Paper Group NANR 220
Active Learning for Dependency Parsing with Partial Annotation. Guided Policy Search via Approximate Mirror Descent. RELPRON: A Relative Clause Evaluation Data Set for Compositional Distributional Semantics. Inference of ICD Codes from Japanese Medical Records by Searching Disease Names. A Discriminative Topic Model using Document Network Structure …
Active Learning for Dependency Parsing with Partial Annotation
| Title | Active Learning for Dependency Parsing with Partial Annotation |
| Authors | Zhenghua Li, Min Zhang, Yue Zhang, Zhanyi Liu, Wenliang Chen, Hua Wu, Haifeng Wang |
| Abstract | |
| Tasks | Active Learning, Dependency Parsing |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1033/ |
| https://www.aclweb.org/anthology/P16-1033 | |
| PWC | https://paperswithcode.com/paper/active-learning-for-dependency-parsing-with |
| Repo | |
| Framework | |
Guided Policy Search via Approximate Mirror Descent
| Title | Guided Policy Search via Approximate Mirror Descent |
| Authors | William H. Montgomery, Sergey Levine |
| Abstract | Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised learning to train the policy to mimic a “teacher” algorithm, such as a trajectory optimizer or a trajectory-centric reinforcement learning method. Guided policy search methods provide asymptotic local convergence guarantees by construction, but it is not clear how much the policy improves within a small, finite number of iterations. We show that guided policy search algorithms can be interpreted as an approximate variant of mirror descent, where the projection onto the constraint manifold is not exact. We derive a new guided policy search algorithm that is simpler and provides appealing improvement and convergence guarantees in simplified convex and linear settings, and show that in the more general nonlinear setting, the error in the projection step can be bounded. We provide empirical results on several simulated robotic manipulation tasks that show that our method is stable and achieves similar or better performance when compared to prior guided policy search methods, with a simpler formulation and fewer hyperparameters. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6105-guided-policy-search-via-approximate-mirror-descent |
| http://papers.nips.cc/paper/6105-guided-policy-search-via-approximate-mirror-descent.pdf | |
| PWC | https://paperswithcode.com/paper/guided-policy-search-via-approximate-mirror |
| Repo | |
| Framework | |
RELPRON: A Relative Clause Evaluation Data Set for Compositional Distributional Semantics
| Title | RELPRON: A Relative Clause Evaluation Data Set for Compositional Distributional Semantics |
| Authors | Laura Rimell, Jean Maillard, Tamara Polajnar, Stephen Clark |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/J16-4004/ |
| https://www.aclweb.org/anthology/J16-4004 | |
| PWC | https://paperswithcode.com/paper/relpron-a-relative-clause-evaluation-data-set |
| Repo | |
| Framework | |
Inference of ICD Codes from Japanese Medical Records by Searching Disease Names
| Title | Inference of ICD Codes from Japanese Medical Records by Searching Disease Names |
| Authors | Masahito Sakishita, Yoshinobu Kano |
| Abstract | Importance of utilizing medical information is getting increased as electronic health records (EHRs) are widely used nowadays. We aim to assign international standardized disease codes, ICD-10, to Japanese textual information in EHRs for users to reuse the information accurately. In this paper, we propose methods to automatically extract diagnosis and to assign ICD codes to Japanese medical records. Due to the lack of available training data, we dare employed rule-based methods rather than machine learning. We observed characteristics of medical records carefully, writing rules to make effective methods by hand. We applied our system to the NTCIR-12 MedNLPDoc shared task data where participants are required to assign ICD-10 codes of possible diagnosis in given EHRs. In this shared task, our system achieved the highest F-measure score among all participants in the most severe evaluation criteria. Through comparison with other approaches, we show that our approach could be a useful milestone for the future development of Japanese medical record processing. |
| Tasks | Information Retrieval |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4209/ |
| https://www.aclweb.org/anthology/W16-4209 | |
| PWC | https://paperswithcode.com/paper/inference-of-icd-codes-from-japanese-medical |
| Repo | |
| Framework | |
A Discriminative Topic Model using Document Network Structure
| Title | A Discriminative Topic Model using Document Network Structure |
| Authors | Weiwei Yang, Jordan Boyd-Graber, Philip Resnik |
| Abstract | |
| Tasks | Link Prediction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1065/ |
| https://www.aclweb.org/anthology/P16-1065 | |
| PWC | https://paperswithcode.com/paper/a-discriminative-topic-model-using-document |
| Repo | |
| Framework | |
Automatic Generation and Scoring of Positive Interpretations from Negated Statements
| Title | Automatic Generation and Scoring of Positive Interpretations from Negated Statements |
| Authors | Eduardo Blanco, Zahra Sarabi |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1169/ |
| https://www.aclweb.org/anthology/N16-1169 | |
