Paper Group NANR 146
Rating Continuous Actions in Spatial Multi-Agent Problems. Translation Quality Assessment Tools and Processes in Relation to CAT Tools. Corpus Linguistics, Translation and Error Analysis. Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters’ D'ecalage. Interlaced Greedy Algorithm …
Rating Continuous Actions in Spatial Multi-Agent Problems
| Title | Rating Continuous Actions in Spatial Multi-Agent Problems |
| Authors | Uwe Dick, Maryam Tavakol, Ulf Brefeld |
| Abstract | We study credit assignment problems in spatial multi-agent environments where agents pursue a joint objective. On the example of soccer, we rate the movements of individual players with respect to their potential for staging a successful attack. We propose a purely data-driven approach to simultaneously learn a model of agent movements as well as their ratings via an agent-centric deep reinforcement learning framework. Our model allows for efficient learning and sampling of ratings in the continuous action space. We empirically observe on historic soccer data that the model accurately rates agent movements w.r.t. their relative contribution to the collective goal. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HygqJnCqtm |
| https://openreview.net/pdf?id=HygqJnCqtm | |
| PWC | https://paperswithcode.com/paper/rating-continuous-actions-in-spatial-multi |
| Repo | |
| Framework | |
Translation Quality Assessment Tools and Processes in Relation to CAT Tools
| Title | Translation Quality Assessment Tools and Processes in Relation to CAT Tools |
| Authors | Viktoriya Petrova |
| Abstract | Modern translation QA tools are the latest attempt to overcome the inevitable subjective component of human revisers. This paper analyzes the current situation in the translation industry in respect to those tools and their relationship with CAT tools. The adoption of international standards has set the basic frame that defines {``}quality{''}. Because of the clear impossibility to develop a universal QA tool, all of the existing ones have in common a wide variety of settings for the user to choose from. A brief comparison is made between most popular standalone QA tools. In order to verify their results in practice, QA outputs from two of those tools have been compared. Polls that cover a period of 12 years have been collected. Their participants explained what practices they adopted in order to guarantee quality. | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8711/ |
| https://www.aclweb.org/anthology/W19-8711 | |
| PWC | https://paperswithcode.com/paper/translation-quality-assessment-tools-and |
| Repo | |
| Framework | |
Corpus Linguistics, Translation and Error Analysis
| Title | Corpus Linguistics, Translation and Error Analysis |
| Authors | Maria Stambolieva |
| Abstract | The paper presents a study of the French Imparfait and its functional equivalents in Bulgarian and English in view of applications in machine translation and error analysis. The aims of the study are: 1/ based on the analysis of a corpus of text, to validate/revise earlier research on the values of the French Imparfait, 2/ to define the contextual factors pointing to the realisation of one or another value of the forms, 3/ based on the analysis of aligned translations, to identify the translation equivalents of these values, 4/ to formulate translation rules, 5/ based on the analysis of the translation rules, to refine the annotation modules of the environment used {–} the NBU e-Platform for language teaching and research. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8712/ |
| https://www.aclweb.org/anthology/W19-8712 | |
| PWC | https://paperswithcode.com/paper/corpus-linguistics-translation-and-error |
| Repo | |
| Framework | |
Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters’ D'ecalage
| Title | Human-Informed Speakers and Interpreters Analysis in the WAW Corpus and an Automatic Method for Calculating Interpreters’ D'ecalage |
| Authors | Irina Temnikova, Ahmed Abdelali, Souhila Djabri, Samy Hedaya |
| Abstract | This article presents a multi-faceted analysis of a subset of interpreted conference speeches from the WAW corpus for the English-Arabic language pair. We analyze several speakers and interpreters variables via manual annotation and automatic methods. We propose a new automatic method for calculating interpreters{'} d{'e}calage based on Automatic Speech Recognition (ASR) and automatic alignment of named entities and content words between speaker and interpreter. The method is evaluated by two human annotators who have expertise in interpreting and Interpreting Studies and shows highly satisfactory results, accompanied with a high inter-annotator agreement. We provide insights about the relations of speakers{'} variables, interpreters{'} variables and d{'e}calage and discuss them from Interpreting Studies and interpreting practice point of view. We had interesting findings about interpreters behavior which need to be extended to a large number of conference sessions in our future research. |
| Tasks | Speech Recognition |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8713/ |
| https://www.aclweb.org/anthology/W19-8713 | |
| PWC | https://paperswithcode.com/paper/human-informed-speakers-and-interpreters |
| Repo | |
| Framework | |
Interlaced Greedy Algorithm for Maximization of Submodular Functions in Nearly Linear Time
| Title | Interlaced Greedy Algorithm for Maximization of Submodular Functions in Nearly Linear Time |
| Authors | Alan Kuhnle |
