Paper Group NANR 191
Graph Methods for Multilingual FrameNets. Improving Sequence to Sequence Neural Machine Translation by Utilizing Syntactic Dependency Information. Compositionality in Verb-Particle Constructions. Learning to Score System Summaries for Better Content Selection Evaluation.. Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objectiv …
Graph Methods for Multilingual FrameNets
| Title | Graph Methods for Multilingual FrameNets |
| Authors | Collin Baker, Michael Ellsworth |
| Abstract | This paper introduces a new, graph-based view of the data of the FrameNet project, which we hope will make it easier to understand the mixture of semantic and syntactic information contained in FrameNet annotation. We show how English FrameNet and other Frame Semantic resources can be represented as sets of interconnected graphs of frames, frame elements, semantic types, and annotated instances of them in text. We display examples of the new graphical representation based on the annotations, which combine Frame Semantics and Construction Grammar, thus capturing most of the syntax and semantics of each sentence. We consider how graph theory could help researchers to make better use of FrameNet data for tasks such as automatic Frame Semantic role labeling, paraphrasing, and translation. Finally, we describe the development of FrameNet-like lexical resources for other languages in the current Multilingual FrameNet project. which seeks to discover cross-lingual alignments, both in the lexicon (for frames and lexical units within frames) and across parallel or comparable texts. We conclude with an example showing graphically the semantic and syntactic similarities and differences between parallel sentences in English and Japanese. We will release software for displaying such graphs from the current data releases. |
| Tasks | Semantic Role Labeling |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2406/ |
| https://www.aclweb.org/anthology/W17-2406 | |
| PWC | https://paperswithcode.com/paper/graph-methods-for-multilingual-framenets |
| Repo | |
| Framework | |
Improving Sequence to Sequence Neural Machine Translation by Utilizing Syntactic Dependency Information
| Title | Improving Sequence to Sequence Neural Machine Translation by Utilizing Syntactic Dependency Information |
| Authors | An Nguyen Le, Ander Martinez, Akifumi Yoshimoto, Yuji Matsumoto |
| Abstract | Sequence to Sequence Neural Machine Translation has achieved significant performance in recent years. Yet, there are some existing issues that Neural Machine Translation still does not solve completely. Two of them are translation for long sentences and the {``}over-translation{''}. To address these two problems, we propose an approach that utilize more grammatical information such as syntactic dependencies, so that the output can be generated based on more abundant information. In our approach, syntactic dependencies is employed in decoding. In addition, the output of the model is presented not as a simple sequence of tokens but as a linearized tree construction. In order to assess the performance, we construct model based on an attention mechanism encoder-decoder model in which the source language is input to the encoder as a sequence and the decoder generates the target language as a linearized dependency tree structure. Experiments on the Europarl-v7 dataset of French-to-English translation demonstrate that our proposed method improves BLEU scores by 1.57 and 2.40 on datasets consisting of sentences with up to 50 and 80 tokens, respectively. Furthermore, the proposed method also solved the two existing problems, ineffective translation for long sentences and over-translation in Neural Machine Translation. | |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1003/ |
| https://www.aclweb.org/anthology/I17-1003 | |
| PWC | https://paperswithcode.com/paper/improving-sequence-to-sequence-neural-machine |
| Repo | |
| Framework | |
Compositionality in Verb-Particle Constructions
| Title | Compositionality in Verb-Particle Constructions |
| Authors | Archna Bhatia, Choh Man Teng, James Allen |
| Abstract | We are developing a broad-coverage deep semantic lexicon for a system that parses sentences into a logical form expressed in a rich ontology that supports reasoning. In this paper we look at verb-particle constructions (VPCs), and the extent to which they can be treated compositionally vs idiomatically. First we distinguish between the different types of VPCs based on their compositionality and then present a set of heuristics for classifying specific instances as compositional or not. We then identify a small set of general sense classes for particles when used compositionally and discuss the resulting lexical representations that are being added to the lexicon. By treating VPCs as compositional whenever possible, we attain broad coverage in a compact way, and also enable interpretations of novel VPC usages not explicitly present in the lexicon. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1719/ |
| https://www.aclweb.org/anthology/W17-1719 | |
| PWC | https://paperswithcode.com/paper/compositionality-in-verb-particle |
| Repo | |
| Framework | |
Learning to Score System Summaries for Better Content Selection Evaluation.
