaluating Composition Models for Verb Phrase Elliptical Sentence Embeddings
| Title | Evaluating Composition Models for Verb Phrase Elliptical Sentence Embeddings |
| Authors | Gijs Wijnholds, Mehrnoosh Sadrzadeh |
| Abstract | Ellipsis is a natural language phenomenon where part of a sentence is missing and its information must be recovered from its surrounding context, as in {``}Cats chase dogs and so do foxes.{''}. Formal semantics has different methods for resolving ellipsis and recovering the missing information, but the problem has not been considered for distributional semantics, where words have vector embeddings and combinations thereof provide embeddings for sentences. In elliptical sentences these combinations go beyond linear as copying of elided information is necessary. In this paper, we develop different models for embedding VP-elliptical sentences. We extend existing verb disambiguation and sentence similarity datasets to ones containing elliptical phrases and evaluate our models on these datasets for a variety of non-linear combinations and their linear counterparts. We compare results of these compositional models to state of the art holistic sentence encoders. Our results show that non-linear addition and a non-linear tensor-based composition outperform the naive non-compositional baselines and the linear models, and that sentence encoders perform well on sentence similarity, but not on verb disambiguation. | |
| Tasks | Sentence Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1023/ |
| https://www.aclweb.org/anthology/N19-1023 | |
| PWC | https://paperswithcode.com/paper/evaluating-composition-models-for-verb-phrase |
| Repo | |
| Framework | |
Two Discourse Tree - Based Approaches to Indexing Answers
| Title | Two Discourse Tree - Based Approaches to Indexing Answers |
| Authors | Boris Galitsky, Dmitry Ilvovsky |
| Abstract | We explore anatomy of answers with respect to which text fragments from an answer are worth matching with a question and which should not be matched. We apply the Rhetorical Structure Theory to build a discourse tree of an answer and select elementary discourse units that are suitable for indexing. Manual rules for selection of these discourse units as well as automated classification based on web search engine mining are evaluated con-cerning improving search accuracy. We form two sets of question-answer pairs for FAQ and community QA search domains and use them for evaluation of the proposed indexing methodology, which delivers up to 16 percent improvement in search recall. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1043/ |
| https://www.aclweb.org/anthology/R19-1043 | |
| PWC | https://paperswithcode.com/paper/two-discourse-tree-based-approaches-to |
| Repo | |
| Framework | |
DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German
| Title | DisSim: A Discourse-Aware Syntactic Text Simplification Framework for English and German |
| Authors | Christina Niklaus, Matthias Cetto, Andr{'e} Freitas, H, Siegfried schuh |
| Abstract | We introduce DisSim, a discourse-aware sentence splitting framework for English and German whose goal is to transform syntactically complex sentences into an intermediate representation that presents a simple and more regular structure which is easier to process for downstream semantic applications. For this purpose, we turn input sentences into a two-layered semantic hierarchy in the form of core facts and accompanying contexts, while identifying the rhetorical relations that hold between them. In that way, we preserve the coherence structure of the input and, hence, its interpretability for downstream tasks. |
| Tasks | Text Simplification |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8662/ |
| https://www.aclweb.org/anthology/W19-8662 | |
| PWC | https://paperswithcode.com/paper/dissim-a-discourse-aware-syntactic-text-1 |
| Repo | |
| Framework | |
Using Unknown Occluders to Recover Hidden Scenes
| Title | Using Unknown Occluders to Recover Hidden Scenes |
| Authors | Adam B. Yedidia, Manel Baradad, Christos Thrampoulidis, William T. Freeman, Gregory W. Wornell |
| Abstract | We consider the challenging problem of inferring a hidden moving scene from faint shadows cast on a diffuse surface. Recent work in passive non-line-of-sight (NLoS) imaging has shown that the presence of occluding objects in between the scene and the diffuse surface significantly improves the conditioning of the problem. However, that work assumes that the shape of the occluder is known a priori. In this paper, we relax this often impractical assumption, extending the range of applications for passive occluder-based NLoS imaging systems. We formulate the task of jointly recovering the unknown scene and unknown occluder as a blind deconvolution problem, for which we propose a simple but effective two-step algorithm. At the first step, the algorithm exploits motion in the scene in order to obtain an estimate of the occluder. In particular, it exploits the fact that motion in realistic scenes is typically sparse. The second step is more standard: using regularization, we deconvolve by the occluder estimate to solve for the hidden scene. We demonstrate the effectiveness of our method with simulations and experiments in a variety of settings. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yedidia_Using_Unknown_Occluders_to_Recover_Hidden_Scenes_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Yedidia_Using_Unknown_Occluders_to_Recover_Hidden_Scenes_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/using-unknown-occluders-to-recover-hidden |
