Paper Group NANR 83
Building Multimodal Simulations for Natural Language. Multi-Document Summarization of Persian Text using Paragraph Vectors. If You Can’t Beat Them Join Them: Handcrafted Features Complement Neural Nets for Non-Factoid Answer Reranking. Adaptive Clustering through Semidefinite Programming. Overview of the Second BUCC Shared Task: Spotting Parallel S …
Building Multimodal Simulations for Natural Language
| Title | Building Multimodal Simulations for Natural Language |
| Authors | James Pustejovsky, Nikhil Krishnaswamy |
| Abstract | In this tutorial, we introduce a computational framework and modeling language (VoxML) for composing multimodal simulations of natural language expressions within a 3D simulation environment (VoxSim). We demonstrate how to construct voxemes, which are visual object representations of linguistic entities. We also show how to compose events and actions over these objects, within a restricted domain of dynamics. This gives us the building blocks to simulate narratives of multiple events or participate in a multimodal dialogue with synthetic agents in the simulation environment. To our knowledge, this is the first time such material has been presented as a tutorial within the CL community.This will be of relevance to students and researchers interested in modeling actionable language, natural language communication with agents and robots, spatial and temporal constraint solving through language, referring expression generation, embodied cognition, as well as minimal model creation.Multimodal simulation of language, particularly motion expressions, brings together a number of existing lines of research from the computational linguistic, semantics, robotics, and formal logic communities, including action and event representation (Di Eugenio, 1991), modeling gestural correlates to NL expressions (Kipp et al., 2007; Neff et al., 2008), and action event modeling (Kipper and Palmer, 2000; Yang et al., 2015). We combine an approach to event modeling with a scene generation approach akin to those found in work by (Coyne and Sproat, 2001; Siskind, 2011; Chang et al., 2015). Mapping natural language expressions through a formal model and a dynamic logic interpretation into a visualization of the event described provides an environment for grounding concepts and referring expressions that is interpretable by both a computer and a human user. This opens a variety of avenues for humans to communicate with computerized agents and robots, as in (Matuszek et al., 2013; Lauria et al., 2001), (Forbes et al., 2015), and (Deits et al., 2013; Walter et al., 2013; Tellex et al., 2014). Simulation and automatic visualization of events from natural language descriptions and supplementary modalities, such as gestures, allows humans to use their native capabilities as linguistic and visual interpreters to collaborate on tasks with an artificial agent or to put semantic intuitions to the test in an environment where user and agent share a common context.In previous work (Pustejovsky and Krishnaswamy, 2014; Pustejovsky, 2013a), we introduced a method for modeling natural language expressions within a 3D simulation environment built on top of the game development platform Unity (Goldstone, 2009). The goal of that work was to evaluate, through explicit visualizations of linguistic input, the semantic presuppositions inherent in the different lexical choices of an utterance. This work led to two additional lines of research: an explicit encoding for how an object is itself situated relative to its environment; and an operational characterization of how an object changes its location or how an agent acts on an object over time, e.g., its affordance structure. The former has developed into a semantic notion of situational context, called a habitat (Pustejovsky, 2013a; McDonald and Pustejovsky, 2014), while the latter is addressed by dynamic interpretations of event structure (Pustejovsky and Moszkowicz, 2011; Pustejovsky and Krishnaswamy, 2016b; Pustejovsky, 2013b).The requirements on building a visual simulation from language include several components. We require a rich type system for lexical items and their composition, as well as a language for modeling the dynamics of events, based on Generative Lexicon (GL). Further, a minimal embedding space (MES) for the simulation must be determined. This is the 3D region within which the state is configured or the event unfolds. Object-based attributes for participants in a situation or event also need to be specified; e.g., orientation, relative size, default position or pose, etc. The simulation establishes an epistemic condition on the object and event rendering, imposing an implicit point of view (POV). Finally, there must be some sort of agent-dependent embodiment; this determines the relative scaling of an agent and its event participants and their surroundings, as it engages in the environment.In order to construct a robust simulation from linguistic input, an event and its participants