October 16, 2019

2147 words 11 mins read

Paper Group NANR 39

Paper Group NANR 39

Towards Building Affect sensitive Word Distributions. Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora. Maximizing SLU Performance with Minimal Training Data Using Hybrid RNN Plus Rule-based Approach. Relaxation-Free Deep Hashing via Policy Gradient. The Interplay of …

Towards Building Affect sensitive Word Distributions

Title Towards Building Affect sensitive Word Distributions
Authors Kushal Chawla, Sopan Khosla, Niyati Chhaya, Kokil Jaidka
Abstract Learning word representations from large available corpora relies on the distributional hypothesis that words present in similar contexts tend to have similar meanings. Recent work has shown that word representations learnt in this manner lack sentiment information which, fortunately, can be leveraged using external knowledge. Our work addresses the question: can affect lexica improve the word representations learnt from a corpus? In this work, we propose techniques to incorporate affect lexica, which capture fine-grained information about a word’s psycholinguistic and emotional orientation, into the training process of Word2Vec SkipGram, Word2Vec CBOW and GloVe methods using a joint learning approach. We use affect scores from Warriner’s affect lexicon to regularize the vector representations learnt from an unlabelled corpus. Our proposed method outperforms previously proposed methods on standard tasks for word similarity detection, outlier detection and sentiment detection. We also demonstrate the usefulness of our approach for a new task related to the prediction of formality, frustration and politeness in corporate communication.
Tasks Outlier Detection
Published 2018-01-01
URL https://openreview.net/forum?id=By5SY2gA-
PDF https://openreview.net/pdf?id=By5SY2gA-
PWC https://paperswithcode.com/paper/towards-building-affect-sensitive-word
Repo
Framework

Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora

Title Automatic Token and Turn Level Language Identification for Code-Switched Text Dialog: An Analysis Across Language Pairs and Corpora
Authors Vikram Ramanarayanan, Robert Pugh
Abstract We examine the efficacy of various feature{–}learner combinations for language identification in different types of text-based code-switched interactions {–} human-human dialog, human-machine dialog as well as monolog {–} at both the token and turn levels. In order to examine the generalization of such methods across language pairs and datasets, we analyze 10 different datasets of code-switched text. We extract a variety of character- and word-based text features and pass them into multiple learners, including conditional random fields, logistic regressors and recurrent neural networks. We further examine the efficacy of novel character-level embedding and GloVe features in improving performance and observe that our best-performing text system significantly outperforms a majority vote baseline across language pairs and datasets.
Tasks Language Identification, Spoken Language Understanding, Text Generation
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5009/
PDF https://www.aclweb.org/anthology/W18-5009
PWC https://paperswithcode.com/paper/automatic-token-and-turn-level-language
Repo
Framework

Maximizing SLU Performance with Minimal Training Data Using Hybrid RNN Plus Rule-based Approach

Title Maximizing SLU Performance with Minimal Training Data Using Hybrid RNN Plus Rule-based Approach
Authors Takeshi Homma, Adriano S. Arantes, Maria Teresa Gonzalez Diaz, Masahito Togami
Abstract Spoken language understanding (SLU) by using recurrent neural networks (RNN) achieves good performances for large training data sets, but collecting large training datasets is a challenge, especially for new voice applications. Therefore, the purpose of this study is to maximize SLU performances, especially for small training data sets. To this aim, we propose a novel CRF-based dialog act selector which chooses suitable dialog acts from outputs of RNN SLU and rule-based SLU. We evaluate the selector by using DSTC2 corpus when RNN SLU is trained by less than 1,000 training sentences. The evaluation demonstrates the selector achieves Micro F1 better than both RNN and rule-based SLUs. In addition, it shows the selector achieves better Macro F1 than RNN SLU and the same Macro F1 as rule-based SLU. Thus, we confirmed our method offers advantages in SLU performances for small training data sets.
Tasks Spoken Language Understanding
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5043/
PDF https://www.aclweb.org/anthology/W18-5043
PWC https://paperswithcode.com/paper/maximizing-slu-performance-with-minimal
Repo
Framework

Relaxation-Free Deep Hashing via Policy Gradient

Title Relaxation-Free Deep Hashing via Policy Gradient
Authors Xin Yuan, Liangliang Ren, Jiwen Lu, Jie Zhou
Abstract In this paper, we propose a simple yet effective relaxation-free method to learn more effective binary codes via policy gradient for scalable image search. While a variety of deep hashing methods have been proposed in recent years, most of them are confronted by the dilemma to obtain optimal binary codes in a truly end-to-end manner with non-smooth sign activations. Unlike existing methods which usually employ a general relaxation framework to adapt to the gradient-based algorithms, our approach formulates the non-smooth part of the hashing network as sampling with a stochastic policy, so that the retrieval performance degradation caused by the relaxation can be avoided. Specifically, our method directly generates the binary codes and maximizes the expectation of rewards for similarity preservation, where the network can be trained directly via policy gradient. Hence, the differentiation challenge for discrete optimization can be naturally addressed, which leads to effective gradients and binary codes. Extensive experimental results on three benchmark datasets validate the effectiveness of the proposed method.
Tasks Image Retrieval
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Xin_Yuan_Towards_Optimal_Deep_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Xin_Yuan_Towards_Optimal_Deep_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/relaxation-free-deep-hashing-via-policy
Repo
Framework