| Title | Learning to Score System Summaries for Better Content Selection Evaluation. |
| Authors | Maxime Peyrard, Teresa Botschen, Iryna Gurevych |
| Abstract | The evaluation of summaries is a challenging but crucial task of the summarization field. In this work, we propose to learn an automatic scoring metric based on the human judgements available as part of classical summarization datasets like TAC-2008 and TAC-2009. Any existing automatic scoring metrics can be included as features, the model learns the combination exhibiting the best correlation with human judgments. The reliability of the new metric is tested in a further manual evaluation where we ask humans to evaluate summaries covering the whole scoring spectrum of the metric. We release the trained metric as an open-source tool. |
| Tasks | Document Summarization, Multi-Document Summarization, Semantic Textual Similarity |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4510/ |
| https://www.aclweb.org/anthology/W17-4510 | |
| PWC | https://paperswithcode.com/paper/learning-to-score-system-summaries-for-better |
| Repo | |
| Framework | |
Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function
| Title | Information-Theory Interpretation of the Skip-Gram Negative-Sampling Objective Function |
| Authors | Oren Melamud, Jacob Goldberger |
| Abstract | In this paper we define a measure of dependency between two random variables, based on the Jensen-Shannon (JS) divergence between their joint distribution and the product of their marginal distributions. Then, we show that word2vec{'}s skip-gram with negative sampling embedding algorithm finds the optimal low-dimensional approximation of this JS dependency measure between the words and their contexts. The gap between the optimal score and the low-dimensional approximation is demonstrated on a standard text corpus. |
| Tasks | Dependency Parsing, Entity Extraction, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2026/ |
| https://www.aclweb.org/anthology/P17-2026 | |
| PWC | https://paperswithcode.com/paper/information-theory-interpretation-of-the-skip |
| Repo | |
| Framework | |
Co-PoeTryMe: a Co-Creative Interface for the Composition of Poetry
| Title | Co-PoeTryMe: a Co-Creative Interface for the Composition of Poetry |
| Authors | Hugo Gon{\c{c}}alo Oliveira, Tiago Mendes, Ana Boavida |
| Abstract | Co-PoeTryMe is a web application for poetry composition, guided by the user, though with the help of automatic features, such as the generation of full (editable) drafts, as well as the acquisition of additional well-formed lines, or semantically-related words, possibly constrained by the number of syllables, rhyme, or polarity. Towards the final poem, the latter can replace lines or words in the draft. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3508/ |
| https://www.aclweb.org/anthology/W17-3508 | |
| PWC | https://paperswithcode.com/paper/co-poetryme-a-co-creative-interface-for-the |
| Repo | |
| Framework | |
Learning Latent Space Models with Angular Constraints
| Title | Learning Latent Space Models with Angular Constraints |
| Authors | Pengtao Xie, Yuntian Deng, Yi Zhou, Abhimanu Kumar, Yaoliang Yu, James Zou, Eric P. Xing |
| Abstract | The large model capacity of latent space models (LSMs) enables them to achieve great performance on various applications, but meanwhile renders LSMs to be prone to overfitting. Several recent studies investigate a new type of regularization approach, which encourages components in LSMs to be diverse, for the sake of alleviating overfitting. While they have shown promising empirical effectiveness, in theory why larger “diversity” results in less overfitting is still unclear. To bridge this gap, we propose a new diversity-promoting approach that is both theoretically analyzable and empirically effective. Specifically, we use near-orthogonality to characterize “diversity” and impose angular constraints (ACs) on the components of LSMs to promote diversity. A generalization error analysis shows that larger diversity results in smaller estimation error and larger approximation error. An efficient ADMM algorithm is developed to solve the constrained LSM problems. Experiments demonstrate that ACs improve generalization performance of LSMs and outperform other diversity-promoting approaches. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=499 |
| http://proceedings.mlr.press/v70/xie17a/xie17a.pdf | |
| PWC | https://paperswithcode.com/paper/learning-latent-space-models-with-angular |
| Repo | |
| Framework | |
Identifying Semantic Edit Intentions from Revisions in Wikipedia
| Title | Identifying Semantic Edit Intentions from Revisions in Wikipedia |
| Authors | Diyi Yang, Aaron Halfaker, Robert Kraut, Eduard Hovy |
