Paper Group NANR 97
AttentionMeSH: Simple, Effective and Interpretable Automatic MeSH Indexer. Overview of the 2018 ALTA Shared Task: Classifying Patent Applications. Simultaneous 3D Reconstruction for Water Surface and Underwater Scene. A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding. Adapting SimpleNLG to Galician language. Credit Assign …
AttentionMeSH: Simple, Effective and Interpretable Automatic MeSH Indexer
| Title | AttentionMeSH: Simple, Effective and Interpretable Automatic MeSH Indexer |
| Authors | Qiao Jin, Bhuwan Dhingra, William Cohen, Xinghua Lu |
| Abstract | There are millions of articles in PubMed database. To facilitate information retrieval, curators in the National Library of Medicine (NLM) assign a set of Medical Subject Headings (MeSH) to each article. MeSH is a hierarchically-organized vocabulary, containing about 28K different concepts, covering the fields from clinical medicine to information sciences. Several automatic MeSH indexing models have been developed to improve the time-consuming and financially expensive manual annotation, including the NLM official tool {–} Medical Text Indexer, and the winner of BioASQ Task5a challenge {–} DeepMeSH. However, these models are complex and not interpretable. We propose a novel end-to-end model, AttentionMeSH, which utilizes deep learning and attention mechanism to index MeSH terms to biomedical text. The attention mechanism enables the model to associate textual evidence with annotations, thus providing interpretability at the word level. The model also uses a novel masking mechanism to enhance accuracy and speed. In the final week of BioASQ Chanllenge Task6a, we ranked 2nd by average MiF using an on-construction model. After the contest, we achieve close to state-of-the-art MiF performance of ∼ 0.684 using our final model. Human evaluations show AttentionMeSH also provides high level of interpretability, retrieving about 90{%} of all expert-labeled relevant words given an MeSH-article pair at 20 output. |
| Tasks | Information Retrieval, Question Answering |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5306/ |
| https://www.aclweb.org/anthology/W18-5306 | |
| PWC | https://paperswithcode.com/paper/attentionmesh-simple-effective-and |
| Repo | |
| Framework | |
Overview of the 2018 ALTA Shared Task: Classifying Patent Applications
| Title | Overview of the 2018 ALTA Shared Task: Classifying Patent Applications |
| Authors | Diego Moll{'a}, Dilesha Seneviratne |
| Abstract | We present an overview of the 2018 ALTA shared task. This is the 9th of the series of shared tasks organised by ALTA since 2010. The task was to classify Australian patent classifications following the sections defined by the International Patient Classification (IPC), using data made available by IP Australia. We introduce the task, describe the data and present the results of the participating teams. Some of the participating teams outperformed state of the art. |
| Tasks | |
| Published | 2018-12-01 |
| URL | https://www.aclweb.org/anthology/U18-1011/ |
| https://www.aclweb.org/anthology/U18-1011 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-2018-alta-shared-task |
| Repo | |
| Framework | |
Simultaneous 3D Reconstruction for Water Surface and Underwater Scene
| Title | Simultaneous 3D Reconstruction for Water Surface and Underwater Scene |
| Authors | Yiming Qian, Yinqiang Zheng, Minglun Gong, Yee-Hong Yang |
| Abstract | This paper presents the first approach for simultaneously recovering the 3D shape of both the wavy water surface and the moving underwater scene. A portable camera array system is constructed, which captures the scene from multiple viewpoints above the water. The correspondences across these cameras are estimated using an optical flow method and are used to infer the shape of the water surface and the underwater scene. We assume that there is only one refraction occurring at the water interface. Under this assumption, two estimates of the water surface normals should agree: one from Snell’s law of light refraction and another from local surface structure. The experimental results using both synthetic and real data demonstrate the effectiveness of the presented approach. |
| Tasks | 3D Reconstruction, Optical Flow Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yiming_Qian_Simultaneous_3D_Reconstruction_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yiming_Qian_Simultaneous_3D_Reconstruction_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-3d-reconstruction-for-water |
| Repo | |
| Framework | |
A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding
| Title | A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding |
| Authors | Changliang Li, Liang Li, Ji Qi |
