Paper Group NANR 188
Adaptor Grammars for the Linguist: Word Segmentation Experiments for Very Low-Resource Languages. Ternary Twitter Sentiment Classification with Distant Supervision and Sentiment-Specific Word Embeddings. APLenty: annotation tool for creating high-quality datasets using active and proactive learning. From Chinese Word Segmentation to Extraction of C …
Adaptor Grammars for the Linguist: Word Segmentation Experiments for Very Low-Resource Languages
| Title | Adaptor Grammars for the Linguist: Word Segmentation Experiments for Very Low-Resource Languages |
| Authors | Pierre Godard, Laurent Besacier, François Yvon, Martine Adda-Decker, Gilles Adda, Hélène Maynard, Annie Rialland |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/papers/W18-5804/w18-5804 |
| https://www.aclweb.org/anthology/W18-5804 | |
| PWC | https://paperswithcode.com/paper/adaptor-grammars-for-the-linguist-word |
| Repo | |
| Framework | |
Ternary Twitter Sentiment Classification with Distant Supervision and Sentiment-Specific Word Embeddings
| Title | Ternary Twitter Sentiment Classification with Distant Supervision and Sentiment-Specific Word Embeddings |
| Authors | Mats Byrkjeland, Frederik Gørvell de Lichtenberg, Björn Gambäck |
| Abstract | |
| Tasks | Sentiment Analysis, Twitter Sentiment Analysis, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/papers/W18-6215/w18-6215 |
| https://www.aclweb.org/anthology/W18-6215 | |
| PWC | https://paperswithcode.com/paper/ternary-twitter-sentiment-classification-with |
| Repo | |
| Framework | |
APLenty: annotation tool for creating high-quality datasets using active and proactive learning
| Title | APLenty: annotation tool for creating high-quality datasets using active and proactive learning |
| Authors | Minh-Quoc Nghiem, Sophia Ananiadou |
| Abstract | In this paper, we present APLenty, an annotation tool for creating high-quality sequence labeling datasets using active and proactive learning. A major innovation of our tool is the integration of automatic annotation with active learning and proactive learning. This makes the task of creating labeled datasets easier, less time-consuming and requiring less human effort. APLenty is highly flexible and can be adapted to various other tasks. |
| Tasks | Active Learning, Multi-Label Learning, Part-Of-Speech Tagging |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2019/ |
| https://www.aclweb.org/anthology/D18-2019 | |
| PWC | https://paperswithcode.com/paper/aplenty-annotation-tool-for-creating-high |
| Repo | |
| Framework | |
From Chinese Word Segmentation to Extraction of Constructions: Two Sides of the Same Algorithmic Coin
| Title | From Chinese Word Segmentation to Extraction of Constructions: Two Sides of the Same Algorithmic Coin |
| Authors | Jean-Pierre Colson |
| Abstract | This paper presents the results of two experiments carried out within the framework of computational construction grammar. Starting from the constructionist point of view that there are just constructions in language, including lexical ones, we tested the validity of a clustering algorithm that was primarily designed for MWE extraction, the cpr-score (Colson, 2017), on Chinese word segmentation. Our results indicate a striking recall rate of 75 percent without any special adaptation to Chinese or to the lexicon, which confirms that there is some similarity between extracting MWEs and CWS. Our second experiment also suggests that the same methodology might be used for extracting more schematic or abstract constructions, thereby providing evidence for the statistical foundation of construction grammar. |
| Tasks | Chinese Word Segmentation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4907/ |
| https://www.aclweb.org/anthology/W18-4907 | |
| PWC | https://paperswithcode.com/paper/from-chinese-word-segmentation-to-extraction |
| Repo | |
| Framework | |
Complex and Precise Movie and Book Annotations in French Language for Aspect Based Sentiment Analysis
| Title | Complex and Precise Movie and Book Annotations in French Language for Aspect Based Sentiment Analysis |
| Authors | Stefania Pecore, Jeanne Villaneau |
| Abstract | |
| Tasks | Aspect-Based Sentiment Analysis, Opinion Mining, Sentiment Analysis, Subjectivity Analysis, Text Classification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1419/ |
| https://www.aclweb.org/anthology/L18-1419 | |
| PWC | https://paperswithcode.com/paper/complex-and-precise-movie-and-book |
| Repo | |
| Framework | |
Enriching a Lexicon of Discourse Connectives with Corpus-based Data