must be embedded within an appropriate minimal embedding space. This must sufficiently enclose the event localization, while optionally including space enough for a frame of reference for the event (the viewer{^a}€{\mbox{$^\mbox{TM}$}}s perspective).We first describe the formal multimodal foundations for the modeling language, VoxML, which creates a minimal simulation from the linguistic input interpreted by the multimodal language, DITL. We then describe VoxSim, the compositional modeling and simulation environment, which maps the minimal VoxML model of the linguistic utterance to a simulation in Unity. This knowledge includes specification of object affordances, e.g., what actions are possible or enabled by use an object.VoxML (Pustejovsky and Krishnaswamy, 2016b; Pustejovsky and Krishnaswamy, 2016a) encodes semantic knowledge of real-world objects represented as 3D models, and of events and attributes related to and enacted over these objects. VoxML goes beyond the limitations of existing 3D visual markup languages by allowing for the encoding of a broad range of semantic knowledge that can be exploited by a simulation platform such as VoxSim.VoxSim (Krishnaswamy and Pustejovsky, 2016a; Krishnaswamy and Pustejovsky, 2016b) uses object and event semantic knowledge to generate animated scenes in real time without a complex animation interface. It uses the Unity game engine for graphics and I/O processing and takes as input a simple natural language utterance. The parsed utterance is semantically interpreted and transformed into a hybrid dynamic logic representation (DITL), and used to generate a minimal simulation of the event when composed with VoxML knowledge. 3D assets and VoxML-modeled nominal objects and events are created with other Unity-based tools, and VoxSim uses the entirety of the composed information to render a visualization of the described event.The tutorial participants will learn how to build simulatable objects, compose dynamic event structures, and simulate the events running over the objects. The toolkit consists of object and program (event) composers and the runtime environment, which allows for the user to directly manipulate the objects, or interact with synthetic agents in VoxSim. As a result of this tutorial, the student will acquire the following skill set: take a novel object geometry from a library and model it in VoxML; apply existing library behaviors (actions or events) to the new VoxML object; model attributes of new objects as well as introduce novel attributes; model novel behaviors over objects.The tutorial modules will be conducted within a build image of the software. Access to libraries will be provided by the instructors. No knowledge of 3D modeling or the Unity platform will be required. |
| Tasks | Scene Generation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-5006/ |
| https://www.aclweb.org/anthology/E17-5006 | |
| PWC | https://paperswithcode.com/paper/building-multimodal-simulations-for-natural |
| Repo | |
| Framework | |
Multi-Document Summarization of Persian Text using Paragraph Vectors
| Title | Multi-Document Summarization of Persian Text using Paragraph Vectors |
| Authors | Morteza Rohanian |
| Abstract | A multi-document summarizer finds the key topics from multiple textual sources and organizes information around them. In this paper we propose a summarization method for Persian text using paragraph vectors that can represent textual units of arbitrary lengths. We use these vectors to calculate the semantic relatedness between documents, cluster them to a number of predetermined groups, weight them based on their distance to the centroids and the intra-cluster homogeneity and take out the key paragraphs. We compare the final summaries with the gold-standard summaries of 21 digital topics using the ROUGE evaluation metric. Experimental results show the advantages of using paragraph vectors over earlier attempts at developing similar methods for a low resource language like Persian. |
| Tasks | Abstractive Text Summarization, Document Summarization, Multi-Document Summarization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-2005/ |
| https://doi.org/10.26615/issn.1314-9156.2017_005 | |
| PWC | https://paperswithcode.com/paper/multi-document-summarization-of-persian-text |
| Repo | |
| Framework | |
If You Can’t Beat Them Join Them: Handcrafted Features Complement Neural Nets for Non-Factoid Answer Reranking
| Title | If You Can’t Beat Them Join Them: Handcrafted Features Complement Neural Nets for Non-Factoid Answer Reranking |
| Authors | Dasha Bogdanova, Jennifer Foster, Daria Dzendzik, Qun Liu |
| Abstract | We show that a neural approach to the task of non-factoid answer reranking can benefit from the inclusion of tried-and-tested handcrafted features. We present a neural network architecture based on a combination of recurrent neural networks that are used to encode questions and answers, and a multilayer perceptron. We show how this approach can be combined with additional features, in particular, the discourse features used by previous research. Our neural approach achieves state-of-the-art performance on a public dataset from Yahoo! Answers and its performance is further improved by incorporating the discourse features. Additionally, we present a new dataset of Ask Ubuntu questions where the hybrid approach also achieves good results. |