| Abstract | Spoken Language Understanding (SLU), which typically involves intent determination and slot filling, is a core component of spoken dialogue systems. Joint learning has shown to be effective in SLU given that slot tags and intents are supposed to share knowledge with each other. However, most existing joint learning methods only consider joint learning by sharing parameters on surface level rather than semantic level. In this work, we propose a novel self-attentive model with gate mechanism to fully utilize the semantic correlation between slot and intent. Our model first obtains intent-augmented embeddings based on neural network with self-attention mechanism. And then the intent semantic representation is utilized as the gate for labelling slot tags. The objectives of both tasks are optimized simultaneously via joint learning in an end-to-end way. We conduct experiment on popular benchmark ATIS. The results show that our model achieves state-of-the-art and outperforms other popular methods by a large margin in terms of both intent detection error rate and slot filling F1-score. This paper gives a new perspective for research on SLU. |
| Tasks | Intent Detection, Language Modelling, Slot Filling, Speech Recognition, Spoken Dialogue Systems, Spoken Language Understanding |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1417/ |
| https://www.aclweb.org/anthology/D18-1417 | |
| PWC | https://paperswithcode.com/paper/a-self-attentive-model-with-gate-mechanism |
| Repo | |
| Framework | |
Adapting SimpleNLG to Galician language
| Title | Adapting SimpleNLG to Galician language |
| Authors | Andrea Cascallar-Fuentes, Alej Ramos-Soto, ro, Alberto Bugar{'\i}n Diz |
| Abstract | In this paper, we describe SimpleNLG-GL, an adaptation of the linguistic realisation SimpleNLG library for the Galician language. This implementation is derived from SimpleNLG-ES, the English-Spanish version of this library. It has been tested using a battery of examples which covers the most common rules for Galician. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6507/ |
| https://www.aclweb.org/anthology/W18-6507 | |
| PWC | https://paperswithcode.com/paper/adapting-simplenlg-to-galician-language |
| Repo | |
| Framework | |
Credit Assignment For Collective Multiagent RL With Global Rewards
| Title | Credit Assignment For Collective Multiagent RL With Global Rewards |
| Authors | Duc Thien Nguyen, Akshat Kumar, Hoong Chuin Lau |
| Abstract | Scaling decision theoretic planning to large multiagent systems is challenging due to uncertainty and partial observability in the environment. We focus on a multiagent planning model subclass, relevant to urban settings, where agent interactions are dependent on their ``collective influence’’ on each other, rather than their identities. Unlike previous work, we address a general setting where system reward is not decomposable among agents. We develop collective actor-critic RL approaches for this setting, and address the problem of multiagent credit assignment, and computing low variance policy gradient estimates that result in faster convergence to high quality solutions. We also develop difference rewards based credit assignment methods for the collective setting. Empirically our new approaches provide significantly better solutions than previous methods in the presence of global rewards on two real world problems modeling taxi fleet optimization and multiagent patrolling, and a synthetic grid navigation domain. | |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8033-credit-assignment-for-collective-multiagent-rl-with-global-rewards |
| http://papers.nips.cc/paper/8033-credit-assignment-for-collective-multiagent-rl-with-global-rewards.pdf | |
| PWC | https://paperswithcode.com/paper/credit-assignment-for-collective-multiagent |
| Repo | |
| Framework | |
Active Fixation Control to Predict Saccade Sequences
| Title | Active Fixation Control to Predict Saccade Sequences |
| Authors | Calden Wloka, Iuliia Kotseruba, John K. Tsotsos |
| Abstract | Visual attention is a field with a considerable history, with eye movement control and prediction forming an important subfield. Fixation modeling in the past decades has been largely dominated computationally by a number of highly influential bottom-up saliency models, such as the Itti-Koch-Niebur model. The accuracy of such models has dramatically increased recently due to deep learning. However, on static images the emphasis of these models has largely been based on non-ordered prediction of fixations through a saliency map. Very few implemented models can generate temporally ordered human-like sequences of saccades beyond an initial fixation point. Towards addressing these shortcomings we present STAR-FC, a novel multi-saccade generator based on the integration of central high-level and object-based saliency and peripheral lower-level feature-based saliency. We have evaluated our model using the CAT2000 database, successfully predicting human patterns of fixation with equivalent accuracy and quality compared to what can be achieved by using one human sequence to predict another. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wloka_Active_Fixation_Control_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wloka_Active_Fixation_Control_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/active-fixation-control-to-predict-saccade |