| Title | Enriching a Lexicon of Discourse Connectives with Corpus-based Data |
| Authors | Anna Feltracco, Elisabetta Jezek, Bernardo Magnini |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1684/ |
| https://www.aclweb.org/anthology/L18-1684 | |
| PWC | https://paperswithcode.com/paper/enriching-a-lexicon-of-discourse-connectives |
| Repo | |
| Framework | |
The First Multilingual Surface Realisation Shared Task (SRâ18): Overview and Evaluation Results
| Title | The First Multilingual Surface Realisation Shared Task (SRâ18): Overview and Evaluation Results |
| Authors | Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Emily Pitler, Leo Wanner |
| Abstract | |
| Tasks | Question Answering, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/papers/W18-3601/w18-3601 |
| https://www.aclweb.org/anthology/W18-3601v2 | |
| PWC | https://paperswithcode.com/paper/the-first-multilingual-surface-realisation |
| Repo | |
| Framework | |
Local Private Hypothesis Testing: Chi-Square Tests
| Title | Local Private Hypothesis Testing: Chi-Square Tests |
| Authors | Marco Gaboardi, Ryan Rogers |
| Abstract | The local model for differential privacy is emerging as the reference model for practical applications of collecting and sharing sensitive information while satisfying strong privacy guarantees. In the local model, there is no trusted entity which is allowed to have each individual’s raw data as is assumed in the traditional curator model. Individuals’ data are usually perturbed before sharing them. We explore the design of private hypothesis tests in the local model, where each data entry is perturbed to ensure the privacy of each participant. Specifically, we analyze locally private chi-square tests for goodness of fit and independence testing. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2346 |
| http://proceedings.mlr.press/v80/gaboardi18a/gaboardi18a.pdf | |
| PWC | https://paperswithcode.com/paper/local-private-hypothesis-testing-chi-square |
| Repo | |
| Framework | |
Interpretable Structure Induction via Sparse Attention
| Title | Interpretable Structure Induction via Sparse Attention |
| Authors | Ben Peters, Vlad Niculae, Andr{'e} F. T. Martins |
| Abstract | Neural network methods are experiencing wide adoption in NLP, thanks to their empirical performance on many tasks. Modern neural architectures go way beyond simple feedforward and recurrent models: they are complex pipelines that perform soft, differentiable computation instead of discrete logic. The price of such soft computing is the introduction of dense dependencies, which make it hard to disentangle the patterns that trigger a prediction. Our recent work on sparse and structured latent computation presents a promising avenue for enhancing interpretability of such neural pipelines. Through this extended abstract, we aim to discuss and explore the potential and impact of our methods. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5450/ |
| https://www.aclweb.org/anthology/W18-5450 | |
| PWC | https://paperswithcode.com/paper/interpretable-structure-induction-via-sparse |
| Repo | |
| Framework | |
Learning an Embedding Space for Transferable Robot Skills
| Title | Learning an Embedding Space for Transferable Robot Skills |
| Authors | Karol Hausman, Jost Tobias Springenberg, Ziyu Wang, Nicolas Heess, Martin Riedmiller |
| Abstract | We present a method for reinforcement learning of closely related skills that are parameterized via a skill embedding space. We learn such skills by taking advantage of latent variables and exploiting a connection between reinforcement learning and variational inference. The main contribution of our work is an entropy-regularized policy gradient formulation for hierarchical policies, and an associated, data-efficient and robust off-policy gradient algorithm based on stochastic value gradients. We demonstrate the effectiveness of our method on several simulated robotic manipulation tasks. We find that our method allows for discovery of multiple solutions and is capable of learning the minimum number of distinct skills that are necessary to solve a given set of tasks. In addition, our results indicate that the hereby proposed technique can interpolate and/or sequence previously learned skills in order to accomplish more complex tasks, even in the presence of sparse rewards. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rk07ZXZRb |
| https://openreview.net/pdf?id=rk07ZXZRb | |
| PWC | https://paperswithcode.com/paper/learning-an-embedding-space-for-transferable |
| Repo | |
| Framework | |