| PWC | https://paperswithcode.com/paper/automatic-generation-and-scoring-of-positive |
| Repo | |
| Framework | |
The OFAI Multi-Modal Task Description Corpus
| Title | The OFAI Multi-Modal Task Description Corpus |
| Authors | Stephanie Schreitter, Brigitte Krenn |
| Abstract | The OFAI Multimodal Task Description Corpus (OFAI-MMTD Corpus) is a collection of dyadic teacher-learner (human-human and human-robot) interactions. The corpus is multimodal and tracks the communication signals exchanged between interlocutors in task-oriented scenarios including speech, gaze and gestures. The focus of interest lies on the communicative signals conveyed by the teacher and which objects are salient at which time. Data are collected from four different task description setups which involve spatial utterances, navigation instructions and more complex descriptions of joint tasks. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1224/ |
| https://www.aclweb.org/anthology/L16-1224 | |
| PWC | https://paperswithcode.com/paper/the-ofai-multi-modal-task-description-corpus |
| Repo | |
| Framework | |
Modeling Social Norms Evolution for Personalized Sentiment Classification
| Title | Modeling Social Norms Evolution for Personalized Sentiment Classification |
| Authors | Lin Gong, Mohammad Al Boni, Hongning Wang |
| Abstract | |
| Tasks | Multi-Task Learning, Opinion Mining, Sentiment Analysis, Transfer Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1081/ |
| https://www.aclweb.org/anthology/P16-1081 | |
| PWC | https://paperswithcode.com/paper/modeling-social-norms-evolution-for |
| Repo | |
| Framework | |
Modeling Concept Dependencies in a Scientific Corpus
| Title | Modeling Concept Dependencies in a Scientific Corpus |
| Authors | Jonathan Gordon, Linhong Zhu, Aram Galstyan, Prem Natarajan, Gully Burns |
| Abstract | |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1082/ |
| https://www.aclweb.org/anthology/P16-1082 | |
| PWC | https://paperswithcode.com/paper/modeling-concept-dependencies-in-a-scientific |
| Repo | |
| Framework | |
Using Factored Word Representation in Neural Network Language Models
| Title | Using Factored Word Representation in Neural Network Language Models |
| Authors | Jan Niehues, Thanh-Le Ha, Eunah Cho, Alex Waibel |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2208/ |
| https://www.aclweb.org/anthology/W16-2208 | |
| PWC | https://paperswithcode.com/paper/using-factored-word-representation-in-neural |
| Repo | |
| Framework | |
RBPB: Regularization-Based Pattern Balancing Method for Event Extraction
| Title | RBPB: Regularization-Based Pattern Balancing Method for Event Extraction |
| Authors | Lei Sha, Jing Liu, Chin-Yew Lin, Sujian Li, Baobao Chang, Zhifang Sui |
| Abstract | |
| Tasks | Dependency Parsing, Representation Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1116/ |
| https://www.aclweb.org/anthology/P16-1116 | |
| PWC | https://paperswithcode.com/paper/rbpb-regularization-based-pattern-balancing |
| Repo | |
| Framework | |
「V到」結構的合分詞及語意區分(Word segmentation and sense representation for V-dao structure in Chinese)[In Chinese]
| Title | 「V到」結構的合分詞及語意區分(Word segmentation and sense representation for V-dao structure in Chinese)[In Chinese] |
| Authors | Shu-Ling Huang, Shi-Min Li, Ming-Hong Bai, Jian-Cheng Wu, Ying-Ni Wang, Qing-Long Lin |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/O16-1005/ |
| https://www.aclweb.org/anthology/O16-1005 | |
| PWC | https://paperswithcode.com/paper/avaaccaaeaeaaaword-segmentation-and-sense |
| Repo | |
| Framework | |
Corpus Query Lingua Franca (CQLF)
| Title | Corpus Query Lingua Franca (CQLF) |
| Authors | Piotr Ba{'n}ski, Elena Frick, Andreas Witt |
| Abstract | The present paper describes Corpus Query Lingua Franca (ISO CQLF), a specification designed at ISO Technical Committee 37 Subcommittee 4 {``}Language resource management{''} for the purpose of facilitating the comparison of properties of corpus query languages. We overview the motivation for this endeavour and present its aims and its general architecture. CQLF is intended as a multi-part specification; here, we concentrate on the basic metamodel that provides a frame that the other parts fit in. | |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1446/ |
| https://www.aclweb.org/anthology/L16-1446 | |
| PWC | https://paperswithcode.com/paper/corpus-query-lingua-franca-cqlf |
| Repo | |
| Framework | |
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification
| Title | Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification |
| Authors | Peng Zhou, Wei Shi, Jun Tian, Zhenyu Qi, Bingchen Li, Hongwei Hao, Bo Xu |
| Abstract | |
| Tasks | Question Answering, Relation Classification |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2034/ |
| https://www.aclweb.org/anthology/P16-2034 | |
| PWC | https://paperswithcode.com/paper/attention-based-bidirectional-long-short-term |
| Repo | |
| Framework | |
Prototype Synthesis for Model Laws
| Title | Prototype Synthesis for Model Laws |
| Authors | Matthew Burgess, Eugenia Giraudy, Eytan Adar |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1149/ |
| https://www.aclweb.org/anthology/P16-1149 | |
| PWC | https://paperswithcode.com/paper/prototype-synthesis-for-model-laws |
| Repo | |
| Framework | |
