Paper Group NANR 158
Metadata Collection Records for Language Resources. Managing Public Sector Data for Multilingual Applications Development. Strategies and Challenges for Crowdsourcing Regional Dialect Perception Data for Swiss German and Swiss French. Johns Hopkins or johnny-hopkins: Classifying Individuals versus Organizations on Twitter. Cheating a Parser to Deat …
Metadata Collection Records for Language Resources
| Title | Metadata Collection Records for Language Resources |
| Authors | Henk van den Heuvel, Erwin Komen, Nelleke Oostdijk |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1204/ |
| https://www.aclweb.org/anthology/L18-1204 | |
| PWC | https://paperswithcode.com/paper/metadata-collection-records-for-language |
| Repo | |
| Framework | |
Managing Public Sector Data for Multilingual Applications Development
| Title | Managing Public Sector Data for Multilingual Applications Development |
| Authors | Stelios Piperidis, Penny Labropoulou, Miltos Deligiannis, Maria Giagkou |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1205/ |
| https://www.aclweb.org/anthology/L18-1205 | |
| PWC | https://paperswithcode.com/paper/managing-public-sector-data-for-multilingual |
| Repo | |
| Framework | |
Strategies and Challenges for Crowdsourcing Regional Dialect Perception Data for Swiss German and Swiss French
| Title | Strategies and Challenges for Crowdsourcing Regional Dialect Perception Data for Swiss German and Swiss French |
| Authors | Jean-Philippe Goldman, Simon Clematide, Mathieu Avanzi, T, Raphael ler |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1234/ |
| https://www.aclweb.org/anthology/L18-1234 | |
| PWC | https://paperswithcode.com/paper/strategies-and-challenges-for-crowdsourcing |
| Repo | |
| Framework | |
Johns Hopkins or johnny-hopkins: Classifying Individuals versus Organizations on Twitter
| Title | Johns Hopkins or johnny-hopkins: Classifying Individuals versus Organizations on Twitter |
| Authors | Zach Wood-Doughty, Praateek Mahajan, Mark Dredze |
| Abstract | Twitter user accounts include a range of different user types. While many individuals use Twitter, organizations also have Twitter accounts. Identifying opinions and trends from Twitter requires the accurate differentiation of these two groups. Previous work (McCorriston et al., 2015) presented a method for determining if an account was an individual or organization based on account profile and a collection of tweets. We present a method that relies solely on the account profile, allowing for the classification of individuals versus organizations based on a single tweet. Our method obtains accuracies comparable to methods that rely on much more information by leveraging two improvements: a character-based Convolutional Neural Network, and an automatically derived labeled corpus an order of magnitude larger than the previously available dataset. We make both the dataset and the resulting tool available. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1108/ |
| https://www.aclweb.org/anthology/W18-1108 | |
| PWC | https://paperswithcode.com/paper/johns-hopkins-or-johnny-hopkins-classifying |
| Repo | |
| Framework | |
Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer
| Title | Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer |
| Authors | Djam{'e} Seddah, Eric de la Clergerie, Beno{^\i}t Sagot, H{'e}ctor Mart{'\i}nez Alonso, C, Marie ito |
| Abstract | |
| Tasks | Dependency Parsing, Tokenization |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1718/ |
| https://www.aclweb.org/anthology/L18-1718 | |
| PWC | https://paperswithcode.com/paper/cheating-a-parser-to-death-data-driven-cross |
| Repo | |
| Framework | |
TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions
| Title | TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions |
| Authors | Regina Stodden, Behrang QasemiZadeh, Laura Kallmeyer |
| Abstract | We describe the TRAPACC system and its variant TRAPACCS that participated in the closed track of the PARSEME Shared Task 2018 on labeling verbal multiword expressions (VMWEs). TRAPACC is a modified arc-standard transition system based on Constant and Nivre{'}s (2016) model of joint syntactic and lexical analysis in which the oracle is approximated using a classifier. For TRAPACC, the classifier consists of a data-independent dimension reduction and a convolutional neural network (CNN) for learning and labelling transitions. TRAPACCS extends TRAPACC by replacing the softmax layer of the CNN with a support vector machine (SVM). We report the results obtained for 19 languages, for 8 of which our system yields the best results compared to other participating systems in the closed-track of the shared task. |
| Tasks | Dimensionality Reduction, Lexical Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4930/ |
| https://www.aclweb.org/anthology/W18-4930 | |
| PWC | https://paperswithcode.com/paper/trapacc-and-trapaccs-at-parseme-shared-task |
| Repo | |
| Framework | |
Proceedings of the Third Conference on Machine Translation: Shared Task Papers
| Title | Proceedings of the Third Conference on Machine Translation: Shared Task Papers |
| Authors | Ond{\v{r}}ej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aur{'e}lie N{'e}v{'e}ol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W18/W18-6400/ |