| Tasks | Answer Selection, Community Question Answering, Feature Engineering, Learning-To-Rank, Question Answering |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1012/ |
| https://www.aclweb.org/anthology/E17-1012 | |
| PWC | https://paperswithcode.com/paper/if-you-cant-beat-them-join-them-handcrafted |
| Repo | |
| Framework | |
Adaptive Clustering through Semidefinite Programming
| Title | Adaptive Clustering through Semidefinite Programming |
| Authors | Martin Royer |
| Abstract | We analyze the clustering problem through a flexible probabilistic model that aims to identify an optimal partition on the sample X1,…,Xn. We perform exact clustering with high probability using a convex semidefinite estimator that interprets as a corrected, relaxed version of K-means. The estimator is analyzed through a non-asymptotic framework and showed to be optimal or near-optimal in recovering the partition. Furthermore, its performances are shown to be adaptive to the problem’s effective dimension, as well as to K the unknown number of groups in this partition. We illustrate the method’s performances in comparison to other classical clustering algorithms with numerical experiments on simulated high-dimensional data. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6776-adaptive-clustering-through-semidefinite-programming |
| http://papers.nips.cc/paper/6776-adaptive-clustering-through-semidefinite-programming.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-clustering-through-semidefinite |
| Repo | |
| Framework | |
Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora
| Title | Overview of the Second BUCC Shared Task: Spotting Parallel Sentences in Comparable Corpora |
| Authors | Pierre Zweigenbaum, Serge Sharoff, Reinhard Rapp |
| Abstract | This paper presents the BUCC 2017 shared task on parallel sentence extraction from comparable corpora. It recalls the design of the datasets, presents their final construction and statistics and the methods used to evaluate system results. 13 runs were submitted to the shared task by 4 teams, covering three of the four proposed language pairs: French-English (7 runs), German-English (3 runs), and Chinese-English (3 runs). The best F-scores as measured against the gold standard were 0.84 (German-English), 0.80 (French-English), and 0.43 (Chinese-English). Because of the design of the dataset, in which not all gold parallel sentence pairs are known, these are only minimum values. We examined manually a small sample of the false negative sentence pairs for the most precise French-English runs and estimated the number of parallel sentence pairs not yet in the provided gold standard. Adding them to the gold standard leads to revised estimates for the French-English F-scores of at most +1.5pt. This suggests that the BUCC 2017 datasets provide a reasonable approximate evaluation of the parallel sentence spotting task. |
| Tasks | Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2512/ |
| https://www.aclweb.org/anthology/W17-2512 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-second-bucc-shared-task |
| Repo | |
| Framework | |
Compatible Reward Inverse Reinforcement Learning
| Title | Compatible Reward Inverse Reinforcement Learning |
| Authors | Alberto Maria Metelli, Matteo Pirotta, Marcello Restelli |
| Abstract | Inverse Reinforcement Learning (IRL) is an effective approach to recover a reward function that explains the behavior of an expert by observing a set of demonstrations. This paper is about a novel model-free IRL approach that, differently from most of the existing IRL algorithms, does not require to specify a function space where to search for the expert’s reward function. Leveraging on the fact that the policy gradient needs to be zero for any optimal policy, the algorithm generates a set of basis functions that span the subspace of reward functions that make the policy gradient vanish. Within this subspace, using a second-order criterion, we search for the reward function that penalizes the most a deviation from the expert’s policy. After introducing our approach for finite domains, we extend it to continuous ones. The proposed approach is empirically compared to other IRL methods both in the (finite) Taxi domain and in the (continuous) Linear Quadratic Gaussian (LQG) and Car on the Hill environments. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6800-compatible-reward-inverse-reinforcement-learning |
| http://papers.nips.cc/paper/6800-compatible-reward-inverse-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/compatible-reward-inverse-reinforcement |
| Repo | |
| Framework | |
Optimized Pre-Processing for Discrimination Prevention
