October 15, 2019

2122 words 10 mins read

Paper Group NANR 108

Paper Group NANR 108

On Learning Better Embeddings from Chinese Clinical Records: Study on Combining In-Domain and Out-Domain Data. The Effect of Adding Authorship Knowledge in Automated Text Scoring. A Pedagogical Application of NooJ in Language Teaching: The Adjective in Spanish and Italian. Deep Learning Architecture for Complex Word Identification. Learning Globall …

On Learning Better Embeddings from Chinese Clinical Records: Study on Combining In-Domain and Out-Domain Data

Title On Learning Better Embeddings from Chinese Clinical Records: Study on Combining In-Domain and Out-Domain Data
Authors Yaqiang Wang, Yunhui Chen, Hongping Shu, Yongguang Jiang
Abstract High quality word embeddings are of great significance to advance applications of biomedical natural language processing. In recent years, a surge of interest on how to learn good embeddings and evaluate embedding quality based on English medical text has become increasing evident, however a limited number of studies based on Chinese medical text, particularly Chinese clinical records, were performed. Herein, we proposed a novel approach of improving the quality of learned embeddings using out-domain data as a supplementary in the case of limited Chinese clinical records. Moreover, the embedding quality evaluation method was conducted based on Medical Conceptual Similarity Property. The experimental results revealed that selecting good training samples was necessary, and collecting right amount of out-domain data and trading off between the quality of embeddings and the training time consumption were essential factors for better embeddings.
Tasks Disease Prediction, Information Retrieval, Language Modelling, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2323/
PDF https://www.aclweb.org/anthology/W18-2323
PWC https://paperswithcode.com/paper/on-learning-better-embeddings-from-chinese
Repo
Framework

The Effect of Adding Authorship Knowledge in Automated Text Scoring

Title The Effect of Adding Authorship Knowledge in Automated Text Scoring
Authors Meng Zhang, Xie Chen, Ronan Cummins, {\O}istein E. Andersen, Ted Briscoe
Abstract Some language exams have multiple writing tasks. When a learner writes multiple texts in a language exam, it is not surprising that the quality of these texts tends to be similar, and the existing automated text scoring (ATS) systems do not explicitly model this similarity. In this paper, we suggest that it could be useful to include the other texts written by this learner in the same exam as extra references in an ATS system. We propose various approaches of fusing information from multiple tasks and pass this authorship knowledge into our ATS model on six different datasets. We show that this can positively affect the model performance at a global level.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0536/
PDF https://www.aclweb.org/anthology/W18-0536
PWC https://paperswithcode.com/paper/the-effect-of-adding-authorship-knowledge-in
Repo
Framework

A Pedagogical Application of NooJ in Language Teaching: The Adjective in Spanish and Italian

Title A Pedagogical Application of NooJ in Language Teaching: The Adjective in Spanish and Italian
Authors Andrea Rodrigo, Mario Monteleone, Silvia Reyes
Abstract In this paper, a pedagogical application of NooJ to the teaching and learning of Spanish as a foreign language is presented, which is directed to a specific addressee: learners whose mother tongue is Italian. The category {`}adjective{'} has been chosen on account of its lower frequency of occurrence in texts written in Spanish, and particularly in the Argentine Rioplatense variety, and with the aim of developing strategies to increase its use. In addition, the features that the adjective shares with other grammatical categories render it extremely productive and provide elements that enrich the learners{'} proficiency. The reference corpus contains the front pages of the Argentinian newspaper Clar{'\i}n related to an emblematic historical moment, whose starting point is 24 March 1976, when a military coup began, and covers a thirty year period until 24 March 2006. It can be seen how the term desaparecido emerges with all its cultural and social charge, providing a context which allows an approach to Rioplatense Spanish from a more comprehensive perspective. Finally, a pedagogical proposal accounting for the application of the NooJ platform in language teaching is included. |
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-3807/
PDF https://www.aclweb.org/anthology/W18-3807
PWC https://paperswithcode.com/paper/a-pedagogical-application-of-nooj-in-language
Repo
Framework

Deep Learning Architecture for Complex Word Identification

Title Deep Learning Architecture for Complex Word Identification
Authors Dirk De Hertog, Ana{"\i}s Tack
Abstract We describe a system for the CWI-task that includes information on 5 aspects of the (complex) lexical item, namely distributional information of the item itself, morphological structure, psychological measures, corpus-counts and topical information. We constructed a deep learning architecture that combines those features and apply it to the probabilistic and binary classification task for all English sets and Spanish. We achieved reasonable performance on all sets with best performances seen on the probabilistic task, particularly on the English news set (MAE 0.054 and F1-score of 0.872). An analysis of the results shows that reasonable performance can be achieved with a single architecture without any domain-specific tweaking of the parameter settings and that distributional features capture almost all of the information also found in hand-crafted features.
Tasks Complex Word Identification, Lexical Simplification
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0539/
PDF https://www.aclweb.org/anthology/W18-0539
PWC https://paperswithcode.com/paper/deep-learning-architecture-for-complex-word
Repo
Framework