| https://www.aclweb.org/anthology/W18-6400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-third-conference-on-2 |
| Repo | |
| Framework | |
FastSense: An Efficient Word Sense Disambiguation Classifier
| Title | FastSense: An Efficient Word Sense Disambiguation Classifier |
| Authors | Tolga Uslu, Alex Mehler, er, Daniel Baumartz, Wahed Hemati |
| Abstract | |
| Tasks | Entity Linking, Text Classification, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1168/ |
| https://www.aclweb.org/anthology/L18-1168 | |
| PWC | https://paperswithcode.com/paper/fastsense-an-efficient-word-sense |
| Repo | |
| Framework | |
Addressing the Winograd Schema Challenge as a Sequence Ranking Task
| Title | Addressing the Winograd Schema Challenge as a Sequence Ranking Task |
| Authors | Juri Opitz, Anette Frank |
| Abstract | The Winograd Schema Challenge targets pronominal anaphora resolution problems which require the application of cognitive inference in combination with world knowledge. These problems are easy to solve for humans but most difficult to solve for machines. Computational models that previously addressed this task rely on syntactic preprocessing and incorporation of external knowledge by manually crafted features. We address the Winograd Schema Challenge from a new perspective as a sequence ranking task, and design a Siamese neural sequence ranking model which performs significantly better than a random baseline, even when solely trained on sequences of words. We evaluate against a baseline and a state-of-the-art system on two data sets and show that anonymization of noun phrase candidates strongly helps our model to generalize. |
| Tasks | Coreference Resolution, Language Modelling |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4105/ |
| https://www.aclweb.org/anthology/W18-4105 | |
| PWC | https://paperswithcode.com/paper/addressing-the-winograd-schema-challenge-as-a |
| Repo | |
| Framework | |
The Mutual Autoencoder: Controlling Information in Latent Code Representations
| Title | The Mutual Autoencoder: Controlling Information in Latent Code Representations |
| Authors | Mary Phuong, Max Welling, Nate Kushman, Ryota Tomioka, Sebastian Nowozin |
| Abstract | Variational autoencoders (VAE) learn probabilistic latent variable models by optimizing a bound on the marginal likelihood of the observed data. Beyond providing a good density model a VAE model assigns to each data instance a latent code. In many applications, this latent code provides a useful high-level summary of the observation. However, the VAE may fail to learn a useful representation when the decoder family is very expressive. This is because maximum likelihood does not explicitly encourage useful representations and the latent variable is used only if it helps model the marginal distribution. This makes representation learning with VAEs unreliable. To address this issue, we propose a method for explicitly controlling the amount of information stored in the latent code. Our method can learn codes ranging from independent to nearly deterministic while benefiting from decoder capacity. Thus, we decouple the choice of decoder capacity and the latent code dimensionality from the amount of information stored in the code. |
| Tasks | Latent Variable Models, Representation Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HkbmWqxCZ |
| https://openreview.net/pdf?id=HkbmWqxCZ | |
| PWC | https://paperswithcode.com/paper/the-mutual-autoencoder-controlling |
| Repo | |
| Framework | |
Changing the Level of Directness in Dialogue using Dialogue Vector Models and Recurrent Neural Networks
| Title | Changing the Level of Directness in Dialogue using Dialogue Vector Models and Recurrent Neural Networks |
| Authors | Louisa Pragst, Stefan Ultes |
| Abstract | In cooperative dialogues, identifying the intent of ones conversation partner and acting accordingly is of great importance. While this endeavour is facilitated by phrasing intentions as directly as possible, we can observe in human-human communication that a number of factors such as cultural norms and politeness may result in expressing one{'}s intent indirectly. Therefore, in human-computer communication we have to anticipate the possibility of users being indirect and be prepared to interpret their actual meaning. Furthermore, a dialogue system should be able to conform to human expectations by adjusting the degree of directness it uses to improve the user experience. To reach those goals, we propose an approach to differentiate between direct and indirect utterances and find utterances of the opposite characteristic that express the same intent. In this endeavour, we employ dialogue vector models and recurrent neural networks. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5002/ |
| https://www.aclweb.org/anthology/W18-5002 | |
| PWC | https://paperswithcode.com/paper/changing-the-level-of-directness-in-dialogue |
| Repo | |
| Framework | |
Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images
| Title | Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images |
| Authors | Keisuke Tateno, Nassir Navab, Federico Tombari |