| Abstract | A deterministic approximation algorithm is presented for the maximization of non-monotone submodular functions over a ground set of size $n$ subject to cardinality constraint $k$; the algorithm is based upon the idea of interlacing two greedy procedures. The algorithm uses interlaced, thresholded greedy procedures to obtain tight ratio $1/4 - \epsilon$ in $O \left( \frac{n}{\epsilon} \log \left( \frac{k}{\epsilon} \right) \right)$ queries of the objective function, which improves upon both the ratio and the quadratic time complexity of the previously fastest deterministic algorithm for this problem. The algorithm is validated in the context of two applications of non-monotone submodular maximization, on which it outperforms the fastest deterministic and randomized algorithms in prior literature. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8508-interlaced-greedy-algorithm-for-maximization-of-submodular-functions-in-nearly-linear-time |
| http://papers.nips.cc/paper/8508-interlaced-greedy-algorithm-for-maximization-of-submodular-functions-in-nearly-linear-time.pdf | |
| PWC | https://paperswithcode.com/paper/interlaced-greedy-algorithm-for-maximization |
| Repo | |
| Framework | |
FiNet: Compatible and Diverse Fashion Image Inpainting
| Title | FiNet: Compatible and Diverse Fashion Image Inpainting |
| Authors | Xintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott, Larry S. Davis |
| Abstract | Visual compatibility is critical for fashion analysis, yet is missing in existing fashion image synthesis systems. In this paper, we propose to explicitly model visual compatibility through fashion image inpainting. We present Fashion Inpainting Networks (FiNet), a two-stage image-to-image generation framework that is able to perform compatible and diverse inpainting. Disentangling the generation of shape and appearance to ensure photorealistic results, our framework consists of a shape generation network and an appearance generation network. More importantly, for each generation network, we introduce two encoders interacting with one another to learn latent codes in a shared compatibility space. The latent representations are jointly optimized with the corresponding generation network to condition the synthesis process, encouraging a diverse set of generated results that are visually compatible with existing fashion garments. In addition, our framework is readily extended to clothing reconstruction and fashion transfer. Extensive experiments on fashion synthesis quantitatively and qualitatively demonstrate the effectiveness of our method. |
| Tasks | Image Generation, Image Inpainting |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Han_FiNet_Compatible_and_Diverse_Fashion_Image_Inpainting_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Han_FiNet_Compatible_and_Diverse_Fashion_Image_Inpainting_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/finet-compatible-and-diverse-fashion-image |
| Repo | |
| Framework | |
Reasoning About Physical Interactions with Object-Centric Models
| Title | Reasoning About Physical Interactions with Object-Centric Models |
| Authors | Michael Janner, Sergey Levine, William T. Freeman, Joshua B. Tenenbaum, Chelsea Finn, Jiajun Wu |
| Abstract | Object-based factorizations provide a useful level of abstraction for interacting with the world. Building explicit object representations, however, often requires supervisory signals that are difficult to obtain in practice. We present a paradigm for learning object-centric representations for physical scene understanding without direct supervision of object properties. Our model, object-oriented prediction and planning (O2P2), jointly learns a perception function to map from image observations to object representations, a pairwise physics interaction function to predict the time evolution of a collection of objects, and a rendering function to map objects back to pixels. For evaluation, we consider not only the accuracy of the physical predictions of the model, but also its utility for downstream tasks that require an actionable representation of intuitive physics. After training our model on an image prediction task, we can use its learned representations to build block towers more complicated than those observed during training. |
| Tasks | Scene Understanding |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJx9EhC9tQ |
| https://openreview.net/pdf?id=HJx9EhC9tQ | |
| PWC | https://paperswithcode.com/paper/reasoning-about-physical-interactions-with |
| Repo | |
| Framework | |
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
| Title | Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control |
| Authors | Robert Csordas, Juergen Schmidhuber |
| Abstract | The Differentiable Neural Computer (DNC) can learn algorithmic and question answering tasks. An analysis of its internal activation patterns reveals three problems: Most importantly, the lack of key-value separation makes the address distribution resulting from content-based look-up noisy and flat, since the value influences the score calculation, although only the key should. Second, DNC’s de-allocation of memory results in aliasing, which is a problem for content-based look-up. Thirdly, chaining memory reads with the temporal linkage matrix exponentially degrades the quality of the address distribution. Our proposed fixes of these problems yield improved performance on arithmetic tasks, and also improve the mean error rate on the bAbI question answering dataset by 43%. |
| Tasks | Question Answering |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyGEM3C9KQ |
| https://openreview.net/pdf?id=HyGEM3C9KQ | |
| PWC | https://paperswithcode.com/paper/improving-differentiable-neural-computers |