The Interplay of Form and Meaning in Complex Medical Terms: Evidence from a Clinical Corpus

Title The Interplay of Form and Meaning in Complex Medical Terms: Evidence from a Clinical Corpus
Authors Leonie Gr{"o}n, Ann Bertels, Kris Heylen
Abstract We conduct a corpus study to investigate the structure of multi-word expressions (MWEs) in the clinical domain. Based on an existing medical taxonomy, we develop an annotation scheme and label a sample of MWEs from a Dutch corpus with semantic and grammatical features. The analysis of the annotated data shows that the formal structure of clinical MWEs correlates with their conceptual properties. The insights gained from this study could inform the design of Natural Language Processing (NLP) systems for clinical writing, but also for other specialized genres.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4905/
PDF https://www.aclweb.org/anthology/W18-4905
PWC https://paperswithcode.com/paper/the-interplay-of-form-and-meaning-in-complex
Repo
Framework

Preference Based Adaptation for Learning Objectives

Title Preference Based Adaptation for Learning Objectives
Authors Yao-Xiang Ding, Zhi-Hua Zhou
Abstract In many real-world learning tasks, it is hard to directly optimize the true performance measures, meanwhile choosing the right surrogate objectives is also difficult. Under this situation, it is desirable to incorporate an optimization of objective process into the learning loop based on weak modeling of the relationship between the true measure and the objective. In this work, we discuss the task of objective adaptation, in which the learner iteratively adapts the learning objective to the underlying true objective based on the preference feedback from an oracle. We show that when the objective can be linearly parameterized, this preference based learning problem can be solved by utilizing the dueling bandit model. A novel sampling based algorithm DL^2M is proposed to learn the optimal parameter, which enjoys strong theoretical guarantees and efficient empirical performance. To avoid learning a hypothesis from scratch after each objective function update, a boosting based hypothesis adaptation approach is proposed to efficiently adapt any pre-learned element hypothesis to the current objective. We apply the overall approach to multi-label learning, and show that the proposed approach achieves significant performance under various multi-label performance measures.
Tasks Multi-Label Learning
Published 2018-12-01
URL http://papers.nips.cc/paper/8008-preference-based-adaptation-for-learning-objectives
PDF http://papers.nips.cc/paper/8008-preference-based-adaptation-for-learning-objectives.pdf
PWC https://paperswithcode.com/paper/preference-based-adaptation-for-learning
Repo
Framework

Modeling Northern Haida Verb Morphology

Title Modeling Northern Haida Verb Morphology
Authors Jordan Lachler, Lene Antonsen, Trond Trosterud, Sjur Moshagen, Antti Arppe
Abstract
Tasks Language Modelling
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1368/
PDF https://www.aclweb.org/anthology/L18-1368
PWC https://paperswithcode.com/paper/modeling-northern-haida-verb-morphology
Repo
Framework

Finely Tuned, 2 Billion Token Based Word Embeddings for Portuguese

Title Finely Tuned, 2 Billion Token Based Word Embeddings for Portuguese
Authors Jo{~a}o Rodrigues, Ant{'o}nio Branco
Abstract
Tasks Named Entity Recognition, Question Answering, Word Embeddings
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1382/
PDF https://www.aclweb.org/anthology/L18-1382
PWC https://paperswithcode.com/paper/finely-tuned-2-billion-token-based-word
Repo
Framework

Causal Discovery from Discrete Data using Hidden Compact Representation

Title Causal Discovery from Discrete Data using Hidden Compact Representation
Authors Ruichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang, Zhifeng Hao
Abstract Causal discovery from a set of observations is one of the fundamental problems across several disciplines. For continuous variables, recently a number of causal discovery methods have demonstrated their effectiveness in distinguishing the cause from effect by exploring certain properties of the conditional distribution, but causal discovery on categorical data still remains to be a challenging problem, because it is generally not easy to find a compact description of the causal mechanism for the true causal direction. In this paper we make an attempt to find a way to solve this problem by assuming a two-stage causal process: the first stage maps the cause to a hidden variable of a lower cardinality, and the second stage generates the effect from the hidden representation. In this way, the causal mechanism admits a simple yet compact representation. We show that under this model, the causal direction is identifiable under some weak conditions on the true causal mechanism. We also provide an effective solution to recover the above hidden compact representation within the likelihood framework. Empirical studies verify the effectiveness of the proposed approach on both synthetic and real-world data.
Tasks Causal Discovery
Published 2018-12-01
URL http://papers.nips.cc/paper/7532-causal-discovery-from-discrete-data-using-hidden-compact-representation
PDF http://papers.nips.cc/paper/7532-causal-discovery-from-discrete-data-using-hidden-compact-representation.pdf
PWC https://paperswithcode.com/paper/causal-discovery-from-discrete-data-using
Repo
Framework

Web-based Annotation Tool for Inflectional Language Resources

Title Web-based Annotation Tool for Inflectional Language Resources
Authors Abdulrahman Alosaimy, Eric Atwell
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1621/
PDF https://www.aclweb.org/anthology/L18-1621
PWC https://paperswithcode.com/paper/web-based-annotation-tool-for-inflectional
Repo
Framework

SynPaFlex-Corpus: An Expressive French Audiobooks Corpus dedicated to expressive speech synthesis.