Learning Globally Optimized Object Detector via Policy Gradient

Title Learning Globally Optimized Object Detector via Policy Gradient
Authors Yongming Rao, Dahua Lin, Jiwen Lu, Jie Zhou
Abstract In this paper, we propose a simple yet effective method to learn globally optimized detector for object detection, which is a simple modification to the standard cross-entropy gradient inspired by the REINFORCE algorithm. In our approach, the cross-entropy gradient is adaptively adjusted according to overall mean Average Precision (mAP) of the current state for each detection candidate, which leads to more effective gradient and global optimization of detection results, and brings no computational overhead. Benefiting from more precise gradients produced by the global optimization method, our framework significantly improves state-of-the-art object detectors. Furthermore, since our method is based on scores and bounding boxes without modification on the architecture of object detector, it can be easily applied to off-the-shelf modern object detection frameworks.
Tasks Object Detection
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Rao_Learning_Globally_Optimized_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Rao_Learning_Globally_Optimized_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/learning-globally-optimized-object-detector
Repo
Framework

Pose Proposal Networks

Title Pose Proposal Networks
Authors Taiki Sekii
Abstract We propose a novel method to detect an unknown number of articulated 2D poses in real time. To decouple the runtime complexity of pixel-wise body part detectors from their convolutional neural network (CNN) feature map resolutions, our approach, called pose proposal networks, introduces a state-of-the-art single-shot object detection paradigm using grid-wise image feature maps in a bottom-up pose detection scenario. Body part proposals, which are represented as region proposals, and limbs are detected directly via a single-shot CNN. Specialized to such detections, a bottom-up greedy parsing step is probabilistically redesigned to take into account the global context. Experimental results on the MPII Multi-Person benchmark confirm that our method achieves 72.8% mAP comparable to state-of-the-art bottom-up approaches while its total runtime using a GeForce GTX1080Ti card reaches up to 5.6 ms (180 FPS), which exceeds the bottleneck runtimes that are observed in state-of-the-art approaches.
Tasks Object Detection
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Sekii_Pose_Proposal_Networks_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Sekii_Pose_Proposal_Networks_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/pose-proposal-networks
Repo
Framework

Adaptive Learning with Unknown Information Flows

Title Adaptive Learning with Unknown Information Flows
Authors Yonatan Gur, Ahmadreza Momeni
Abstract An agent facing sequential decisions that are characterized by partial feedback needs to strike a balance between maximizing immediate payoffs based on available information, and acquiring new information that may be essential for maximizing future payoffs. This trade-off is captured by the multi-armed bandit (MAB) framework that has been studied and applied when at each time epoch payoff observations are collected on the actions that are selected at that epoch. In this paper we introduce a new, generalized MAB formulation in which additional information on each arm may appear arbitrarily throughout the decision horizon, and study the impact of such information flows on the achievable performance and the design of efficient decision-making policies. By obtaining matching lower and upper bounds, we characterize the (regret) complexity of this family of MAB problems as a function of the information flows. We introduce an adaptive exploration policy that, without any prior knowledge of the information arrival process, attains the best performance (in terms of regret rate) that is achievable when the information arrival process is a priori known. Our policy uses dynamically customized virtual time indexes to endogenously control the exploration rate based on the realized information arrival process.
Tasks Decision Making
Published 2018-12-01
URL http://papers.nips.cc/paper/7976-adaptive-learning-with-unknown-information-flows
PDF http://papers.nips.cc/paper/7976-adaptive-learning-with-unknown-information-flows.pdf
PWC https://paperswithcode.com/paper/adaptive-learning-with-unknown-information
Repo
Framework

Predicting Second Language Learner Successes and Mistakes by Means of Conjunctive Features

Title Predicting Second Language Learner Successes and Mistakes by Means of Conjunctive Features
Authors Yves Bestgen
Abstract This paper describes the system developed by the Centre for English Corpus Linguistics for the 2018 Duolingo SLAM challenge. It aimed at predicting the successes and mistakes of second language learners on each of the words that compose the exercises they answered. Its main characteristic is to include conjunctive features, built by combining word ngrams with metadata about the user and the exercise. It achieved a relatively good performance, ranking fifth out of 15 systems. Complementary analyses carried out to gauge the contribution of the different sets of features to the performance confirmed the usefulness of the conjunctive features for the SLAM task.
Tasks Language Acquisition
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0542/
PDF https://www.aclweb.org/anthology/W18-0542
PWC https://paperswithcode.com/paper/predicting-second-language-learner-successes
Repo
Framework