| Abstract | Most studies on human editing focus merely on syntactic revision operations, failing to capture the intentions behind revision changes, which are essential for facilitating the single and collaborative writing process. In this work, we develop in collaboration with Wikipedia editors a 13-category taxonomy of the semantic intention behind edits in Wikipedia articles. Using labeled article edits, we build a computational classifier of intentions that achieved a micro-averaged F1 score of 0.621. We use this model to investigate edit intention effectiveness: how different types of edits predict the retention of newcomers and changes in the quality of articles, two key concerns for Wikipedia today. Our analysis shows that the types of edits that users make in their first session predict their subsequent survival as Wikipedia editors, and articles in different stages need different types of edits. |
| Tasks | Information Retrieval, Lexical Simplification, Natural Language Inference, Sentence Compression |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1213/ |
| https://www.aclweb.org/anthology/D17-1213 | |
| PWC | https://paperswithcode.com/paper/identifying-semantic-edit-intentions-from |
| Repo | |
| Framework | |
Why We Speak
| Title | Why We Speak |
| Authors | Rohit Parikh |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3407/ |
| https://www.aclweb.org/anthology/W17-3407 | |
| PWC | https://paperswithcode.com/paper/why-we-speak |
| Repo | |
| Framework | |
Unified representation of tractography and diffusion-weighted MRI data using sparse multidimensional arrays
| Title | Unified representation of tractography and diffusion-weighted MRI data using sparse multidimensional arrays |
| Authors | Cesar F. Caiafa, Olaf Sporns, Andrew Saykin, Franco Pestilli |
| Abstract | Recently, linear formulations and convex optimization methods have been proposed to predict diffusion-weighted Magnetic Resonance Imaging (dMRI) data given estimates of brain connections generated using tractography algorithms. The size of the linear models comprising such methods grows with both dMRI data and connectome resolution, and can become very large when applied to modern data. In this paper, we introduce a method to encode dMRI signals and large connectomes, i.e., those that range from hundreds of thousands to millions of fascicles (bundles of neuronal axons), by using a sparse tensor decomposition. We show that this tensor decomposition accurately approximates the Linear Fascicle Evaluation (LiFE) model, one of the recently developed linear models. We provide a theoretical analysis of the accuracy of the sparse decomposed model, LiFESD, and demonstrate that it can reduce the size of the model significantly. Also, we develop algorithms to implement the optimisation solver using the tensor representation in an efficient way. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7021-unified-representation-of-tractography-and-diffusion-weighted-mri-data-using-sparse-multidimensional-arrays |
| http://papers.nips.cc/paper/7021-unified-representation-of-tractography-and-diffusion-weighted-mri-data-using-sparse-multidimensional-arrays.pdf | |
| PWC | https://paperswithcode.com/paper/unified-representation-of-tractography-and |
| Repo | |
| Framework | |
Annotation of greeting, introduction, and leavetaking in dialogues
| Title | Annotation of greeting, introduction, and leavetaking in dialogues |
| Authors | Emer Gilmartin, Brendan Spillane, Maria O{'}Reilly, Christian Saam, Ketong Su, Benjamin R. Cowan, Killian Levacher, Arturo Calvo Devesa, Lodana Cerrato, Nick Campbell, Vincent Wade |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7405/ |
| https://www.aclweb.org/anthology/W17-7405 | |
| PWC | https://paperswithcode.com/paper/annotation-of-greeting-introduction-and |
| Repo | |
| Framework | |
Reservoir observers: Model-free inference of unmeasured variables in chaotic systems
| Title | Reservoir observers: Model-free inference of unmeasured variables in chaotic systems |
| Authors | Zhixin Lu, Jaideep Pathak, Brian Hunt, Michelle Girvan, Roger Brockett, and Edward Ott |
| Abstract | Deducing the state of a dynamical system as a function of time from a limited number of concurrent system state measurements is an important problem of great practical utility. A scheme that accomplishes this is called an “observer.” We consider the case in which a model of the system is unavailable or insufficiently accurate, but “training” time series data of the desired state variables are available for a short period of time, and a limited number of other system variables are continually measured. We propose a solution to this problem using networks of neuron-like units known as “reservoir computers.” The measurements that are continually available are input to the network, which is trained with the limited-time data to output estimates of the desired state variables. We demonstrate our method, which we call a “reservoir observer,” using the Rössler system, the Lorenz system, and the spatiotemporally chaotic Kuramoto–Sivashinsky equation. Subject to the condition of observability (i.e., whether it is in principle possible, by any means, to infer the desired unmeasured variables from