October 15, 2019

1910 words 9 mins read

Paper Group NANR 79

Paper Group NANR 79

Learning Emotion-enriched Word Representations. Coherence Modeling Improves Implicit Discourse Relation Recognition. A Computational Model for the Linguistic Notion of Morphological Paradigm. Kernel Graph Convolutional Neural Nets. Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology. “Style” Trans …

Learning Emotion-enriched Word Representations

Title Learning Emotion-enriched Word Representations
Authors Ameeta Agrawal, Aijun An, Manos Papagelis
Abstract Most word representation learning methods are based on the distributional hypothesis in linguistics, according to which words that are used and occur in the same contexts tend to possess similar meanings. As a consequence, emotionally dissimilar words, such as {}happy{''} and {}sad{''} occurring in similar contexts would purport more similar meaning than emotionally similar words, such as {}happy{''} and {}joy{''}. This complication leads to rather undesirable outcome in predictive tasks that relate to affect (emotional state), such as emotion classification and emotion similarity. In order to address this limitation, we propose a novel method of obtaining emotion-enriched word representations, which projects emotionally similar words into neighboring spaces and emotionally dissimilar ones far apart. The proposed approach leverages distant supervision to automatically obtain a large training dataset of text documents and two recurrent neural network architectures for learning the emotion-enriched representations. Through extensive evaluation on two tasks, including emotion classification and emotion similarity, we demonstrate that the proposed representations outperform several competitive general-purpose and affective word representations.
Tasks Emotion Classification, Multi-Label Classification, Representation Learning, Word Embeddings
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1081/
PDF https://www.aclweb.org/anthology/C18-1081
PWC https://paperswithcode.com/paper/learning-emotion-enriched-word
Repo
Framework

Coherence Modeling Improves Implicit Discourse Relation Recognition

Title Coherence Modeling Improves Implicit Discourse Relation Recognition
Authors Noriki Nishida, Hideki Nakayama
Abstract The research described in this paper examines how to learn linguistic knowledge associated with discourse relations from unlabeled corpora. We introduce an unsupervised learning method on text coherence that could produce numerical representations that improve implicit discourse relation recognition in a semi-supervised manner. We also empirically examine two variants of coherence modeling: order-oriented and topic-oriented negative sampling, showing that, of the two, topic-oriented negative sampling tends to be more effective.
Tasks Transfer Learning
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5040/
PDF https://www.aclweb.org/anthology/W18-5040
PWC https://paperswithcode.com/paper/coherence-modeling-improves-implicit
Repo
Framework

A Computational Model for the Linguistic Notion of Morphological Paradigm

Title A Computational Model for the Linguistic Notion of Morphological Paradigm
Authors Miikka Silfverberg, Ling Liu, Mans Hulden
Abstract In supervised learning of morphological patterns, the strategy of generalizing inflectional tables into more abstract paradigms through alignment of the longest common subsequence found in an inflection table has been proposed as an efficient method to deduce the inflectional behavior of unseen word forms. In this paper, we extend this notion of morphological {`}paradigm{'} from earlier work and provide a formalization that more accurately matches linguist intuitions about what an inflectional paradigm is. Additionally, we propose and evaluate a mechanism for learning full human-readable paradigm specifications from incomplete data{—}a scenario when we only have access to a few inflected forms for each lexeme, and want to reconstruct the missing inflections as well as generalize and group the witnessed patterns into a model of more abstract paradigmatic behavior of lexemes. |
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-1137/
PDF https://www.aclweb.org/anthology/C18-1137
PWC https://paperswithcode.com/paper/a-computational-model-for-the-linguistic
Repo
Framework

Kernel Graph Convolutional Neural Nets

Title Kernel Graph Convolutional Neural Nets
Authors Giannis Nikolentzos, Polykarpos Meladianos, Antoine J-P Tixier, Konstantinos Skianis, Michalis Vazirgiannis
Abstract Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the features defined implicitly by this kernel. This two-stage approach decouples data representation from learning, which is suboptimal. On the other hand, Convolutional Neural Networks (CNNs) have the capability to learn their own features directly from the raw data during training. Unfortunately, they cannot handle irregular data such as graphs. We address this challenge by using graph kernels to embed meaningful local neighborhoods of the graphs in a continuous vector space. A set of filters is then convolved with these patches, pooled, and the output is then passed to a feedforward network. With limited parameter tuning, our approach outperforms strong baselines on 7 out of 10 benchmark datasets, and reaches comparable performance elsewhere. Code and data are publicly available.
Tasks Graph Classification
Published 2018-01-01
URL https://openreview.net/forum?id=SyW4Gjg0W
PDF https://openreview.net/pdf?id=SyW4Gjg0W
PWC https://paperswithcode.com/paper/kernel-graph-convolutional-neural-nets
Repo
Framework

Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology

Title Proceedings of the Fifteenth Workshop on Computational Research in Phonetics, Phonology, and Morphology
Authors
Abstract
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5800/
PDF https://www.aclweb.org/anthology/W18-5800
PWC https://paperswithcode.com/paper/proceedings-of-the-fifteenth-workshop-on
Repo
Framework

“Style” Transfer for Musical Audio Using Multiple Time-Frequency Representations

Title “Style” Transfer for Musical Audio Using Multiple Time-Frequency Representations
Authors Shaun Barry, Youngmoo Kim
Abstract Neural Style Transfer has become a popular technique for generating images of distinct artistic styles using convolutional neural networks. This recent success in image style transfer has raised the question of whether similar methods can be leveraged to alter the “style” of musical audio. In this work, we attempt long time-scale high-quality audio transfer and texture synthesis in the time-domain that captures harmonic, rhythmic, and timbral elements related to musical style, using examples that may have different lengths and musical keys. We demonstrate the ability to use randomly initialized convolutional neural networks to transfer these aspects of musical style from one piece onto another using 3 different representations of audio: the log-magnitude of the Short Time Fourier Transform (STFT), the Mel spectrogram, and the Constant-Q Transform spectrogram. We propose using these representations as a way of generating and modifying perceptually significant characteristics of musical audio content. We demonstrate each representation’s shortcomings and advantages over others by carefully designing neural network structures that complement the nature of musical audio. Finally, we show that the most compelling “style” transfer examples make use of an ensemble of these representations to help capture the varying desired characteristics of audio signals.
Tasks Style Transfer, Texture Synthesis
Published 2018-01-01
URL https://openreview.net/forum?id=BybQ7zWCb
PDF https://openreview.net/pdf?id=BybQ7zWCb
PWC https://paperswithcode.com/paper/style-transfer-for-musical-audio-using
Repo
Framework

The glass ceiling in NLP

Title The glass ceiling in NLP
Authors Natalie Schluter
Abstract In this paper, we provide empirical evidence based on a rigourously studied mathematical model for bi-populated networks, that a glass ceiling within the field of NLP has developed since the mid 2000s.
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1301/
PDF https://www.aclweb.org/anthology/D18-1301
PWC https://paperswithcode.com/paper/the-glass-ceiling-in-nlp
Repo
Framework

Combining Neural and Non-Neural Methods for Low-Resource Morphological Reinflection

Title Combining Neural and Non-Neural Methods for Low-Resource Morphological Reinflection
Authors Saeed Najafi, Bradley Hauer, Rashed Rubby Riyadh, Leyuan Yu, Grzegorz Kondrak
Abstract
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-3015/
PDF https://www.aclweb.org/anthology/K18-3015
PWC https://paperswithcode.com/paper/combining-neural-and-non-neural-methods-for
Repo
Framework

Modeling Reduplication with 2-way Finite-State Transducers

Title Modeling Reduplication with 2-way Finite-State Transducers
Authors Hossep Dolatian, Jeffrey Heinz
Abstract This article describes a novel approach to the computational modeling of reduplication. Reduplication is a well-studied linguistic phenomenon. However, it is often treated as a stumbling block within finite-state treatments of morphology. Most finite-state implementations of computational morphology cannot adequately capture the productivity of unbounded copying in reduplication, nor can they adequately capture bounded copying. We show that an understudied type of finite-state machines, two-way finite-state transducers (2-way FSTs), captures virtually all reduplicative processes, including total reduplication. 2-way FSTs can model reduplicative typology in a way which is convenient, easy to design and debug in practice, and linguistically-motivated. By virtue of being finite-state, 2-way FSTs are likewise incorporable into existing finite-state systems and programs. A small but representative typology of reduplicative processes is described in this article, alongside their corresponding 2-way FST models.
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5807/
PDF https://www.aclweb.org/anthology/W18-5807
PWC https://paperswithcode.com/paper/modeling-reduplication-with-2-way-finite
Repo
Framework

VarIDE at PARSEME Shared Task 2018: Are Variants Really as Alike as Two Peas in a Pod?