| Repo | |
| Framework | |
Self-Supervised Neural Machine Translation
| Title | Self-Supervised Neural Machine Translation |
| Authors | Dana Ruiter, Cristina Espa{~n}a-Bonet, Josef van Genabith |
| Abstract | We present a simple new method where an emergent NMT system is used for simultaneously selecting training data and learning internal NMT representations. This is done in a self-supervised way without parallel data, in such a way that both tasks enhance each other during training. The method is language independent, introduces no additional hyper-parameters, and achieves BLEU scores of 29.21 (en2fr) and 27.36 (fr2en) on newstest2014 using English and French Wikipedia data for training. |
| Tasks | Machine Translation |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1178/ |
| https://www.aclweb.org/anthology/P19-1178 | |
| PWC | https://paperswithcode.com/paper/self-supervised-neural-machine-translation |
| Repo | |
| Framework | |
Neural Network-based Models with Commonsense Knowledge for Machine Reading Comprehension
| Title | Neural Network-based Models with Commonsense Knowledge for Machine Reading Comprehension |
| Authors | Denis Smirnov |
| Abstract | State-of-the-art machine reading comprehension models are capable of producing answers for factual questions about a given piece of text. However, some type of questions requires commonsense knowledge which cannot be inferred from the given text passage. Thus, external semantic information could enhance the performance of these models. This PhD research proposal provides a brief overview of some existing machine reading comprehension datasets and models and outlines possible ways of their improvement. |
| Tasks | Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2014/ |
| https://www.aclweb.org/anthology/R19-2014 | |
| PWC | https://paperswithcode.com/paper/neural-network-based-models-with-commonsense |
| Repo | |
| Framework | |
Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning
| Title | Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning |
| Authors | Akihiro Kishimoto, Beat Buesser, Bei Chen, Adi Botea |
| Abstract | Search techniques, such as Monte Carlo Tree Search (MCTS) and Proof-Number Search (PNS), are effective in playing and solving games. However, the understanding of their performance in industrial applications is still limited. We investigate MCTS and Depth-First Proof-Number (DFPN) Search, a PNS variant, in the domain of Retrosynthetic Analysis (RA). We find that DFPN’s strengths, that justify its success in games, have limited value in RA, and that an enhanced MCTS variant by Segler et al. significantly outperforms DFPN. We address this disadvantage of DFPN in RA with a novel approach to combine DFPN with Heuristic Edge Initialization. Our new search algorithm DFPN-E outperforms the enhanced MCTS in search time by a factor of 3 on average, with comparable success rates. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8943-depth-first-proof-number-search-with-heuristic-edge-cost-and-application-to-chemical-synthesis-planning |
| http://papers.nips.cc/paper/8943-depth-first-proof-number-search-with-heuristic-edge-cost-and-application-to-chemical-synthesis-planning.pdf | |
| PWC | https://paperswithcode.com/paper/depth-first-proof-number-search-with |
| Repo | |
| Framework | |
A Novel Hybrid Sequential Model for Review-based Rating Prediction
| Title | A Novel Hybrid Sequential Model for Review-based Rating Prediction |
| Authors | Yuanquan Lu, Wei Zhang, Pan Lu, Jianyong Wang |
| Abstract | Nowadays, the online interactions between users and items become diverse, and may include textual reviews as well as numerical ratings. Reviews often express various opinions and sentiments, which can alleviate the sparsity problem of recommendations to some extent. In this paper, we address the personalized review-based rating prediction problem, namely, leveraging users’ historical reviews and corresponding ratings to predict their future ratings for items they have not interacted with before. While much effort has been devoted to this challenging problem mainly to investigate how to jointly model natural text and user personalization, most of them ignored sequential characteristics hidden in users’ review and rating sequences. To bridge this gap, we propose a novel Hybrid Review-based Sequential Model (HRSM) to capture future trajectories of users and items. This is achieved by feeding both users’ and items’ review sequences to a Long Short-Term Memory (LSTM) model that captures dynamics, in addition to incorporating a more traditional low-rank factorization that captures stationary states. The experimental results on real public datasets demonstrate that our model outperforms the state-of-the-art baselines. |
| Tasks | Multi-Domain Recommender Systems, Recommendation Systems |
| Published | 2019-04-14 |
| URL | https://www.springerprofessional.de/en/a-novel-hybrid-sequential-model-for-review-based-rating-predicti/16591760 |
| https://lupantech.github.io/papers/pakdd2019_hybrid.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-hybrid-sequential-model-for-review |
