Paper Group NANR 94
In your wildest dreams: the language and psychological features of dreams. Unsupervised Morpheme Segmentation Through Numerical Weighting and Thresholding. Runtime Neural Pruning. The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes. Spectral Analysis of Information Density in Dialogue Predicts Collaborative Task Performance. Ha …
In your wildest dreams: the language and psychological features of dreams
| Title | In your wildest dreams: the language and psychological features of dreams |
| Authors | Kate Niederhoffer, Jonathan Schler, Patrick Crutchley, Kate Loveys, Glen Coppersmith |
| Abstract | In this paper, we provide the first quantified exploration of the structure of the language of dreams, their linguistic style and emotional content. We present a collection of digital dream logs as a viable corpus for the growing study of mental health through the lens of language, complementary to the work done examining more traditional social media. This paper is largely exploratory in nature to lay the groundwork for subsequent research in mental health, rather than optimizing a particular text classification task. |
| Tasks | Decision Making, Text Classification |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3102/ |
| https://www.aclweb.org/anthology/W17-3102 | |
| PWC | https://paperswithcode.com/paper/in-your-wildest-dreams-the-language-and |
| Repo | |
| Framework | |
Unsupervised Morpheme Segmentation Through Numerical Weighting and Thresholding
| Title | Unsupervised Morpheme Segmentation Through Numerical Weighting and Thresholding |
| Authors | Joy Mahapatra, Sudip Kumar Naskar |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7537/ |
| https://www.aclweb.org/anthology/W17-7537 | |
| PWC | https://paperswithcode.com/paper/unsupervised-morpheme-segmentation-through |
| Repo | |
| Framework | |
Runtime Neural Pruning
| Title | Runtime Neural Pruning |
| Authors | Ji Lin, Yongming Rao, Jiwen Lu, Jie Zhou |
| Abstract | In this paper, we propose a Runtime Neural Pruning (RNP) framework which prunes the deep neural network dynamically at the runtime. Unlike existing neural pruning methods which produce a fixed pruned model for deployment, our method preserves the full ability of the original network and conducts pruning according to the input image and current feature maps adaptively. The pruning is performed in a bottom-up, layer-by-layer manner, which we model as a Markov decision process and use reinforcement learning for training. The agent judges the importance of each convolutional kernel and conducts channel-wise pruning conditioned on different samples, where the network is pruned more when the image is easier for the task. Since the ability of network is fully preserved, the balance point is easily adjustable according to the available resources. Our method can be applied to off-the-shelf network structures and reach a better tradeoff between speed and accuracy, especially with a large pruning rate. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6813-runtime-neural-pruning |
| http://papers.nips.cc/paper/6813-runtime-neural-pruning.pdf | |
| PWC | https://paperswithcode.com/paper/runtime-neural-pruning |
| Repo | |
| Framework | |
The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes
| Title | The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes |
| Authors | Gerhard Neuhold, Tobias Ollmann, Samuel Rota Bulo, Peter Kontschieder |
| Abstract | The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25,000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes. Annotation is performed in a dense and fine-grained style by using polygons for delineating individual objects. Our dataset is 5x larger than the total amount of fine annotations for Cityscapes and contains images from all around the world, captured at various conditions regarding weather, season and daytime. Images come from different imaging devices (mobile phones, tablets, action cameras, professional capturing rigs) and differently experienced photographers. In such a way, our dataset has been designed and compiled to cover diversity, richness of detail and geographic extent. As default benchmark tasks, we define semantic image segmentation and instance-specific image segmentation, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding. |
| Tasks | Instance Segmentation, Scene Understanding, Semantic Segmentation |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Neuhold_The_Mapillary_Vistas_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Neuhold_The_Mapillary_Vistas_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/the-mapillary-vistas-dataset-for-semantic |
| Repo | |
| Framework | |
Spectral Analysis of Information Density in Dialogue Predicts Collaborative Task Performance
| Title | Spectral Analysis of Information Density in Dialogue Predicts Collaborative Task Performance |
| Authors | Yang Xu, David Reitter |
| Abstract | We propose a perspective on dialogue that focuses on relative information contributions of conversation partners as a key to successful communication. We predict the success of collaborative task in English and Danish corpora of task-oriented dialogue. Two features are extracted from the frequency domain representations of the lexical entropy series of each interlocutor, power spectrum overlap (PSO) and relative phase (RP). We find that PSO is a negative predictor of task success, while RP is a positive one. An SVM with these features significantly improved on previous task success prediction models. Our findings suggest that the strategic distribution of information density between interlocutors is relevant to task success. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1058/ |
