Paper Group NANR 89
Unsupervised Joint Training of Bilingual Word Embeddings. Learning to Reinforcement Learn by Imitation. ON THE USE OF CONVOLUTIONAL AUTO-ENCODER FOR INCREMENTAL CLASSIFIER LEARNING IN CONTEXT AWARE ADVERTISEMENT. Generative Adversarial Models for Learning Private and Fair Representations. Deep Depth From Aberration Map. SYSTRAN @ WNGT 2019: DGT Tas …
Unsupervised Joint Training of Bilingual Word Embeddings
| Title | Unsupervised Joint Training of Bilingual Word Embeddings |
| Authors | Benjamin Marie, Atsushi Fujita |
| Abstract | State-of-the-art methods for unsupervised bilingual word embeddings (BWE) train a mapping function that maps pre-trained monolingual word embeddings into a bilingual space. Despite its remarkable results, unsupervised mapping is also well-known to be limited by the original dissimilarity between the word embedding spaces to be mapped. In this work, we propose a new approach that trains unsupervised BWE jointly on synthetic parallel data generated through unsupervised machine translation. We demonstrate that existing algorithms that jointly train BWE are very robust to noisy training data and show that unsupervised BWE jointly trained significantly outperform unsupervised mapped BWE in several cross-lingual NLP tasks. |
| Tasks | Machine Translation, Unsupervised Machine Translation, Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1312/ |
| https://www.aclweb.org/anthology/P19-1312 | |
| PWC | https://paperswithcode.com/paper/unsupervised-joint-training-of-bilingual-word |
| Repo | |
| Framework | |
Learning to Reinforcement Learn by Imitation
| Title | Learning to Reinforcement Learn by Imitation |
| Authors | Rosen Kralev, Russell Mendonca, Alvin Zhang, Tianhe Yu, Abhishek Gupta, Pieter Abbeel, Sergey Levine, Chelsea Finn |
| Abstract | Meta-reinforcement learning aims to learn fast reinforcement learning (RL) procedures that can be applied to new tasks or environments. While learning fast RL procedures holds promise for allowing agents to autonomously learn a diverse range of skills, existing methods for learning efficient RL are impractical for real world settings, as they rely on slow reinforcement learning algorithms for meta-training, even when the learned procedures are fast. In this paper, we propose to learn a fast reinforcement learning procedure through supervised imitation of an expert, such that, after meta-learning, an agent can quickly learn new tasks through trial-and-error. Through our proposed method, we show that it is possible to learn fast RL using demonstrations, rather than relying on slow RL, where expert agents can be trained quickly by using privileged information or off-policy RL methods. Our experimental evaluation on a number of complex simulated robotic domains demonstrates that our method can effectively learn to learn from spare rewards and is significantly more efficient than prior meta reinforcement learning algorithms. |
| Tasks | Meta-Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJG1Uo09Fm |
| https://openreview.net/pdf?id=HJG1Uo09Fm | |
| PWC | https://paperswithcode.com/paper/learning-to-reinforcement-learn-by-imitation |
| Repo | |
| Framework | |
ON THE USE OF CONVOLUTIONAL AUTO-ENCODER FOR INCREMENTAL CLASSIFIER LEARNING IN CONTEXT AWARE ADVERTISEMENT
| Title | ON THE USE OF CONVOLUTIONAL AUTO-ENCODER FOR INCREMENTAL CLASSIFIER LEARNING IN CONTEXT AWARE ADVERTISEMENT |
| Authors | Tin Lay Nwe, Shudong Xie, Balaji Nataraj, Yiqun Li, Joo-Hwee Lim |
| Abstract | Context Aware Advertisement (CAA) is a type of advertisement appearing on websites or mobile apps. The advertisement is targeted on specific group of users and/or the content displayed on the websites or apps. This paper focuses on classifying images displayed on the websites by incremental learning classifier with Deep Convolutional Neural Network (DCNN) especially for Context Aware Advertisement (CAA) framework. Incrementally learning new knowledge with DCNN leads to catastrophic forgetting as previously stored information is replaced with new information. To prevent catastrophic forgetting, part of previously learned knowledge should be stored for the life time of incremental classifier. Storing information for life time involves privacy and legal concerns especially in context aware advertising framework. Here, we propose an incremental classifier learning method which addresses privacy and legal concerns while taking care of catastrophic forgetting problem. We conduct experiments on different datasets including CIFAR-100. Experimental results show that proposed system achieves relatively high performance compared to the state-of-the-art incremental learning methods. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJeEqiC5KQ |
| https://openreview.net/pdf?id=rJeEqiC5KQ | |
| PWC | https://paperswithcode.com/paper/on-the-use-of-convolutional-auto-encoder-for |
| Repo | |
| Framework | |
Generative Adversarial Models for Learning Private and Fair Representations
| Title | Generative Adversarial Models for Learning Private and Fair Representations |
| Authors | Chong Huang, Xiao Chen, Peter Kairouz, Lalitha Sankar, Ram Rajagopal |