the measured variables), we show that the reservoir observer can be a very effective and versatile tool for robustly reconstructing unmeasured dynamical system variables. Knowing the state of a dynamical system as it evolves in time is important for a variety of applications. This paper proposes a general-purpose method for inferring unmeasured state variables from a limited set of ongoing measurements. Our method is intended for situations in which mathematical models of system dynamics are unavailable or are insufficiently accurate to perform the desired inference. We use the machine-learning technique called “reservoir computing,” with which we construct a system-independent means of processing the measurements. A key point is the extent to which this approach is “universal.” That is, our examples show that the same reservoir can be trained to infer the state of different systems. It is the training that relates to a specific system, not the “hardware.” The reservoir hardware plays a similar role to an animal’s brain, which retrains itself as the system represented by its body and environment changes. |
| Tasks | Time Series |
| Published | 2017-04-05 |
| URL | https://aip.scitation.org/doi/10.1063/1.4979665 |
| https://aip.scitation.org/doi/pdf/10.1063/1.4979665?class=pdf | |
| PWC | https://paperswithcode.com/paper/reservoir-observers-model-free-inference-of |
| Repo | |
| Framework | |
Segmentation Guided Attention Networks for Visual Question Answering
| Title | Segmentation Guided Attention Networks for Visual Question Answering |
| Authors | Vasu Sharma, Ankita Bishnu, Labhesh Patel |
| Abstract | |
| Tasks | Common Sense Reasoning, Question Answering, Scene Understanding, Semantic Segmentation, Visual Question Answering |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3008/ |
| https://www.aclweb.org/anthology/P17-3008 | |
| PWC | https://paperswithcode.com/paper/segmentation-guided-attention-networks-for |
| Repo | |
| Framework | |
Differentially Private Clustering in High-Dimensional Euclidean Spaces
| Title | Differentially Private Clustering in High-Dimensional Euclidean Spaces |
| Authors | Maria-Florina Balcan, Travis Dick, Yingyu Liang, Wenlong Mou, Hongyang Zhang |
| Abstract | We study the problem of clustering sensitive data while preserving the privacy of individuals represented in the dataset, which has broad applications in practical machine learning and data analysis tasks. Although the problem has been widely studied in the context of low-dimensional, discrete spaces, much remains unknown concerning private clustering in high-dimensional Euclidean spaces $\mathbb{R}^d$. In this work, we give differentially private and efficient algorithms achieving strong guarantees for $k$-means and $k$-median clustering when $d=\Omega(\mathsf{polylog}(n))$. Our algorithm achieves clustering loss at most $\log^3(n)\mathsf{OPT}+\mathsf{poly}(\log n,d,k)$, advancing the state-of-the-art result of $\sqrt{d}\mathsf{OPT}+\mathsf{poly}(\log n,d^d,k^d)$. We also study the case where the data points are $s$-sparse and show that the clustering loss can scale logarithmically with $d$, i.e., $\log^3(n)\mathsf{OPT}+\mathsf{poly}(\log n,\log d,k,s)$. Experiments on both synthetic and real datasets verify the effectiveness of the proposed method. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=756 |
| http://proceedings.mlr.press/v70/balcan17a/balcan17a.pdf | |
| PWC | https://paperswithcode.com/paper/differentially-private-clustering-in-high |
| Repo | |
| Framework | |
A novel DDPG method with prioritized experience replay
| Title | A novel DDPG method with prioritized experience replay |
| Authors | Yuenan Hou, Lifeng Liu, Qing Wei, Xudong Xu, Chunlin Chen |
| Abstract | Recently, a state-of-the-art algorithm, called deep deterministic policy gradient (DDPG), has achieved good performance in many continuous control tasks in the MuJoCo simulator. To further improve the efficiency of the experience replay mechanism in DDPG and thus speeding up the training process, in this paper, a prioritized experience replay method is proposed for the DDPG algorithm, where prioritized sampling is adopted instead of uniform sampling. The proposed DDPG with prioritized experience replay is tested with an inverted pendulum task via OpenAI Gym. The experimental results show that DDPG with prioritized experience replay can reduce the training time and improve the stability of the training process, and is less sensitive to the changes of some hyperparameters such as the size of replay buffer, minibatch and the updating rate of the target network. |
| Tasks | Continuous Control |
| Published | 2017-10-01 |
| URL | https://www.researchgate.net/publication/321406256_A_novel_DDPG_method_with_prioritized_experience_replay |
| https://www.researchgate.net/publication/321406256_A_novel_DDPG_method_with_prioritized_experience_replay | |
| PWC | https://paperswithcode.com/paper/a-novel-ddpg-method-with-prioritized |
| Repo | |
| Framework | |