| Repo | |
| Framework | |
Classification in the dark using tactile exploration
| Title | Classification in the dark using tactile exploration |
| Authors | Mayur Mudigonda, Blake Tickell, Pulkit Agrawal |
| Abstract | Combining information from different sensory modalities to execute goal directed actions is a key aspect of human intelligence. Specifically, human agents are very easily able to translate the task communicated in one sensory domain (say vision) into a representation that enables them to complete this task when they can only sense their environment using a separate sensory modality (say touch). In order to build agents with similar capabilities, in this work we consider the problem of a retrieving a target object from a drawer. The agent is provided with an image of a previously unseen object and it explores objects in the drawer using only tactile sensing to retrieve the object that was shown in the image without receiving any visual feedback. Success at this task requires close integration of visual and tactile sensing. We present a method for performing this task in a simulated environment using an anthropomorphic hand. We hope that future research in the direction of combining sensory signals for acting will find the object retrieval from a drawer to be a useful benchmark problem |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1lXGnRctX |
| https://openreview.net/pdf?id=B1lXGnRctX | |
| PWC | https://paperswithcode.com/paper/classification-in-the-dark-using-tactile |
| Repo | |
| Framework | |
Local Binary Pattern Networks for Character Recognition
| Title | Local Binary Pattern Networks for Character Recognition |
| Authors | Jeng-Hau Lin, Yunfan Yang, Rajesh K. Gupta, Zhuowen Tu |
| Abstract | Memory and computation efficient deep learning architectures are crucial to the continued proliferation of machine learning capabilities to new platforms and systems. Binarization of operations in convolutional neural networks has shown promising results in reducing the model size and computing efficiency. In this paper, we tackle the character recognition problem using a strategy different from the existing literature by proposing local binary pattern networks or LBPNet that can learn and perform bit-wise operations in an end-to-end fashion. LBPNet uses local binary comparisons and random projection in place of conventional convolution (or approximation of convolution) operations, providing important means to improve memory and speed efficiency that is particularly suited for small footprint devices and hardware accelerators. These operations can be implemented efficiently on different platforms including direct hardware implementation. LBPNet demonstrates its particular advantage on the character classification task where the content is composed of strokes. We applied LBPNet to benchmark datasets like MNIST, SVHN, DHCD, ICDAR, and Chars74K and observed encouraging results. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJxcHnRqYQ |
| https://openreview.net/pdf?id=rJxcHnRqYQ | |
| PWC | https://paperswithcode.com/paper/local-binary-pattern-networks-for-character |
| Repo | |
| Framework | |
DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision
| Title | DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision |
| Authors | Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi, Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, Thomas Brox |
| Abstract | Deep neural network (DNN) based salient object detection in images based on high-quality labels is expensive. Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels. In this work, we propose a two-stage mechanism for robust unsupervised object saliency prediction, where the first stage involves refinement of the noisy pseudo labels generated from different handcrafted methods. Each handcrafted method is substituted by a deep network that learns to generate the pseudo labels. These labels are refined incrementally in multiple iterations via our proposed self-supervision technique. In the second stage, the refined labels produced from multiple networks representing multiple saliency methods are used to train the actual saliency detection network. We show that this self-learning procedure outperforms all the existing unsupervised methods over different datasets. Results are even comparable to those of fully-supervised state-of-the-art approaches. |
| Tasks | Object Detection, Saliency Detection, Saliency Prediction, Salient Object Detection |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8314-deepusps-deep-robust-unsupervised-saliency-prediction-via-self-supervision |
| http://papers.nips.cc/paper/8314-deepusps-deep-robust-unsupervised-saliency-prediction-via-self-supervision.pdf | |
| PWC | https://paperswithcode.com/paper/deepusps-deep-robust-unsupervised-saliency-1 |
| Repo | |
| Framework | |
T"upa at SemEval-2019 Task1: (Almost) feature-free Semantic Parsing
| Title | T"upa at SemEval-2019 Task1: (Almost) feature-free Semantic Parsing |
| Authors | Tobias P{"u}tz, Kevin Glocker |