| https://www.aclweb.org/anthology/P17-1058 | |
| PWC | https://paperswithcode.com/paper/spectral-analysis-of-information-density-in |
| Repo | |
| Framework | |
Hafez: an Interactive Poetry Generation System
| Title | Hafez: an Interactive Poetry Generation System |
| Authors | Marjan Ghazvininejad, Xing Shi, Jay Priyadarshi, Kevin Knight |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4008/ |
| https://www.aclweb.org/anthology/P17-4008 | |
| PWC | https://paperswithcode.com/paper/hafez-an-interactive-poetry-generation-system |
| Repo | |
| Framework | |
Implicitly-Defined Neural Networks for Sequence Labeling
| Title | Implicitly-Defined Neural Networks for Sequence Labeling |
| Authors | Michaeel Kazi, Brian Thompson |
| Abstract | In this work, we propose a novel, implicitly-defined neural network architecture and describe a method to compute its components. The proposed architecture forgoes the causality assumption used to formulate recurrent neural networks and instead couples the hidden states of the network, allowing improvement on problems with complex, long-distance dependencies. Initial experiments demonstrate the new architecture outperforms both the Stanford Parser and baseline bidirectional networks on the Penn Treebank Part-of-Speech tagging task and a baseline bidirectional network on an additional artificial random biased walk task. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2027/ |
| https://www.aclweb.org/anthology/P17-2027 | |
| PWC | https://paperswithcode.com/paper/implicitly-defined-neural-networks-for |
| Repo | |
| Framework | |
Towards interoperable annotation of quantification
| Title | Towards interoperable annotation of quantification |
| Authors | Harry Bunt |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7409/ |
| https://www.aclweb.org/anthology/W17-7409 | |
| PWC | https://paperswithcode.com/paper/towards-interoperable-annotation-of |
| Repo | |
| Framework | |
Hunter MT: A Course for Young Researchers in WMT17
| Title | Hunter MT: A Course for Young Researchers in WMT17 |
| Authors | Jia Xu, Yi Zong Kuang, Shondell Baijoo, Jacob Hyun Lee, Uman Shahzad, Mir Ahmed, Meredith Lancaster, Chris Carlan |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4744/ |
| https://www.aclweb.org/anthology/W17-4744 | |
| PWC | https://paperswithcode.com/paper/hunter-mt-a-course-for-young-researchers-in |
| Repo | |
| Framework | |
An Ontology-Based Method for Extracting and Classifying Domain-Specific Compositional Nominal Compounds
| Title | An Ontology-Based Method for Extracting and Classifying Domain-Specific Compositional Nominal Compounds |
| Authors | Maria Pia di Buono |
| Abstract | In this paper, we present our preliminary study on an ontology-based method to extract and classify compositional nominal compounds in specific domains of knowledge. This method is based on the assumption that, applying a conceptual model to represent knowledge domain, it is possible to improve the extraction and classification of lexicon occurrences for that domain in a semi-automatic way. We explore the possibility of extracting and classifying a specific construction type (nominal compounds) spanning a specific domain (Cultural Heritage) and a specific language (Italian). |
| Tasks | Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2211/ |
| https://www.aclweb.org/anthology/W17-2211 | |
| PWC | https://paperswithcode.com/paper/an-ontology-based-method-for-extracting-and |
| Repo | |
| Framework | |
Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning
| Title | Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning |
| Authors | Lu Chen, Xiang Zhou, Cheng Chang, Runzhe Yang, Kai Yu |
| Abstract | Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy. The rule-based policy is often reliable within predefined scope but not self-adaptable, whereas RL is evolvable with data but often suffers from a bad initial performance. We employ a \textit{companion learning} framework to integrate the two approaches for \textit{on-line} dialogue policy learning, in which a pre-defined rule-based policy acts as a {``}teacher{''} and guides a data-driven RL system by giving example actions as well as additional rewards. A novel \textit{agent-aware dropout} Deep Q-Network (AAD-DQN) is proposed to address the problem of when to consult the teacher and how to learn from the teacher{'}s experiences. AAD-DQN, as a data-driven student policy, provides (1) two separate experience memories for student and teacher, (2) an uncertainty estimated by dropout to control the timing of consultation and learning. Simulation experiments showed that the proposed approach can significantly improve both \textit{safety}and \textit{efficiency} of on-line policy optimization compared to other companion learning approaches as well as supervised pre-training using static dialogue corpus. | |
| Tasks | Dialogue Management, Speech Recognition, Spoken Dialogue Systems, Spoken Language Understanding |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1260/ |