| Title | Optimized Pre-Processing for Discrimination Prevention |
| Authors | Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, Kush R. Varshney |
| Abstract | Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling discrimination, limiting distortion in individual data samples, and preserving utility. We characterize the impact of limited sample size in accomplishing this objective. Two instances of the proposed optimization are applied to datasets, including one on real-world criminal recidivism. Results show that discrimination can be greatly reduced at a small cost in classification accuracy. |
| Tasks | Decision Making |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6988-optimized-pre-processing-for-discrimination-prevention |
| http://papers.nips.cc/paper/6988-optimized-pre-processing-for-discrimination-prevention.pdf | |
| PWC | https://paperswithcode.com/paper/optimized-pre-processing-for-discrimination |
| Repo | |
| Framework | |
Multiscale Quantization for Fast Similarity Search
| Title | Multiscale Quantization for Fast Similarity Search |
| Authors | Xiang Wu, Ruiqi Guo, Ananda Theertha Suresh, Sanjiv Kumar, Daniel N. Holtmann-Rice, David Simcha, Felix Yu |
| Abstract | We propose a multiscale quantization approach for fast similarity search on large, high-dimensional datasets. The key insight of the approach is that quantization methods, in particular product quantization, perform poorly when there is large variance in the norms of the data points. This is a common scenario for real- world datasets, especially when doing product quantization of residuals obtained from coarse vector quantization. To address this issue, we propose a multiscale formulation where we learn a separate scalar quantizer of the residual norm scales. All parameters are learned jointly in a stochastic gradient descent framework to minimize the overall quantization error. We provide theoretical motivation for the proposed technique and conduct comprehensive experiments on two large-scale public datasets, demonstrating substantial improvements in recall over existing state-of-the-art methods. |
| Tasks | Quantization |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7157-multiscale-quantization-for-fast-similarity-search |
| http://papers.nips.cc/paper/7157-multiscale-quantization-for-fast-similarity-search.pdf | |
| PWC | https://paperswithcode.com/paper/multiscale-quantization-for-fast-similarity |
| Repo | |
| Framework | |
Dynamic Revenue Sharing
| Title | Dynamic Revenue Sharing |
| Authors | Santiago Balseiro, Max Lin, Vahab Mirrokni, Renato Leme, Iiis Song Zuo |
| Abstract | Many online platforms act as intermediaries between a seller and a set of buyers. Examples of such settings include online retailers (such as Ebay) selling items on behalf of sellers to buyers, or advertising exchanges (such as AdX) selling pageviews on behalf of publishers to advertisers. In such settings, revenue sharing is a central part of running such a marketplace for the intermediary, and fixed-percentage revenue sharing schemes are often used to split the revenue among the platform and the sellers. In particular, such revenue sharing schemes require the platform to (i) take at most a constant fraction \alpha of the revenue from auctions and (ii) pay the seller at least the seller declared opportunity cost c for each item sold. A straightforward way to satisfy the constraints is to set a reserve price at c / (1 - \alpha) for each item, but it is not the optimal solution on maximizing the profit of the intermediary. While previous studies (by Mirrokni and Gomes, and by Niazadeh et al) focused on revenue-sharing schemes in static double auctions, in this paper, we take advantage of the repeated nature of the auctions. In particular, we introduce dynamic revenue sharing schemes where we balance the two constraints over different auctions to achieve higher profit and seller revenue. This is directly motivated by the practice of advertising exchanges where the fixed-percentage revenue-share should be met across all auctions and not in each auction. In this paper, we characterize the optimal revenue sharing scheme that satisfies both constraints in expectation. Finally, we empirically evaluate our revenue sharing scheme on real data. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6861-dynamic-revenue-sharing |
| http://papers.nips.cc/paper/6861-dynamic-revenue-sharing.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-revenue-sharing |
| Repo | |
| Framework | |
Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search
| Title | Decomposition-Invariant Conditional Gradient for General Polytopes with Line Search |
| Authors | Mohammad Ali Bashiri, Xinhua Zhang |