| Repo | |
| Framework | |
Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution
| Title | Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution |
| Authors | Raied Aljadaany, Dipan K. Pal, Marios Savvides |
| Abstract | Blind deconvolution problems are heavily ill-posed where the specific blurring kernel is not known. Recovering these images typically requires estimates of the kernel. In this paper, we present a method called Dr-Net, which does not require any such estimate and is further able to invert the effects of the blurring in blind image recovery tasks. These image recovery problems typically have two terms, the data fidelity term (for faithful reconstruction) and the image prior (for realistic looking reconstructions). We use the Douglas-Rachford iterations to solve this problem since it is a more generally applicable optimization procedure than methods such as the proximal gradient descent algorithm. Two proximal operators originate from these iterations, one from the data fidelity term and the second from the image prior. It is non-trivial to design a hand-crafted function to represent these proximal operators for the data fidelity and the image prior terms which would work with real-world image distributions. We therefore approximate both these proximal operators using deep networks. This provides a sound motivation for the final architecture for Dr-Net which we find outperforms the state-of-the-art on two mainstream blind deconvolution benchmarks. We also find that Dr-Net is one of the fastest algorithms according to wall-clock times while doing so. |
| Tasks | Image Deconvolution |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Aljadaany_Douglas-Rachford_Networks_Learning_Both_the_Image_Prior_and_Data_Fidelity_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Aljadaany_Douglas-Rachford_Networks_Learning_Both_the_Image_Prior_and_Data_Fidelity_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/douglas-rachford-networks-learning-both-the |
| Repo | |
| Framework | |
Towards a Proactive MWE Terminological Platform for Cross-Lingual Mediation in the Age of Big Data
| Title | Towards a Proactive MWE Terminological Platform for Cross-Lingual Mediation in the Age of Big Data |
| Authors | Benjamin K. Tsou, Kapo Chow, JUNRU Nie, Yuan Yuan |
| Abstract | The emergence of China as a global economic power in the 21st Century has brought about surging needs for cross-lingual and cross-cultural mediation, typically performed by translators. Advances in Artificial Intelligence and Language Engineering have been bolstered by Machine learning and suitable Big Data cultivation. They have helped to meet some of the translator{'}s needs, though the technical specialists have not kept pace with the practical and expanding requirements in language mediation. One major technical and linguistic hurdle involves words outside the vocabulary of the translator or the lexical database he/she consults, especially Multi-Word Expressions (Compound Words) in technical subjects. A further problem is in the multiplicity of renditions of a term in the target language. This paper discusses a proactive approach following the successful extraction and application of sizable bilingual Multi-Word Expressions (Compound Words) for language mediation in technical subjects, which do not fall within the expertise of typical translators, who have inadequate appreciation of the range of new technical tools available to help him/her. Our approach draws on the personal reflections of translators and teachers of translation and is based on the prior R{&}D efforts relating to 300,000 comparable Chinese-English patents. The subsequent protocol we have developed aims to be proactive in meeting four identified practical challenges in technical translation (e.g. patents). It has broader economic implication in the Age of Big Data (Tsou et al, 2015) and Trade War, as the workload, if not, the challenges, increasingly cannot be met by currently available front-line translators. We shall demonstrate how new tools can be harnessed to spearhead the application of language technology not only in language mediation but also in the {}teaching{''} and {}learning{''} of translation. It shows how a better appreciation of their needs may enhance the contributions of the technical specialists, and thus enhance the resultant synergetic benefits. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8714/ |
| https://www.aclweb.org/anthology/W19-8714 | |
| PWC | https://paperswithcode.com/paper/towards-a-proactive-mwe-terminological |
| Repo | |
| Framework | |
Contextualized Diachronic Word Representations
| Title | Contextualized Diachronic Word Representations |
| Authors | Ganesh Jawahar, Djam{'e} Seddah |
| Abstract | Diachronic word embeddings play a key role in capturing interesting patterns about how language evolves over time. Most of the existing work focuses on studying corpora spanning across several decades, which is understandably still not a possibility when working on social media-based user-generated content. In this work, we address the problem of studying semantic changes in a large Twitter corpus collected over five years, a much shorter period than what is usually the norm in diachronic studies. We devise a novel attentional model, based on Bernoulli word embeddings, that are conditioned on contextual extra-linguistic (social) features such as network, spatial and socio-economic variables, which are associated with Twitter users, as well as topic-based features. We posit that these social features provide an inductive bias that helps our model to overcome the narrow time-span regime problem. Our extensive experiments reveal that our proposed model is able to capture subtle semantic shifts without being biased towards frequency cues and also works well when certain contextual features are absent. Our model fits the data better than current state-of-the-art dynamic word embedding models and therefore is a promising tool to study diachronic semantic changes over small time periods. |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4705/ |