| Abstract | Our submission for Task 1 {`}Cross-lingual Semantic Parsing with UCCA{'} at SemEval-2018 is a feed-forward neural network that builds upon an existing state-of-the-art transition-based directed acyclic graph parser. We replace most of its features by deep contextualized word embeddings and introduce an approximation to represent non-terminal nodes in the graph as an aggregation of their terminal children. We further demonstrate how augmenting data using the baseline systems provides a consistent advantage in all open submission tracks. We submitted results to all open tracks (English, in- and out-of-domain, German in-domain and French in-domain, low-resource). Our system achieves competitive performance in all settings besides the French, where we did not augment the data. Post-evaluation experiments showed that data augmentation is especially crucial in this setting. | |
| Tasks | Data Augmentation, Semantic Parsing, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2016/ |
| https://www.aclweb.org/anthology/S19-2016 | |
| PWC | https://paperswithcode.com/paper/tupa-at-semeval-2019-task1-almost-feature |
| Repo | |
| Framework | |
SkillBot: Towards Automatic Skill Development via User Demonstration
| Title | SkillBot: Towards Automatic Skill Development via User Demonstration |
| Authors | Yilin Shen, Avik Ray, Hongxia Jin, S Nama, eep |
| Abstract | We present SkillBot that takes the first step to enable end users to teach new skills in personal assistants (PA). Unlike existing PA products that need software developers to build new skills via IDE tools, an end user can use SkillBot to build new skills just by naturally demonstrating the task on device screen. SkillBot automatically develops a natural language understanding (NLU) engine and implements the action without the need of coding. On both benchmark and in-house datasets, we validate the competitive performance of SkillBot automatically built NLU. We also observe that it only takes a few minutes for an end user to build a new skill using SkillBot. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4018/ |
| https://www.aclweb.org/anthology/N19-4018 | |
| PWC | https://paperswithcode.com/paper/skillbot-towards-automatic-skill-development |
| Repo | |
| Framework | |
A Direct tilde{O}(1/epsilon) Iteration Parallel Algorithm for Optimal Transport
| Title | A Direct tilde{O}(1/epsilon) Iteration Parallel Algorithm for Optimal Transport |
| Authors | Arun Jambulapati, Aaron Sidford, Kevin Tian |
| Abstract | Optimal transportation, or computing the Wasserstein or ``earth mover’s’’ distance between two $n$-dimensional distributions, is a fundamental primitive which arises in many learning and statistical settings. We give an algorithm which solves the problem to additive $\epsilon$ accuracy with $\tilde{O}(1/\epsilon)$ parallel depth and $\tilde{O}\left(n^2/\epsilon\right)$ work. \cite{BlanchetJKS18, Quanrud19} obtained this runtime through reductions to positive linear programming and matrix scaling. However, these reduction-based algorithms use subroutines which may be impractical due to requiring solvers for second-order iterations (matrix scaling) or non-parallelizability (positive LP). Our methods match the previous-best work bounds by \cite{BlanchetJKS18, Quanrud19} while either improving parallelization or removing the need for linear system solves, and improve upon the previous best first-order methods running in time $\tilde{O}(\min(n^2 / \epsilon^2, n^{2.5} / \epsilon))$ \cite{DvurechenskyGK18, LinHJ19}. We obtain our results by a primal-dual extragradient method, motivated by recent theoretical improvements to maximum flow \cite{Sherman17}. | |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9313-a-direct-tildeo1epsilon-iteration-parallel-algorithm-for-optimal-transport |
| http://papers.nips.cc/paper/9313-a-direct-tildeo1epsilon-iteration-parallel-algorithm-for-optimal-transport.pdf | |
| PWC | https://paperswithcode.com/paper/a-direct-tildeo1epsilon-iteration-parallel |
| Repo | |
| Framework | |
Improving Answer Selection and Answer Triggering using Hard Negatives
| Title | Improving Answer Selection and Answer Triggering using Hard Negatives |
| Authors | Sawan Kumar, Shweta Garg, Kartik Mehta, Nikhil Rasiwasia |
| Abstract | In this paper, we establish the effectiveness of using hard negatives, coupled with a siamese network and a suitable loss function, for the tasks of answer selection and answer triggering. We show that the choice of sampling strategy is key for achieving improved performance on these tasks. Evaluating on recent answer selection datasets - InsuranceQA, SelQA, and an internal QA dataset, we show that using hard negatives with relatively simple model architectures (bag of words and LSTM-CNN) drives significant performance gains. On InsuranceQA, this strategy alone improves over previously reported results by a minimum of 1.6 points in P@1. Using hard negatives with a Transformer encoder provides a further improvement of 2.3 points. Further, we propose to use quadruplet loss for answer triggering, with the aim of producing globally meaningful similarity scores. We show that quadruplet loss function coupled with the selection of hard negatives enables bag-of-words models to improve F1 score by 2.3 points over previous baselines, on SelQA answer triggering dataset. Our results provide key insights into answer selection and answer triggering tasks. |
| Tasks | Answer Selection |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1604/ |
| https://www.aclweb.org/anthology/D19-1604 | |
| PWC | https://paperswithcode.com/paper/improving-answer-selection-and-answer |
| Repo | |
| Framework | |