| Abstract | We present Generative Adversarial Privacy and Fairness (GAPF), a data-driven framework for learning private and fair representations of the data. GAPF leverages recent advances in adversarial learning to allow a data holder to learn “universal” representations that decouple a set of sensitive attributes from the rest of the dataset. Under GAPF, finding the optimal decorrelation scheme is formulated as a constrained minimax game between a generative decorrelator and an adversary. We show that for appropriately chosen adversarial loss functions, GAPF provides privacy guarantees against strong information-theoretic adversaries and enforces demographic parity. We also evaluate the performance of GAPF on multi-dimensional Gaussian mixture models and real datasets, and show how a designer can certify that representations learned under an adversary with a fixed architecture perform well against more complex adversaries. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1xAH2RqK7 |
| https://openreview.net/pdf?id=H1xAH2RqK7 | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-models-for-learning |
| Repo | |
| Framework | |
Deep Depth From Aberration Map
| Title | Deep Depth From Aberration Map |
| Authors | Masako Kashiwagi, Nao Mishima, Tatsuo Kozakaya, Shinsaku Hiura |
| Abstract | Passive and convenient depth estimation from single-shot image is still an open problem. Existing depth from defocus methods require multiple input images or special hardware customization. Recent deep monocular depth estimation is also limited to an image with sufficient contextual information. In this work, we propose a novel method which realizes a single-shot deep depth measurement based on physical depth cue using only an off-the-shelf camera and lens. When a defocused image is taken by a camera, it contains various types of aberrations corresponding to distances from the image sensor and positions in the image plane. We call these minute and complexly compound aberrations as Aberration Map (A-Map) and we found that A-Map can be utilized as reliable physical depth cue. Additionally, our deep network named A-Map Analysis Network (AMA-Net) is also proposed, which can effectively learn and estimate depth via A-Map. To evaluate validity and robustness of our approach, we have conducted extensive experiments using both real outdoor scenes and simulated images. The qualitative result shows the accuracy and availability of the method in comparison with a state-of-the-art deep context-based method. |
| Tasks | Depth Estimation, Monocular Depth Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Kashiwagi_Deep_Depth_From_Aberration_Map_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Kashiwagi_Deep_Depth_From_Aberration_Map_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-depth-from-aberration-map |
| Repo | |
| Framework | |
SYSTRAN @ WNGT 2019: DGT Task
| Title | SYSTRAN @ WNGT 2019: DGT Task |
| Authors | Li Gong, Josep Crego, Jean Senellart |
| Abstract | This paper describes SYSTRAN participation to the Document-level Generation and Trans- lation (DGT) Shared Task of the 3rd Workshop on Neural Generation and Translation (WNGT 2019). We participate for the first time using a Transformer network enhanced with modified input embeddings and optimising an additional objective function that considers content selection. The network takes in structured data of basketball games and outputs a summary of the game in natural language. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5629/ |
| https://www.aclweb.org/anthology/D19-5629 | |
| PWC | https://paperswithcode.com/paper/systran-wngt-2019-dgt-task |
| Repo | |
| Framework | |
The Swedish PoliGraph: A Semantic Graph for Argument Mining of Swedish Parliamentary Data
| Title | The Swedish PoliGraph: A Semantic Graph for Argument Mining of Swedish Parliamentary Data |
| Authors | Stian R{\o}dven Eide |
| Abstract | As part of a larger project on argument mining of Swedish parliamentary data, we have created a semantic graph that, together with named entity recognition and resolution (NER), should make it easier to establish connections between arguments in a given debate. The graph is essentially a semantic database that keeps track of Members of Parliament (MPs), in particular their presence in the parliament and activity in debates, but also party affiliation and participation in commissions. The hope is that the Swedish PoliGraph will enable us to perform named entity resolution on debates in the Swedish parliament with a high accuracy, with the aim of determining to whom an argument is directed. |
| Tasks | Argument Mining, Entity Resolution, Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4506/ |
| https://www.aclweb.org/anthology/W19-4506 | |
| PWC | https://paperswithcode.com/paper/the-swedish-poligraph-a-semantic-graph-for |
| Repo | |
| Framework | |
Hotel Scribe: Generating High Variation Hotel Descriptions
| Title | Hotel Scribe: Generating High Variation Hotel Descriptions |
| Authors | Saad Mahamood, Maciej Zembrzuski |
