Paper Group NANR 81
A Large-Scale User Study of an Alexa Prize Chatbot: Effect of TTS Dynamism on Perceived Quality of Social Dialog. Robust Subspace Clustering With Independent and Piecewise Identically Distributed Noise Modeling. ParHistVis: Visualization of Parallel Multilingual Historical Data. WMDO: Fluency-based Word Mover’s Distance for Machine Translation Eval …
A Large-Scale User Study of an Alexa Prize Chatbot: Effect of TTS Dynamism on Perceived Quality of Social Dialog
| Title | A Large-Scale User Study of an Alexa Prize Chatbot: Effect of TTS Dynamism on Perceived Quality of Social Dialog |
| Authors | Michelle Cohn, Chun-Yen Chen, Zhou Yu |
| Abstract | This study tests the effect of cognitive-emotional expression in an Alexa text-to-speech (TTS) voice on users{'} experience with a social dialog system. We systematically introduced emotionally expressive interjections (e.g., {}Wow!{''}) and filler words (e.g., {}um{''}, {``}mhmm{''}) in an Amazon Alexa Prize socialbot, Gunrock. We tested whether these TTS manipulations improved users{'} ratings of their conversation across thousands of real user interactions (n=5,527). Results showed that interjections and fillers each improved users{'} holistic ratings, an improvement that further increased if the system used both manipulations. A separate perception experiment corroborated the findings from the user study, with improved social ratings for conversations including interjections; however, no positive effect was observed for fillers, suggesting that the role of the rater in the conversation{—}as active participant or external listener{—}is an important factor in assessing social dialogs. | |
| Tasks | Chatbot |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5935/ |
| https://www.aclweb.org/anthology/W19-5935 | |
| PWC | https://paperswithcode.com/paper/a-large-scale-user-study-of-an-alexa-prize |
| Repo | |
| Framework | |
Robust Subspace Clustering With Independent and Piecewise Identically Distributed Noise Modeling
| Title | Robust Subspace Clustering With Independent and Piecewise Identically Distributed Noise Modeling |
| Authors | Yuanman Li, Jiantao Zhou, Xianwei Zheng, Jinyu Tian, Yuan Yan Tang |
| Abstract | Most of the existing subspace clustering (SC) frameworks assume that the noise contaminating the data is generated by an independent and identically distributed (i.i.d.) source, where the Gaussianity is often imposed. Though these assumptions greatly simplify the underlying problems, they do not hold in many real-world applications. For instance, in face clustering, the noise is usually caused by random occlusions, local variations and unconstrained illuminations, which is essentially structural and hence satisfies neither the i.i.d. property nor the Gaussianity. In this work, we propose an independent and piecewise identically distributed (i.p.i.d.) noise model, where the i.i.d. property only holds locally. We demonstrate that the i.p.i.d. model better characterizes the noise encountered in practical scenarios, and accommodates the traditional i.i.d. model as a special case. Assisted by this generalized noise model, we design an information theoretic learning (ITL) framework for robust SC through a novel minimum weighted error entropy (MWEE) criterion. Extensive experimental results show that our proposed SC scheme significantly outperforms the state-of-the-art competing algorithms. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Li_Robust_Subspace_Clustering_With_Independent_and_Piecewise_Identically_Distributed_Noise_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Li_Robust_Subspace_Clustering_With_Independent_and_Piecewise_Identically_Distributed_Noise_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-subspace-clustering-with-independent |
| Repo | |
| Framework | |
ParHistVis: Visualization of Parallel Multilingual Historical Data
| Title | ParHistVis: Visualization of Parallel Multilingual Historical Data |
| Authors | Aikaterini-Lida Kalouli, Rebecca Kehlbeck, Rita Sevastjanova, Katharina Kaiser, Georg A. Kaiser, Miriam Butt |
| Abstract | The study of language change through parallel corpora can be advantageous for the analysis of complex interactions between time, text domain and language. Often, those advantages cannot be fully exploited due to the sparse but high-dimensional nature of such historical data. To tackle this challenge, we introduce ParHistVis: a novel, free, easy-to-use, interactive visualization tool for parallel, multilingual, diachronic and synchronic linguistic data. We illustrate the suitability of the components of the tool based on a use case of word order change in Romance wh-interrogatives. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4714/ |
| https://www.aclweb.org/anthology/W19-4714 | |
| PWC | https://paperswithcode.com/paper/parhistvis-visualization-of-parallel |
| Repo | |
| Framework | |