Adversarial Policy Gradient for Alternating Markov Games
| Title | Adversarial Policy Gradient for Alternating Markov Games |
| Authors | Chao Gao, Martin Mueller, Ryan Hayward |
| Abstract | Policy gradient reinforcement learning has been applied to two-player alternate-turn zero-sum games, e.g., in AlphaGo, self-play REINFORCE was used to improve the neural net model after supervised learning. In this paper, we emphasize that two-player zero-sum games with alternating turns, which have been previously formulated as Alternating Markov Games (AMGs), are different from standard MDP because of their two-agent nature. We exploit the difference in associated Bellman equations, which leads to different policy iteration algorithms. As policy gradient method is a kind of generalized policy iteration, we show how these differences in policy iteration are reflected in policy gradient for AMGs. We formulate an adversarial policy gradient and discuss potential possibilities for developing better policy gradient methods other than self-play REINFORCE. The core idea is to estimate the minimum rather than the mean for the “critic”. Experimental results on the game of Hex show the modified Monte Carlo policy gradient methods are able to learn better pure neural net policies than the REINFORCE variants. To apply learned neural weights to multiple board sizes Hex, we describe a board-size independent neural net architecture. We show that when combined with search, using a single neural net model, the resulting program consistently beats MoHex 2.0, the state-of-the-art computer Hex player, on board sizes from 9×9 to 13×13. |
| Tasks | Policy Gradient Methods |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=rJk51gJRb |
| https://openreview.net/pdf?id=rJk51gJRb | |
| PWC | https://paperswithcode.com/paper/adversarial-policy-gradient-for-alternating |
| Repo | |
| Framework | |
Multitask Boosting for Survival Analysis with Competing Risks
| Title | Multitask Boosting for Survival Analysis with Competing Risks |
| Authors | Alexis Bellot, Mihaela Van Der Schaar |
| Abstract | The co-occurrence of multiple diseases among the general population is an important problem as those patients have more risk of complications and represent a large share of health care expenditure. Learning to predict time-to-event probabilities for these patients is a challenging problem because the risks of events are correlated (there are competing risks) with often only few patients experiencing individual events of interest, and of those only a fraction are actually observed in the data. We introduce in this paper a survival model with the flexibility to leverage a common representation of related events that is designed to correct for the strong imbalance in observed outcomes. The procedure is sequential: outcome-specific survival distributions form the components of nonparametric multivariate estimators which we combine into an ensemble in such a way as to ensure accurate predictions on all outcome types simultaneously. Our algorithm is general and represents the first boosting-like method for time-to-event data with multiple outcomes. We demonstrate the performance of our algorithm on synthetic and real data. |
| Tasks | Survival Analysis |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7413-multitask-boosting-for-survival-analysis-with-competing-risks |
| http://papers.nips.cc/paper/7413-multitask-boosting-for-survival-analysis-with-competing-risks.pdf | |
| PWC | https://paperswithcode.com/paper/multitask-boosting-for-survival-analysis-with |
| Repo | |
| Framework | |
Active Matting
| Title | Active Matting |
| Authors | Xin Yang, Ke Xu, Shaozhe Chen, Shengfeng He, Baocai Yin Yin, Rynson Lau |
| Abstract | Image matting is an ill-posed problem. It requires a user input trimap or some strokes to obtain an alpha matte of the foreground object. A fine user input is essential to obtain a good result, which is either time consuming or suitable for experienced users who know where to place the strokes. In this paper, we explore the intrinsic relationship between the user input and the matting algorithm to address the problem of where and when the user should provide the input. Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts. To this end, we propose an active matting method with recurrent reinforcement learning. The proposed framework involves human in the loop by sequentially detecting informative regions for trivial human judgement. Comparing to traditional matting algorithms, the proposed framework requires much less efforts, and can produce satisfactory results with just 10 regions. Through extensive experiments, we show that the proposed model reduces user efforts significantly and achieves comparable performance to dense trimaps in a user-friendly manner. We further show that the learned informative knowledge can be generalized across different matting algorithms. |