| Abstract | This paper describes the implementation of the Hotel Scribe system. A commercial Natural Language Generation (NLG) system which generates descriptions of hotels from accommodation metadata with a high level of content and linguistic variation in English. It has been deployed live by Anonymised Company Name for the purpose of improving coverage of accommodation descriptions and for Search Engine Optimisation (SEO). In this paper, we describe the motivation for building this system, the challenges faced when dealing with limited metadata, and the implementation used to generate the highly variate accommodation descriptions. Additionally, we evaluate the uniqueness of the texts generated by our system against comparable human written accommodation description texts. |
| Tasks | Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8647/ |
| https://www.aclweb.org/anthology/W19-8647 | |
| PWC | https://paperswithcode.com/paper/hotel-scribe-generating-high-variation-hotel |
| Repo | |
| Framework | |
The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations
| Title | The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations |
| Authors | Jacopo Amidei, Paul Piwek, Alistair Willis |
| Abstract | Rating and Likert scales are widely used in evaluation experiments to measure the quality of Natural Language Generation (NLG) systems. We review the use of rating and Likert scales for NLG evaluation tasks published in NLG specialized conferences over the last ten years (135 papers in total). Our analysis brings to light a number of deviations from good practice in their use. We conclude with some recommendations about the use of such scales. Our aim is to encourage the appropriate use of evaluation methodologies in the NLG community. |
| Tasks | Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8648/ |
| https://www.aclweb.org/anthology/W19-8648 | |
| PWC | https://paperswithcode.com/paper/the-use-of-rating-and-likert-scales-in |
| Repo | |
| Framework | |
Robust Representation Learning of Biomedical Names
| Title | Robust Representation Learning of Biomedical Names |
| Authors | Minh C. Phan, Aixin Sun, Yi Tay |
| Abstract | Biomedical concepts are often mentioned in medical documents under different name variations (synonyms). This mismatch between surface forms is problematic, resulting in difficulties pertaining to learning effective representations. Consequently, this has tremendous implications such as rendering downstream applications inefficacious and/or potentially unreliable. This paper proposes a new framework for learning robust representations of biomedical names and terms. The idea behind our approach is to consider and encode contextual meaning, conceptual meaning, and the similarity between synonyms during the representation learning process. Via extensive experiments, we show that our proposed method outperforms other baselines on a battery of retrieval, similarity and relatedness benchmarks. Moreover, our proposed method is also able to compute meaningful representations for unseen names, resulting in high practical utility in real-world applications. |
| Tasks | Representation Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1317/ |
| https://www.aclweb.org/anthology/P19-1317 | |
| PWC | https://paperswithcode.com/paper/robust-representation-learning-of-biomedical |
| Repo | |
| Framework | |
B. Rex: a dialogue agent for book recommendations
| Title | B. Rex: a dialogue agent for book recommendations |
| Authors | Mitchell Abrams, Luke Gessler, Matthew Marge |
| Abstract | We present B. Rex, a dialogue agent for book recommendations. B. Rex aims to exploit the cognitive ease of natural dialogue and the excitement of a whimsical persona in order to engage users who might not enjoy using more common interfaces for finding new books. B. Rex succeeds in making book recommendations with good quality based on only information revealed by the user in the dialogue. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5948/ |
| https://www.aclweb.org/anthology/W19-5948 | |
| PWC | https://paperswithcode.com/paper/b-rex-a-dialogue-agent-for-book |
| Repo | |
| Framework | |
Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response
| Title | Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response |
| Authors | Tatiana Anikina, Ivana Kruijff-Korbayova |
| Abstract | We present the results we obtained on the classification of dialogue acts in a corpus of human-human team communication in the domain of robot-assisted disaster response. We annotated dialogue acts according to the ISO 24617-2 standard scheme and carried out experiments using the FastText linear classifier as well as several neural architectures, including feed-forward, recurrent and convolutional neural models with different types of embeddings, context and attention mechanism. The best performance was achieved with a {''}Divide {&} Merge{''} architecture presented in the paper, using trainable GloVe embeddings and a structured dialogue history. This model learns from the current utterance and the preceding context separately and then combines the two generated representations. Average accuracy of 10-fold cross-validation is 79.8{%}, F-score 71.8{%}. |
| Tasks | Dialogue Act Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5946/ |
| https://www.aclweb.org/anthology/W19-5946 | |
| PWC | https://paperswithcode.com/paper/dialogue-act-classification-in-team |
| Repo | |
| Framework | |
Neural Variational Inference For Embedding Knowledge Graphs
| Title | Neural Variational Inference For Embedding Knowledge Graphs |
| Authors | Alexander I. Cowen-Rivers, Pasquale Minervini |