WMDO: Fluency-based Word Mover’s Distance for Machine Translation Evaluation
| Title | WMDO: Fluency-based Word Mover’s Distance for Machine Translation Evaluation |
| Authors | Julian Chow, Lucia Specia, Pranava Madhyastha |
| Abstract | We propose WMDO, a metric based on distance between distributions in the semantic vector space. Matching in the semantic space has been investigated for translation evaluation, but the constraints of a translation{'}s word order have not been fully explored. Building on the Word Mover{'}s Distance metric and various word embeddings, we introduce a fragmentation penalty to account for fluency of a translation. This word order extension is shown to perform better than standard WMD, with promising results against other types of metrics. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5356/ |
| https://www.aclweb.org/anthology/W19-5356 | |
| PWC | https://paperswithcode.com/paper/wmdo-fluency-based-word-movers-distance-for |
| Repo | |
| Framework | |
Don’t let your Discriminator be fooled
| Title | Don’t let your Discriminator be fooled |
| Authors | Brady Zhou, Philipp Krähenbühl |
| Abstract | Generative Adversarial Networks are one of the leading tools in generative modeling, image editing and content creation. However, they are hard to train as they require a delicate balancing act between two deep networks fighting a never ending duel. Some of the most promising adversarial models today minimize a Wasserstein objective. It is smoother and more stable to optimize. In this paper, we show that the Wasserstein distance is just one out of a large family of objective functions that yield these properties. By making the discriminator of a GAN robust to adversarial attacks we can turn any GAN objective into a smooth and stable loss. We experimentally show that any GAN objective, including Wasserstein GANs, benefit from adversarial robustness both quantitatively and qualitatively. The training additionally becomes more robust to suboptimal choices of hyperparameters, model architectures, or objective functions. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJE6X305Fm |
| https://openreview.net/pdf?id=HJE6X305Fm | |
| PWC | https://paperswithcode.com/paper/dont-let-your-discriminator-be-fooled |
| Repo | |
| Framework | |
Diversity and Depth in Per-Example Routing Models
| Title | Diversity and Depth in Per-Example Routing Models |
| Authors | Prajit Ramachandran, Quoc V. Le |
| Abstract | Routing models, a form of conditional computation where examples are routed through a subset of components in a larger network, have shown promising results in recent works. Surprisingly, routing models to date have lacked important properties, such as architectural diversity and large numbers of routing decisions. Both architectural diversity and routing depth can increase the representational power of a routing network. In this work, we address both of these deficiencies. We discuss the significance of architectural diversity in routing models, and explain the tradeoffs between capacity and optimization when increasing routing depth. In our experiments, we find that adding architectural diversity to routing models significantly improves performance, cutting the error rates of a strong baseline by 35% on an Omniglot setup. However, when scaling up routing depth, we find that modern routing techniques struggle with optimization. We conclude by discussing both the positive and negative results, and suggest directions for future research. |
| Tasks | Multi-Task Learning, Omniglot |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BkxWJnC9tX |
| https://openreview.net/pdf?id=BkxWJnC9tX | |
| PWC | https://paperswithcode.com/paper/diversity-and-depth-in-per-example-routing |
| Repo | |
| Framework | |
Modeling Hierarchical Syntactic Structures in Morphological Processing
| Title | Modeling Hierarchical Syntactic Structures in Morphological Processing |
| Authors | Yohei Oseki, Charles Yang, Alec Marantz |
| Abstract | Sentences are represented as hierarchical syntactic structures, which have been successfully modeled in sentence processing. In contrast, despite the theoretical agreement on hierarchical syntactic structures within words, words have been argued to be computationally less complex than sentences and implemented by finite-state models as linear strings of morphemes, and even the psychological reality of morphemes has been denied. In this paper, extending the computational models employed in sentence processing to morphological processing, we performed a computational simulation experiment where, given incremental surprisal as a linking hypothesis, five computational models with different representational assumptions were evaluated against human reaction times in visual lexical decision experiments available from the English Lexicon Project (ELP), a {}shared task{''} in the morphological processing literature. The simulation experiment demonstrated that (i) {}amorphous{''} models without morpheme units underperformed relative to {}morphous{''} models, (ii) a computational model with hierarchical syntactic structures, Probabilistic Context-Free Grammar (PCFG), most accurately explained human reaction times, and (iii) this performance was achieved on top of surface frequency effects. These results strongly suggest that morphological processing tracks morphemes incrementally from left to right and parses them into hierarchical syntactic structures, contrary to {}amorphous{''} and finite-state models of morphological processing. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2905/ |