Title SynPaFlex-Corpus: An Expressive French Audiobooks Corpus dedicated to expressive speech synthesis.
Authors Aghilas Sini, Damien Lolive, Ga{"e}lle Vidal, Marie Tahon, {'E}lisabeth Delais-Roussarie
Abstract
Tasks Speech Synthesis, Text-To-Speech Synthesis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1677/
PDF https://www.aclweb.org/anthology/L18-1677
PWC https://paperswithcode.com/paper/synpaflex-corpus-an-expressive-french
Repo
Framework

Learning Sparse Neural Networks through L_0 Regularization

Title Learning Sparse Neural Networks through L_0 Regularization
Authors Christos Louizos, Max Welling, Diederik P. Kingma
Abstract We propose a practical method for $L_0$ norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up training and inference, and (2) it can improve generalization. AIC and BIC, well-known model selection criteria, are special cases of $L_0$ regularization. However, since the $L_0$ norm of weights is non-differentiable, we cannot incorporate it directly as a regularization term in the objective function. We propose a solution through the inclusion of a collection of non-negative stochastic gates, which collectively determine which weights to set to zero. We show that, somewhat surprisingly, for certain distributions over the gates, the expected $L_0$ regularized objective is differentiable with respect to the distribution parameters. We further propose the \emph{hard concrete} distribution for the gates, which is obtained by ``stretching’’ a binary concrete distribution and then transforming its samples with a hard-sigmoid. The parameters of the distribution over the gates can then be jointly optimized with the original network parameters. As a result our method allows for straightforward and efficient learning of model structures with stochastic gradient descent and allows for conditional computation in a principled way. We perform various experiments to demonstrate the effectiveness of the resulting approach and regularizer. |
Tasks Model Selection
Published 2018-01-01
URL https://openreview.net/forum?id=H1Y8hhg0b
PDF https://openreview.net/pdf?id=H1Y8hhg0b
PWC https://paperswithcode.com/paper/learning-sparse-neural-networks-through-l_0-1
Repo
Framework

Increasing Argument Annotation Reproducibility by Using Inter-annotator Agreement to Improve Guidelines

Title Increasing Argument Annotation Reproducibility by Using Inter-annotator Agreement to Improve Guidelines
Authors Milagro Teruel, Cristian Cardellino, Fern Cardellino, o, Laura Alonso Alemany, Serena Villata
Abstract
Tasks Argument Mining
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1640/
PDF https://www.aclweb.org/anthology/L18-1640
PWC https://paperswithcode.com/paper/increasing-argument-annotation
Repo
Framework

L1-L2 Parallel Treebank of Learner Chinese: Overused and Underused Syntactic Structures

Title L1-L2 Parallel Treebank of Learner Chinese: Overused and Underused Syntactic Structures
Authors Keying Li, John Lee
Abstract
Tasks Language Acquisition, Word Alignment
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1647/
PDF https://www.aclweb.org/anthology/L18-1647
PWC https://paperswithcode.com/paper/l1-l2-parallel-treebank-of-learner-chinese
Repo
Framework

Genre Identification and the Compositional Effect of Genre in Literature

Title Genre Identification and the Compositional Effect of Genre in Literature
Authors Joseph Worsham, Jugal Kalita
Abstract Recent advances in Natural Language Processing are finding ways to place an emphasis on the hierarchical nature of text instead of representing language as a flat sequence or unordered collection of words or letters. A human reader must capture multiple levels of abstraction and meaning in order to formulate an understanding of a document. In this paper, we address the problem of developing approaches which are capable of working with extremely large and complex literary documents to perform Genre Identification. The task is to assign the literary classification to a full-length book belonging to a corpus of literature, where the works on average are well over 200,000 words long and genre is an abstract thematic concept. We introduce the Gutenberg Dataset for Genre Identification. Additionally, we present a study on how current deep learning models compare to traditional methods for this task. The results are presented as a baseline along with findings on how using an ensemble of chapters can significantly improve results in deep learning methods. The motivation behind the ensemble of chapters method is discussed as the compositionality of subtexts which make up a larger work and contribute to the overall genre.
Tasks Decision Making, Information Retrieval, Recommendation Systems
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1167/
PDF https://www.aclweb.org/anthology/C18-1167
PWC https://paperswithcode.com/paper/genre-identification-and-the-compositional
Repo
Framework
comments powered by Disqus