| https://www.aclweb.org/anthology/W19-4705 | |
| PWC | https://paperswithcode.com/paper/contextualized-diachronic-word |
| Repo | |
| Framework | |
Sentiment and Emotion Based Representations for Fake Reviews Detection
| Title | Sentiment and Emotion Based Representations for Fake Reviews Detection |
| Authors | Alimuddin Melleng, Anna Jurek-Loughrey, Deepak P |
| Abstract | Fake reviews are increasingly prevalent across the Internet. They can be unethical as well as harmful. They can affect businesses and mislead individual customers. As the opinions on the Web are increasingly used the detection of fake reviews has become more and more critical. In this study, we explore the effectiveness of sentiment and emotions based representations for the task of building machine learning models for fake review detection. We perform empirical studies over three real world datasets and demonstrate that improved data representation can be achieved by combining sentiment and emotion extraction methods, as well as by performing sentiment and emotion analysis on a part-by-part basis by segmenting the reviews. |
| Tasks | Emotion Recognition |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1087/ |
| https://www.aclweb.org/anthology/R19-1087 | |
| PWC | https://paperswithcode.com/paper/sentiment-and-emotion-based-representations |
| Repo | |
| Framework | |
AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation
| Title | AGSS-VOS: Attention Guided Single-Shot Video Object Segmentation |
| Authors | Huaijia Lin, Xiaojuan Qi, Jiaya Jia |
| Abstract | Most video object segmentation approaches process objects separately. This incurs high computational cost when multiple objects exist. In this paper, we propose AGSS-VOS to segment multiple objects in one feed-forward path via instance-agnostic and instance-specific modules. Information from the two modules is fused via an attention-guided decoder to simultaneously segment all object instances in one path. The whole framework is end-to-end trainable with instance IoU loss. Experimental results on Youtube- VOS and DAVIS-2017 dataset demonstrate that AGSS-VOS achieves competitive results in terms of both accuracy and efficiency. |
| Tasks | Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Lin_AGSS-VOS_Attention_Guided_Single-Shot_Video_Object_Segmentation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Lin_AGSS-VOS_Attention_Guided_Single-Shot_Video_Object_Segmentation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/agss-vos-attention-guided-single-shot-video |
| Repo | |
| Framework | |
BME-UW at SRST-2019: Surface realization with Interpreted Regular Tree Grammars
| Title | BME-UW at SRST-2019: Surface realization with Interpreted Regular Tree Grammars |
| Authors | {'A}d{'a}m Kov{'a}cs, Evelin {'A}cs, Judit {'A}cs, Andras Kornai, G{'a}bor Recski |
| Abstract | The Surface Realization Shared Task involves mapping Universal Dependency graphs to raw text, i.e. restoring word order and inflection from a graph of typed, directed dependencies between lemmas. Interpreted Regular Tree Grammars (IRTGs) encode the correspondence between generations in multiple algebras, and have previously been used for semantic parsing from raw text. Our system induces an IRTG for simultaneously building pairs of surface forms and UD graphs in the SRST training data, then prunes this grammar for each UD graph in the test data for efficient parsing and generation of the surface ordering of lemmas. For the inflection step we use a standard sequence-to-sequence model with a biLSTM encoder and an LSTM decoder with attention. Both components of our system are available on GitHub under an MIT license. |
| Tasks | Semantic Parsing |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6304/ |
| https://www.aclweb.org/anthology/D19-6304 | |
| PWC | https://paperswithcode.com/paper/bme-uw-at-srst-2019-surface-realization-with |
| Repo | |
| Framework | |
MultiLing 2019: Financial Narrative Summarisation
| Title | MultiLing 2019: Financial Narrative Summarisation |
| Authors | Mahmoud El-Haj |
| Abstract | The Financial Narrative Summarisation task at MultiLing 2019 aims to demonstrate the value and challenges of applying automatic text summarisation to financial text written in English, usually referred to as financial narrative disclosures. The task dataset has been extracted from UK annual reports published in PDF file format. The participants were asked to provide structured summaries, based on real-world, publicly available financial annual reports of UK firms by extracting information from different key sections. Participants were asked to generate summaries that reflects the analysis and assessment of the financial trend of the business over the past year, as provided by annual reports. The evaluation of the summaries was performed using AutoSummENG and Rouge automatic metrics. This paper focuses mainly on the data creation process. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8902/ |
| https://www.aclweb.org/anthology/W19-8902 | |
| PWC | https://paperswithcode.com/paper/multiling-2019-financial-narrative |
| Repo | |
| Framework | |