| https://www.aclweb.org/anthology/W19-2905 | |
| PWC | https://paperswithcode.com/paper/modeling-hierarchical-syntactic-structures-in |
| Repo | |
| Framework | |
Weighted parsing for grammar-based language models
| Title | Weighted parsing for grammar-based language models |
| Authors | Richard M{"o}rbitz, Heiko Vogler |
| Abstract | We develop a general framework for weighted parsing which is built on top of grammar-based language models and employs flexible weight algebras. It generalizes previous work in that area (semiring parsing, weighted deductive parsing) and also covers applications outside the classical scope of parsing, e.g., algebraic dynamic programming. We show an algorithm which terminates and is correct for a large class of weighted grammar-based language models. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-3108/ |
| https://www.aclweb.org/anthology/W19-3108 | |
| PWC | https://paperswithcode.com/paper/weighted-parsing-for-grammar-based-language |
| Repo | |
| Framework | |
Online Learning for Supervised Dimension Reduction
| Title | Online Learning for Supervised Dimension Reduction |
| Authors | Ning Zhang, Qiang Wu |
| Abstract | Online learning has attracted great attention due to the increasing demand for systems that have the ability of learning and evolving. When the data to be processed is also high dimensional and dimension reduction is necessary for visualization or prediction enhancement, online dimension reduction will play an essential role. The purpose of this paper is to propose new online learning approaches for supervised dimension reduction. Our first algorithm is motivated by adapting the sliced inverse regression (SIR), a pioneer and effective algorithm for supervised dimension reduction, and making it implementable in an incremental manner. The new algorithm, called incremental sliced inverse regression (ISIR), is able to update the subspace of significant factors with intrinsic lower dimensionality fast and efficiently when new observations come in. We also refine the algorithm by using an overlapping technique and develop an incremental overlapping sliced inverse regression (IOSIR) algorithm. We verify the effectiveness and efficiency of both algorithms by simulations and real data applications. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=B1MUroRct7 |
| https://openreview.net/pdf?id=B1MUroRct7 | |
| PWC | https://paperswithcode.com/paper/online-learning-for-supervised-dimension |
| Repo | |
| Framework | |
Transfer Capsule Network for Aspect Level Sentiment Classification
| Title | Transfer Capsule Network for Aspect Level Sentiment Classification |
| Authors | Zhuang Chen, Tieyun Qian |
| Abstract | Aspect-level sentiment classification aims to determine the sentiment polarity of a sentence towards an aspect. Due to the high cost in annotation, the lack of aspect-level labeled data becomes a major obstacle in this area. On the other hand, document-level labeled data like reviews are easily accessible from online websites. These reviews encode sentiment knowledge in abundant contexts. In this paper, we propose a Transfer Capsule Network (TransCap) model for transferring document-level knowledge to aspect-level sentiment classification. To this end, we first develop an aspect routing approach to encapsulate the sentence-level semantic representations into semantic capsules from both the aspect-level and document-level data. We then extend the dynamic routing approach to adaptively couple the semantic capsules with the class capsules under the transfer learning framework. Experiments on SemEval datasets demonstrate the effectiveness of TransCap. |
| Tasks | Sentiment Analysis, Transfer Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1052/ |
| https://www.aclweb.org/anthology/P19-1052 | |
| PWC | https://paperswithcode.com/paper/transfer-capsule-network-for-aspect-level |
| Repo | |
| Framework | |
Accelerated Sparse Recovery Under Structured Measurements
| Title | Accelerated Sparse Recovery Under Structured Measurements |
| Authors | Ke Li, Jitendra Malik |