| Repo | |
| Framework | |
Mining Cross-Cultural Differences and Similarities in Social Media
| Title | Mining Cross-Cultural Differences and Similarities in Social Media |
| Authors | Bill Yuchen Lin, Frank F. Xu, Kenny Zhu, Seung-won Hwang |
| Abstract | Cross-cultural differences and similarities are common in cross-lingual natural language understanding, especially for research in social media. For instance, people of distinct cultures often hold different opinions on a single named entity. Also, understanding slang terms across languages requires knowledge of cross-cultural similarities. In this paper, we study the problem of computing such cross-cultural differences and similarities. We present a lightweight yet effective approach, and evaluate it on two novel tasks: 1) mining cross-cultural differences of named entities and 2) finding similar terms for slang across languages. Experimental results show that our framework substantially outperforms a number of baseline methods on both tasks. The framework could be useful for machine translation applications and research in computational social science. |
| Tasks | Machine Translation, Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1066/ |
| https://www.aclweb.org/anthology/P18-1066 | |
| PWC | https://paperswithcode.com/paper/mining-cross-cultural-differences-and |
| Repo | |
| Framework | |
Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks
| Title | Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks |
| Authors | Mingyi Hong, Meisam Razaviyayn, Jason Lee |
| Abstract | In this work, we study two first-order primal-dual based algorithms, the Gradient Primal-Dual Algorithm (GPDA) and the Gradient Alternating Direction Method of Multipliers (GADMM), for solving a class of linearly constrained non-convex optimization problems. We show that with random initialization of the primal and dual variables, both algorithms are able to compute second-order stationary solutions (ss2) with probability one. This is the first result showing that primal-dual algorithm is capable of finding ss2 when only using first-order information; it also extends the existing results for first-order, but {primal-only} algorithms. An important implication of our result is that it also gives rise to the first global convergence result to the ss2, for two classes of unconstrained distributed non-convex learning problems over multi-agent networks. |
| Tasks | Distributed Optimization |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2156 |
| http://proceedings.mlr.press/v80/hong18a/hong18a.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-primal-dual-algorithm-converges-to |
| Repo | |
| Framework | |
Group Consistent Similarity Learning via Deep CRF for Person Re-Identification
| Title | Group Consistent Similarity Learning via Deep CRF for Person Re-Identification |
| Authors | Dapeng Chen, Dan Xu, Hongsheng Li, Nicu Sebe, Xiaogang Wang |
| Abstract | Person re-identification benefits greatly from deep neural networks (DNN) to learn accurate similarity metrics and robust feature embeddings. However, most of the current methods impose only local constraints for similarity learning. In this paper, we incorporate constraints on large image groups by combining the CRF with deep neural networks. The proposed method aims to learn the local similarity" metrics for image pairs while taking into account the dependencies from all the images in a group, forming group similarities”. Our method involves multiple images to model the relationships among the local and global similarities in a unified CRF during training, while combines multi-scale local similarities as the predicted similarity in testing. We adopt an approximate inference scheme for estimating the group similarity, enabling end-to-end training. Extensive experiments demonstrate the effectiveness of our model that combines DNN and CRF for learning robust multi-scale local similarities. The overall results outperform those by state-of-the-arts with considerable margins on three widely-used benchmarks. |
| Tasks | Person Re-Identification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Chen_Group_Consistent_Similarity_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Chen_Group_Consistent_Similarity_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/group-consistent-similarity-learning-via-deep |
| Repo | |
| Framework | |
VMware MT Tiered Model
| Title | VMware MT Tiered Model |
| Authors | Lynn Ma |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1913/ |
| https://www.aclweb.org/anthology/W18-1913 | |
| PWC | https://paperswithcode.com/paper/vmware-mt-tiered-model |
| Repo | |
| Framework | |
Neural Won! Now What?