| https://www.aclweb.org/anthology/D17-1260 | |
| PWC | https://paperswithcode.com/paper/agent-aware-dropout-dqn-for-safe-and |
| Repo | |
| Framework | |
Learning to Aggregate Ordinal Labels by Maximizing Separating Width
| Title | Learning to Aggregate Ordinal Labels by Maximizing Separating Width |
| Authors | Guangyong Chen, Shengyu Zhang, Di Lin, Hui Huang, Pheng Ann Heng |
| Abstract | While crowdsourcing has been a cost and time efficient method to label massive samples, one critical issue is quality control, for which the key challenge is to infer the ground truth from noisy or even adversarial data by various users. A large class of crowdsourcing problems, such as those involving age, grade, level, or stage, have an ordinal structure in their labels. Based on a technique of sampling estimated label from the posterior distribution, we define a novel separating width among the labeled observations to characterize the quality of sampled labels, and develop an efficient algorithm to optimize it through solving multiple linear decision boundaries and adjusting prior distributions. Our algorithm is empirically evaluated on several real world datasets, and demonstrates its supremacy over state-of-the-art methods. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=503 |
| http://proceedings.mlr.press/v70/chen17i/chen17i.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-aggregate-ordinal-labels-by |
| Repo | |
| Framework | |
Innovation Pursuit: A New Approach to the Subspace Clustering Problem
| Title | Innovation Pursuit: A New Approach to the Subspace Clustering Problem |
| Authors | Mostafa Rahmani, George Atia |
| Abstract | This paper presents a new scalable approach, termed Innovation Pursuit (iPursuit), to the problem of subspace clustering. iPursuit rests on a new geometrical idea whereby each subspace is identified based on its novelty with respect to the other subspaces. The subspaces are identified consecutively by solving a series of simple linear optimization problems, each searching for a direction of innovation in the span of the data. A detailed mathematical analysis is provided establishing sufficient conditions for the proposed approach to correctly cluster the data points. Moreover, the proposed direction search approach can be integrated with spectral clustering to yield a new variant of spectral-clustering-based algorithms. Remarkably, the proposed approach can provably yield exact clustering even when the subspaces have significant intersections. The numerical simulations demonstrate that iPursuit can often outperform the state-of-the-art subspace clustering algorithms – more so for subspaces with significant intersections – along with substantial reductions in computational complexity. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=579 |
| http://proceedings.mlr.press/v70/rahmani17b/rahmani17b.pdf | |
| PWC | https://paperswithcode.com/paper/innovation-pursuit-a-new-approach-to-the |
| Repo | |
| Framework | |
The Scope and Focus of Negation: A Complete Annotation Framework for Italian
| Title | The Scope and Focus of Negation: A Complete Annotation Framework for Italian |
| Authors | Bego{~n}a Altuna, Anne-Lyse Minard, Manuela Speranza |
| Abstract | In this paper we present a complete framework for the annotation of negation in Italian, which accounts for both negation scope and negation focus, and also for language-specific phenomena such as negative concord. In our view, the annotation of negation complements more comprehensive Natural Language Processing tasks, such as temporal information processing and sentiment analysis. We applied the proposed framework and the guidelines built on top of it to the annotation of written texts, namely news articles and tweets, thus producing annotated data for a total of over 36,000 tokens. |
| Tasks | Decision Making, Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1806/ |
| https://www.aclweb.org/anthology/W17-1806 | |
| PWC | https://paperswithcode.com/paper/the-scope-and-focus-of-negation-a-complete |
| Repo | |
| Framework | |
Online Learning of Task-specific Word Representations with a Joint Biconvex Passive-Aggressive Algorithm
| Title | Online Learning of Task-specific Word Representations with a Joint Biconvex Passive-Aggressive Algorithm |
| Authors | Pascal Denis, Liva Ralaivola |
| Abstract | This paper presents a new, efficient method for learning task-specific word vectors using a variant of the Passive-Aggressive algorithm. Specifically, this algorithm learns a word embedding matrix in tandem with the classifier parameters in an online fashion, solving a bi-convex constrained optimization at each iteration. We provide a theoretical analysis of this new algorithm in terms of regret bounds, and evaluate it on both synthetic data and NLP classification problems, including text classification and sentiment analysis. In the latter case, we compare various pre-trained word vectors to initialize our word embedding matrix, and show that the matrix learned by our algorithm vastly outperforms the initial matrix, with performance results comparable or above the state-of-the-art on these tasks. |
| Tasks | Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1073/ |
| https://www.aclweb.org/anthology/E17-1073 | |
| PWC | https://paperswithcode.com/paper/online-learning-of-task-specific-word |
| Repo | |
| Framework | |