Title VarIDE at PARSEME Shared Task 2018: Are Variants Really as Alike as Two Peas in a Pod?
Authors Caroline Pasquer, Carlos Ramisch, Agata Savary, Jean-Yves Antoine
Abstract We describe the VarIDE system (standing for Variant IDEntification) which participated in the edition 1.1 of the PARSEME shared task on automatic identification of verbal multiword expressions (VMWEs). Our system focuses on the task of VMWE variant identification by using morphosyntactic information in the training data to predict if candidates extracted from the test corpus could be idiomatic, thanks to a naive Bayes classifier. We report results for 19 languages.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4932/
PDF https://www.aclweb.org/anthology/W18-4932
PWC https://paperswithcode.com/paper/varide-at-parseme-shared-task-2018-are
Repo
Framework

Dialog Generation Using Multi-Turn Reasoning Neural Networks

Title Dialog Generation Using Multi-Turn Reasoning Neural Networks
Authors Xianchao Wu, Ander Mart{'\i}nez, Momo Klyen
Abstract In this paper, we propose a generalizable dialog generation approach that adapts multi-turn reasoning, one recent advancement in the field of document comprehension, to generate responses ({}answers{''}) by taking current conversation session context as a {}document{''} and current query as a {``}question{''}. The major idea is to represent a conversation session into memories upon which attention-based memory reading mechanism can be performed multiple times, so that (1) user{'}s query is properly extended by contextual clues and (2) optimal responses are step-by-step generated. Considering that the speakers of one conversation are not limited to be one, we separate the single memory used for document comprehension into different groups for speaker-specific topic and opinion embedding. Namely, we utilize the queries{'} memory, the responses{'} memory, and their unified memory, following the time sequence of the conversation session. Experiments on Japanese 10-sentence (5-round) conversation modeling show impressive results on how multi-turn reasoning can produce more diverse and acceptable responses than state-of-the-art single-turn and non-reasoning baselines. |
Tasks Constituency Parsing, Image Captioning, Learning-To-Rank, Machine Translation, Speech Recognition, Text Generation
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1186/
PDF https://www.aclweb.org/anthology/N18-1186
PWC https://paperswithcode.com/paper/dialog-generation-using-multi-turn-reasoning
Repo
Framework

Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop & Shared Task

Title Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop & Shared Task
Authors
Abstract
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5900/
PDF https://www.aclweb.org/anthology/W18-5900
PWC https://paperswithcode.com/paper/proceedings-of-the-2018-emnlp-workshop-smm4h
Repo
Framework

Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances

Title Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances
Authors Grigory Yaroslavtsev, Adithya Vadapalli
Abstract We present first massively parallel (MPC) algorithms and hardness of approximation results for computing Single-Linkage Clustering of n input d-dimensional vectors under Hamming, $\ell_1, \ell_2$ and $\ell_\infty$ distances. All our algorithms run in O(log n) rounds of MPC for any fixed d and achieve (1+\epsilon)-approximation for all distances (except Hamming for which we show an exact algorithm). We also show constant-factor inapproximability results for o(\log n)-round algorithms under standard MPC hardness assumptions (for sufficiently large dimension depending on the distance used). Efficiency of implementation of our algorithms in Apache Spark is demonstrated through experiments on the largest available vector datasets from the UCI machine learning repository exhibiting speedups of several orders of magnitude.
Tasks
Published 2018-07-01
URL https://icml.cc/Conferences/2018/Schedule?showEvent=2366
PDF http://proceedings.mlr.press/v80/yaroslavtsev18a/yaroslavtsev18a.pdf
PWC https://paperswithcode.com/paper/massively-parallel-algorithms-and-hardness
Repo
Framework

Tutorial: MQM-DQF: A Good Marriage (Translation Quality for the 21st Century)

Title Tutorial: MQM-DQF: A Good Marriage (Translation Quality for the 21st Century)
Authors Arle Lommel, Alan Melby
Abstract
Tasks Machine Translation
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-1925/
PDF https://www.aclweb.org/anthology/W18-1925
PWC https://paperswithcode.com/paper/tutorial-mqm-dqf-a-good-marriage-translation
Repo
Framework

Dealing with Medication Non-Adherence Expressions in Twitter

Title Dealing with Medication Non-Adherence Expressions in Twitter
Authors Takeshi Onishi, Davy Weissenbacher, Ari Klein, Karen O{'}Connor, Gonzalez-Hern, Graciela ez
Abstract Through a semi-automatic analysis of tweets, we show that Twitter users not only express Medication Non-Adherence (MNA) in social media but also their reasons for not complying; further research is necessary to fully extract automatically and analyze this information, in order to facilitate the use of this data in epidemiological studies.
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5908/
PDF https://www.aclweb.org/anthology/W18-5908
PWC https://paperswithcode.com/paper/dealing-with-medication-non-adherence
Repo
Framework
comments powered by Disqus