Ensemble Romanian Dependency Parsing with Neural Networks

Title Ensemble Romanian Dependency Parsing with Neural Networks
Authors Radu Ion, Elena Irimia, Verginica Barbu Mititelu
Abstract
Tasks Dependency Parsing, Word Embeddings
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1248/
PDF https://www.aclweb.org/anthology/L18-1248
PWC https://paperswithcode.com/paper/ensemble-romanian-dependency-parsing-with
Repo
Framework

TMU System for SLAM-2018

Title TMU System for SLAM-2018
Authors Masahiro Kaneko, Tomoyuki Kajiwara, Mamoru Komachi
Abstract We introduce the TMU systems for the second language acquisition modeling shared task 2018 (Settles et al., 2018). To model learner error patterns, it is necessary to maintain a considerable amount of information regarding the type of exercises learners have been learning in the past and the manner in which they answered them. Tracking an enormous learner{'}s learning history and their correct and mistaken answers is essential to predict the learner{'}s future mistakes. Therefore, we propose a model which tracks the learner{'}s learning history efficiently. Our systems ranked fourth in the English and Spanish subtasks, and fifth in the French subtask.
Tasks Language Acquisition
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-0544/
PDF https://www.aclweb.org/anthology/W18-0544
PWC https://paperswithcode.com/paper/tmu-system-for-slam-2018
Repo
Framework

Neural Models of Selectional Preferences for Implicit Semantic Role Labeling

Title Neural Models of Selectional Preferences for Implicit Semantic Role Labeling
Authors Minh Le, Antske Fokkens
Abstract
Tasks Semantic Role Labeling
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1484/
PDF https://www.aclweb.org/anthology/L18-1484
PWC https://paperswithcode.com/paper/neural-models-of-selectional-preferences-for
Repo
Framework

Char2char Generation with Reranking for the E2E NLG Challenge

Title Char2char Generation with Reranking for the E2E NLG Challenge
Authors Shubham Agarwal, Marc Dymetman, {'E}ric Gaussier
Abstract This paper describes our submission to the E2E NLG Challenge. Recently, neural seq2seq approaches have become mainstream in NLG, often resorting to pre- (respectively post-) processing \textit{delexicalization} (relexicalization) steps at the word-level to handle rare words. By contrast, we train a simple character level seq2seq model, which requires no pre/post-processing (delexicalization, tokenization or even lowercasing), with surprisingly good results. For further improvement, we explore two re-ranking approaches for scoring candidates. We also introduce a synthetic dataset creation procedure, which opens up a new way of creating artificial datasets for Natural Language Generation.
Tasks Dialogue Generation, Machine Translation, Semantic Parsing, Spoken Dialogue Systems, Text Generation, Tokenization
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6555/
PDF https://www.aclweb.org/anthology/W18-6555
PWC https://paperswithcode.com/paper/char2char-generation-with-reranking-for-the
Repo
Framework

Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method

Title Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method
Authors Yahui Liu, Wei Bi, Jun Gao, Xiaojiang Liu, Jian Yao, Shuming Shi
Abstract Sequence-to-sequence neural generation models have achieved promising performance on short text conversation tasks. However, they tend to generate generic/dull responses, leading to unsatisfying dialogue experience. We observe that in the conversation tasks, each query could have multiple responses, which forms a 1-to-n or m-to-n relationship in the view of the total corpus. The objective function used in standard sequence-to-sequence models will be dominated by loss terms with generic patterns. Inspired by this observation, we introduce a statistical re-weighting method that assigns different weights for the multiple responses of the same query, and trains the common neural generation model with the weights. Experimental results on a large Chinese dialogue corpus show that our method improves the acceptance rate of generated responses compared with several baseline models and significantly reduces the number of generated generic responses.
Tasks Dialogue Generation, Machine Translation, Short-Text Conversation
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1297/
PDF https://www.aclweb.org/anthology/D18-1297
PWC https://paperswithcode.com/paper/towards-less-generic-responses-in-neural
Repo
Framework

From Manuscripts to Archetypes through Iterative Clustering

Title From Manuscripts to Archetypes through Iterative Clustering
Authors Armin Hoenen
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1114/
PDF https://www.aclweb.org/anthology/L18-1114
PWC https://paperswithcode.com/paper/from-manuscripts-to-archetypes-through
Repo
Framework

An Automatic Learning of an Algerian Dialect Lexicon by using Multilingual Word Embeddings

Title An Automatic Learning of an Algerian Dialect Lexicon by using Multilingual Word Embeddings
Authors Abidi Karima, Kamel Sma{"\i}li
Abstract
Tasks Multilingual Word Embeddings, Word Embeddings
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1133/
PDF https://www.aclweb.org/anthology/L18-1133
PWC https://paperswithcode.com/paper/an-automatic-learning-of-an-algerian-dialect
Repo
Framework
comments powered by Disqus