| Abstract | Frank-Wolfe (FW) algorithms with linear convergence rates have recently achieved great efficiency in many applications. Garber and Meshi (2016) designed a new decomposition-invariant pairwise FW variant with favorable dependency on the domain geometry. Unfortunately, it applies only to a restricted class of polytopes and cannot achieve theoretical and practical efficiency at the same time. In this paper, we show that by employing an away-step update, similar rates can be generalized to arbitrary polytopes with strong empirical performance. A new “condition number” of the domain is introduced which allows leveraging the sparsity of the solution. We applied the method to a reformulation of SVM, and the linear convergence rate depends, for the first time, on the number of support vectors. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6862-decomposition-invariant-conditional-gradient-for-general-polytopes-with-line-search |
| http://papers.nips.cc/paper/6862-decomposition-invariant-conditional-gradient-for-general-polytopes-with-line-search.pdf | |
| PWC | https://paperswithcode.com/paper/decomposition-invariant-conditional-gradient |
| Repo | |
| Framework | |
Building Dialectal Arabic Corpora
| Title | Building Dialectal Arabic Corpora |
| Authors | Hani Elgabou, Dimitar Kazakov |
| Abstract | The aim of this research is to identify local Arabic dialects in texts from social media (Twitter) and link them to specific geographic areas. Dialect identification is studied as a subset of the task of language identification. The proposed method is based on unsupervised learning using simultaneously lexical and geographic distance. While this study focusses on Libyan dialects, the approach is general, and could produce resources to support human translators and interpreters when dealing with vernaculars rather than standard Arabic. |
| Tasks | Information Retrieval, Language Identification, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7907/ |
| https://doi.org/10.26615/978-954-452-042-7_007 | |
| PWC | https://paperswithcode.com/paper/building-dialectal-arabic-corpora |
| Repo | |
| Framework | |
WiseReporter: A Korean Report Generation System
| Title | WiseReporter: A Korean Report Generation System |
| Authors | Yunseok Noh, Su Jeong Choi, Seong-Bae Park, Se-Young Park |
| Abstract | We demonstrate a report generation system called WiseReporter. The WiseReporter generates a text report of a specific topic which is usually given as a keyword by verbalizing knowledge base facts involving the topic. This demonstration does not demonstate only the report itself, but also the processes how the sentences for the report are generated. We are planning to enhance WiseReporter in the future by adding data analysis based on deep learning architecture and text summarization. |
| Tasks | Slot Filling, Text Generation, Text Summarization |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3003/ |
| https://www.aclweb.org/anthology/I17-3003 | |
| PWC | https://paperswithcode.com/paper/wisereporter-a-korean-report-generation |
| Repo | |
| Framework | |
Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples
| Title | Houdini: Fooling Deep Structured Visual and Speech Recognition Models with Adversarial Examples |
| Authors | Moustapha M. Cisse, Yossi Adi, Natalia Neverova, Joseph Keshet |
| Abstract | Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and are not designed to alter the true performance measure of the problem at hand. We introduce a novel flexible approach named Houdini for generating adversarial examples specifically tailored for the final performance measure of the task considered, be it combinatorial and non-decomposable. We successfully apply Houdini to a range of applications such as speech recognition, pose estimation and semantic segmentation. In all cases, the attacks based on Houdini achieve higher success rate than those based on the traditional surrogates used to train the models while using a less perceptible adversarial perturbation. |
| Tasks | Pose Estimation, Semantic Segmentation, Speech Recognition |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7273-houdini-fooling-deep-structured-visual-and-speech-recognition-models-with-adversarial-examples |
| http://papers.nips.cc/paper/7273-houdini-fooling-deep-structured-visual-and-speech-recognition-models-with-adversarial-examples.pdf | |
| PWC | https://paperswithcode.com/paper/houdini-fooling-deep-structured-visual-and |
| Repo | |
| Framework | |
Proceedings of the Workshop Computational Semantics Beyond Events and Roles
| Title | Proceedings of the Workshop Computational Semantics Beyond Events and Roles |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1800/ |
| https://www.aclweb.org/anthology/W17-1800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-computational |
| Repo | |
| Framework | |
Discourse Segmentation for Building a RST Chinese Treebank
| Title | Discourse Segmentation for Building a RST Chinese Treebank |
| Authors | Shuyuan Cao, Nianwen Xue, Iria da Cunha, Mikel Iruskieta, Chuan Wang |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3610/ |
| https://www.aclweb.org/anthology/W17-3610 | |
| PWC | https://paperswithcode.com/paper/discourse-segmentation-for-building-a-rst |
| Repo | |
| Framework | |