| Tasks | Image Matting |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7710-active-matting |
| http://papers.nips.cc/paper/7710-active-matting.pdf | |
| PWC | https://paperswithcode.com/paper/active-matting |
| Repo | |
| Framework | |
3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure Constraints
| Title | 3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure Constraints |
| Authors | Sebastian Bullinger, Christoph Bodensteiner, Michael Arens, Rainer Stiefelhagen |
| Abstract | We present a framework to reconstruct three-dimensional vehicle trajectories using monocular video data. We track two-dimensional vehicle shapes on pixel level exploiting instance-aware semantic segmentation techniques and optical flow cues. We apply Structure from Motion techniques to vehicle and background images to determine for each frame camera poses relative to vehicle instances and background structures. By combining vehicle and background camera pose information, we restrict the vehicle trajectory to a one-parameter family of possible solutions. We compute a ground representation by fusing background structures and corresponding semantic segmentations. We propose a novel method to determine vehicle trajectories consistent to image observations and reconstructed environment structures as well as a criterion to identify frames suitable for scale ratio estimation. We show qualitative results using drone imagery as well as driving sequences from the Cityscape dataset. Due to the lack of suitable benchmark datasets we present a new dataset to evaluate the quality of reconstructed three-dimensional vehicle trajectories. The video sequences show vehicles in urban areas and are rendered using the path-tracing render engine Cycles. In contrast to previous work, we perform a quantitative evaluation of the presented approach. Our algorithm achieves an average reconstruction-to-ground-truth-trajectory distance of 0.31 meter using this dataset. The dataset including evaluation scripts will be publicly available on our website. |
| Tasks | Optical Flow Estimation, Semantic Segmentation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Sebastian_Bullinger_3D_Vehicle_Trajectory_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Sebastian_Bullinger_3D_Vehicle_Trajectory_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/3d-vehicle-trajectory-reconstruction-in |
| Repo | |
| Framework | |
Understanding Grounded Language Learning Agents
| Title | Understanding Grounded Language Learning Agents |
| Authors | Felix Hill, Karl Moritz Hermann, Phil Blunsom, Stephen Clark |
| Abstract | Neural network-based systems can now learn to locate the referents of words and phrases in images, answer questions about visual scenes, and even execute symbolic instructions as first-person actors in partially-observable worlds. To achieve this so-called grounded language learning, models must overcome certain well-studied learning challenges that are also fundamental to infants learning their first words. While it is notable that models with no meaningful prior knowledge overcome these learning obstacles, AI researchers and practitioners currently lack a clear understanding of exactly how they do so. Here we address this question as a way of achieving a clearer general understanding of grounded language learning, both to inform future research and to improve confidence in model predictions. For maximum control and generality, we focus on a simple neural network-based language learning agent trained via policy-gradient methods to interpret synthetic linguistic instructions in a simulated 3D world. We apply experimental paradigms from developmental psychology to this agent, exploring the conditions under which established human biases and learning effects emerge. We further propose a novel way to visualise and analyse semantic representation in grounded language learning agents that yields a plausible computational account of the observed effects. |
| Tasks | Policy Gradient Methods |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ByZmGjkA- |
| https://openreview.net/pdf?id=ByZmGjkA- | |
| PWC | https://paperswithcode.com/paper/understanding-grounded-language-learning-1 |
| Repo | |
| Framework | |