| Abstract | Extensive work on compressed sensing has yielded a rich collection of sparse recovery algorithms, each making different tradeoffs between recovery condition and computational efficiency. In this paper, we propose a unified framework for accelerating various existing sparse recovery algorithms without sacrificing recovery guarantees by exploiting structure in the measurement matrix. Unlike fast algorithms that are specific to particular choices of measurement matrices where the columns are Fourier or wavelet filters for example, the proposed approach works on a broad range of measurement matrices that satisfy a particular property. We precisely characterize this property, which quantifies how easy it is to accelerate sparse recovery for the measurement matrix in question. We also derive the time complexity of the accelerated algorithm, which is sublinear in the signal length in each iteration. Moreover, we present experimental results on real world data that demonstrate the effectiveness of the proposed approach in practice. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryxyHnR5tX |
| https://openreview.net/pdf?id=ryxyHnR5tX | |
| PWC | https://paperswithcode.com/paper/accelerated-sparse-recovery-under-structured |
| Repo | |
| Framework | |
Studying Laws of Semantic Divergence across Languages using Cognate Sets
| Title | Studying Laws of Semantic Divergence across Languages using Cognate Sets |
| Authors | Ana Uban, Alina Maria Ciobanu, Liviu P. Dinu |
| Abstract | Semantic divergence in related languages is a key concern of historical linguistics. Intra-lingual semantic shift has been previously studied in computational linguistics, but this can only provide a limited picture of the evolution of word meanings, which often develop in a multilingual environment. In this paper we investigate semantic change across languages by measuring the semantic distance of cognate words in multiple languages. By comparing current meanings of cognates in different languages, we hope to uncover information about their previous meanings, and about how they diverged in their respective languages from their common original etymon. We further study the properties of their semantic divergence, by analyzing how the features of words such as frequency and polysemy are related to the divergence in their meaning, and thus make the first steps towards formulating laws of cross-lingual semantic change. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4720/ |
| https://www.aclweb.org/anthology/W19-4720 | |
| PWC | https://paperswithcode.com/paper/studying-laws-of-semantic-divergence-across |
| Repo | |
| Framework | |
Multi-headed Architecture Based on BERT for Grammatical Errors Correction
| Title | Multi-headed Architecture Based on BERT for Grammatical Errors Correction |
| Authors | Bohdan Didenko, Julia Shaptala |
| Abstract | In this paper, we describe our approach to GEC using the BERT model for creation of encoded representation and some of our enhancements, namely, {``}Heads{''} are fully-connected networks which are used for finding the errors and later receive recommendation from the networks on dealing with a highlighted part of the sentence only. Among the main advantages of our solution is increasing the system productivity and lowering the time of processing while keeping the high accuracy of GEC results. | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4426/ |
| https://www.aclweb.org/anthology/W19-4426 | |
| PWC | https://paperswithcode.com/paper/multi-headed-architecture-based-on-bert-for |
| Repo | |
| Framework | |
Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science
| Title | Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2100/ |
| https://www.aclweb.org/anthology/W19-2100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-third-workshop-on-natural |
| Repo | |
| Framework | |
Towards Machine Reading for Interventions from Humanitarian-Assistance Program Literature
| Title | Towards Machine Reading for Interventions from Humanitarian-Assistance Program Literature |
| Authors | Bonan Min, Yee Seng Chan, Haoling Qiu, Joshua Fasching |
| Abstract | Solving long-lasting problems such as food insecurity requires a comprehensive understanding of interventions applied by governments and international humanitarian assistance organizations, and their results and consequences. Towards achieving this grand goal, a crucial first step is to extract past interventions and when and where they have been applied, from hundreds of thousands of reports automatically. In this paper, we developed a corpus annotated with interventions to foster research, and developed an information extraction system for extracting interventions and their location and time from text. We demonstrate early, very encouraging results on extracting interventions. |
| Tasks | Reading Comprehension |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1680/ |
| https://www.aclweb.org/anthology/D19-1680 | |
| PWC | https://paperswithcode.com/paper/towards-machine-reading-for-interventions |
| Repo | |
| Framework | |