| Abstract | There is a high demand of 3D data for 360° panoramic images and videos, pushed by the growing availability on the market of specialized hardware for both capturing (e.g., omnidirectional cameras) as well as visualizing in 3D (e.g., head mounted displays) panoramic images and videos. At the same time, 3D sensors able to capture 3D panoramic data are expensive and/or hardly available. To fill this gap, we propose a learning approach for panoramic depth map estimation from a single image. Thanks to a specifically developed distortion-aware deformable convolution filter, our method can be trained by means of conventional perspective images, then used to regress depth for panoramic images, thus bypassing the effort needed to create annotated panoramic training dataset. We also demonstrate our approach for emerging tasks such as panoramic monocular SLAM, panoramic semantic segmentation and panoramic style transfer. |
| Tasks | Semantic Segmentation, Style Transfer |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Keisuke_Tateno_Distortion-Aware_Convolutional_Filters_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Keisuke_Tateno_Distortion-Aware_Convolutional_Filters_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/distortion-aware-convolutional-filters-for |
| Repo | |
| Framework | |
Modeling Linguistic and Personality Adaptation for Natural Language Generation
| Title | Modeling Linguistic and Personality Adaptation for Natural Language Generation |
| Authors | Zhichao Hu, Jean Fox Tree, Marilyn Walker |
| Abstract | Previous work has shown that conversants adapt to many aspects of their partners{'} language. Other work has shown that while every person is unique, they often share general patterns of behavior. Theories of personality aim to explain these shared patterns, and studies have shown that many linguistic cues are correlated with personality traits. We propose an adaptation measure for adaptive natural language generation for dialogs that integrates the predictions of both personality theories and adaptation theories, that can be applied as a dialog unfolds, on a turn by turn basis. We show that our measure meets criteria for validity, and that adaptation varies according to corpora and task, speaker, and the set of features used to model it. We also produce fine-grained models according to the dialog segmentation or the speaker, and demonstrate the decaying trend of adaptation. |
| Tasks | Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5003/ |
| https://www.aclweb.org/anthology/W18-5003 | |
| PWC | https://paperswithcode.com/paper/modeling-linguistic-and-personality |
| Repo | |
| Framework | |
Finite State Reasoning for Presupposition Satisfaction
| Title | Finite State Reasoning for Presupposition Satisfaction |
| Authors | Jacob Collard |
| Abstract | Sentences with presuppositions are often treated as uninterpretable or unvalued (neither true nor false) if their presuppositions are not satisfied. However, there is an open question as to how this satisfaction is calculated. In some cases, determining whether a presupposition is satisfied is not a trivial task (or even a decidable one), yet native speakers are able to quickly and confidently identify instances of presupposition failure. I propose that this can be accounted for with a form of possible world semantics that encapsulates some reasoning abilities, but is limited in its computational power, thus circumventing the need to solve computationally difficult problems. This can be modeled using a variant of the framework of finite state semantics proposed by Rooth (2017). A few modifications to this system are necessary, including its extension into a three-valued logic to account for presupposition. Within this framework, the logic necessary to calculate presupposition satisfaction is readily available, but there is no risk of needing exceptional computational power. This correctly predicts that certain presuppositions will not be calculated intuitively, while others can be easily evaluated. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4106/ |
| https://www.aclweb.org/anthology/W18-4106 | |
| PWC | https://paperswithcode.com/paper/finite-state-reasoning-for-presupposition |
| Repo | |
| Framework | |
Estimating User Interest from Open-Domain Dialogue
| Title | Estimating User Interest from Open-Domain Dialogue |
| Authors | Michimasa Inaba, Kenichi Takahashi |
| Abstract | Dialogue personalization is an important issue in the field of open-domain chat-oriented dialogue systems. If these systems could consider their users{'} interests, user engagement and satisfaction would be greatly improved. This paper proposes a neural network-based method for estimating users{'} interests from their utterances in chat dialogues to personalize dialogue systems{'} responses. We introduce a method for effectively extracting topics and user interests from utterances and also propose a pre-training approach that increases learning efficiency. Our experimental results indicate that the proposed model can estimate user{'}s interest more accurately than baseline approaches. |
| Tasks | Speech Recognition |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5004/ |
| https://www.aclweb.org/anthology/W18-5004 | |
| PWC | https://paperswithcode.com/paper/estimating-user-interest-from-open-domain |
| Repo | |
| Framework | |