| Title | Neural Won! Now What? |
| Authors | Alex Yanishevsky |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1911/ |
| https://www.aclweb.org/anthology/W18-1911 | |
| PWC | https://paperswithcode.com/paper/neural-won-now-what |
| Repo | |
| Framework | |
Improved Dependency Parsing using Implicit Word Connections Learned from Unlabeled Data
| Title | Improved Dependency Parsing using Implicit Word Connections Learned from Unlabeled Data |
| Authors | Wenhui Wang, Baobao Chang, Mairgup Mansur |
| Abstract | Pre-trained word embeddings and language model have been shown useful in a lot of tasks. However, both of them cannot directly capture word connections in a sentence, which is important for dependency parsing given its goal is to establish dependency relations between words. In this paper, we propose to implicitly capture word connections from unlabeled data by a word ordering model with self-attention mechanism. Experiments show that these implicit word connections do improve our parsing model. Furthermore, by combining with a pre-trained language model, our model gets state-of-the-art performance on the English PTB dataset, achieving 96.35{%} UAS and 95.25{%} LAS. |
| Tasks | Dependency Parsing, Feature Engineering, Language Modelling, Machine Translation, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1311/ |
| https://www.aclweb.org/anthology/D18-1311 | |
| PWC | https://paperswithcode.com/paper/improved-dependency-parsing-using-implicit |
| Repo | |
| Framework | |
A Framework for Understanding the Role of Morphology in Universal Dependency Parsing
| Title | A Framework for Understanding the Role of Morphology in Universal Dependency Parsing |
| Authors | Mathieu Dehouck, Pascal Denis |
| Abstract | This paper presents a simple framework for characterizing morphological complexity and how it encodes syntactic information. In particular, we propose a new measure of morpho-syntactic complexity in terms of governor-dependent preferential attachment that explains parsing performance. Through experiments on dependency parsing with data from Universal Dependencies (UD), we show that representations derived from morphological attributes deliver important parsing performance improvements over standard word form embeddings when trained on the same datasets. We also show that the new morpho-syntactic complexity measure is predictive of the gains provided by using morphological attributes over plain forms on parsing scores, making it a tool to distinguish languages using morphology as a syntactic marker from others. |
| Tasks | Dependency Parsing, Representation Learning, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1312/ |
| https://www.aclweb.org/anthology/D18-1312 | |
| PWC | https://paperswithcode.com/paper/a-framework-for-understanding-the-role-of |
| Repo | |
| Framework | |
Split and Rephrase: Better Evaluation and Stronger Baselines
| Title | Split and Rephrase: Better Evaluation and Stronger Baselines |
| Authors | Roee Aharoni, Yoav Goldberg |
| Abstract | Splitting and rephrasing a complex sentence into several shorter sentences that convey the same meaning is a challenging problem in NLP. We show that while vanilla seq2seq models can reach high scores on the proposed benchmark (Narayan et al., 2017), they suffer from memorization of the training set which contains more than 89{%} of the unique simple sentences from the validation and test sets. To aid this, we present a new train-development-test data split and neural models augmented with a copy-mechanism, outperforming the best reported baseline by 8.68 BLEU and fostering further progress on the task. |
| Tasks | Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2114/ |
| https://www.aclweb.org/anthology/P18-2114 | |
| PWC | https://paperswithcode.com/paper/split-and-rephrase-better-evaluation-and |
| Repo | |
| Framework | |