| Abstract | Recent advances in Neural Variational Inference allowed for a renaissance in latent variable models in a variety of domains involving high-dimensional data. In this paper, we introduce two generic Variational Inference frameworks for generative models of Knowledge Graphs; Latent Fact Model and Latent Information Model. While traditional variational methods derive an analytical approximation for the intractable distribution over the latent variables, here we construct an inference network conditioned on the symbolic representation of entities and relation types in the Knowledge Graph, to provide the variational distributions. The new framework can create models able to discover underlying probabilistic semantics for the symbolic representation by utilising parameterisable distributions which permit training by back-propagation in the context of neural variational inference, resulting in a highly-scalable method. Under a Bernoulli sampling framework, we provide an alternative justification for commonly used techniques in large-scale stochastic variational inference, which drastically reduces training time at a cost of an additional approximation to the variational lower bound. The generative frameworks are flexible enough to allow training under any prior distribution that permits a re-parametrisation trick, as well as under any scoring function that permits maximum likelihood estimation of the parameters. Experiment results display the potential and efficiency of this framework by improving upon multiple benchmarks with Gaussian prior representations. Code publicly available on Github. |
| Tasks | Knowledge Graphs, Latent Variable Models |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJM4rsRqFX |
| https://openreview.net/pdf?id=HJM4rsRqFX | |
| PWC | https://paperswithcode.com/paper/neural-variational-inference-for-embedding |
| Repo | |
| Framework | |
Laplace Landmark Localization
| Title | Laplace Landmark Localization |
| Authors | Joseph P. Robinson, Yuncheng Li, Ning Zhang, Yun Fu, Sergey Tulyakov |
| Abstract | Landmark localization in images and videos is a classic problem solved in various ways. Nowadays, with deep networks prevailing throughout machine learning, there are revamped interests in pushing facial landmark detectors to handle more challenging data. Most efforts use network objectives based on L1 or L2 norms, which have several disadvantages. First of all, the generated heatmaps translate to the locations of landmarks (i.e. confidence maps) from which predicted landmark locations (i.e. the means) get penalized without accounting for the spread: a high- scatter corresponds to low confidence and vice-versa. For this, we introduce a LaplaceKL objective that penalizes for low confidence. Another issue is a dependency on labeled data, which are expensive to obtain and susceptible to error. To address both issues, we propose an adversarial training framework that leverages unlabeled data to improve model performance. Our method claims state-of-the-art on all of the 300W benchmarks and ranks second-to-best on the Annotated Facial Landmarks in the Wild (AFLW) dataset. Furthermore, our model is robust with a reduced size: 1/8 the number of channels (i.e. 0.0398 MB) is comparable to the state-of-the-art in real-time on CPU. Thus, this work is of high practical value to real-life application. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Robinson_Laplace_Landmark_Localization_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Robinson_Laplace_Landmark_Localization_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/laplace-landmark-localization-1 |
| Repo | |
| Framework | |
Identifying therapist conversational actions across diverse psychotherapeutic approaches
| Title | Identifying therapist conversational actions across diverse psychotherapeutic approaches |
| Authors | Fei-Tzin Lee, Derrick Hull, Jacob Levine, Bonnie Ray, Kathy McKeown |
| Abstract | While conversation in therapy sessions can vary widely in both topic and style, an understanding of the underlying techniques used by therapists can provide valuable insights into how therapists best help clients of different types. Dialogue act classification aims to identify the conversational {``}action{''} each speaker takes at each utterance, such as sympathizing, problem-solving or assumption checking. We propose to apply dialogue act classification to therapy transcripts, using a therapy-specific labeling scheme, in order to gain a high-level understanding of the flow of conversation in therapy sessions. We present a novel annotation scheme that spans multiple psychotherapeutic approaches, apply it to a large and diverse corpus of psychotherapy transcripts, and present and discuss classification results obtained using both SVM and neural network-based models. The results indicate that identifying the structure and flow of therapeutic actions is an obtainable goal, opening up the opportunity in the future to provide therapeutic recommendations tailored to specific client situations. | |
| Tasks | Dialogue Act Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3002/ |
| https://www.aclweb.org/anthology/W19-3002 | |
| PWC | https://paperswithcode.com/paper/identifying-therapist-conversational-actions |
| Repo | |
| Framework | |
