arXiv subjects

Yutaka Matsuo

Publications and source records attributed to Yutaka Matsuo.

At least 181 records · Page 10Linked to original sources

arXiv2018

IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations

In this paper we describe our system designed for the WASSA 2018 Implicit Emotion Shared Task (IEST), which obtained 2$^{\text{nd}}$ place out of 26 teams with a test macro F1 score of $0.710$. The system is composed of a single pre-trained ELMo layer for encoding words, a Bidirectional Long-Short Memory Network BiLSTM for enriching word representations with context, a max-pooling operation for creating sentence representations from said word vectors, and a Dense Layer for projecting the sentence representations into label space. Our official submission was obtained by ensembling 6 of these models initialized with different random seeds. The code for replicating this paper is available at https://github.com/jabalazs/implicit_emotion.

cs.CL↗

arXiv2018

Learning to Automatically Generate Fill-In-The-Blank Quizzes

In this paper we formalize the problem automatic fill-in-the-blank question generation using two standard NLP machine learning schemes, proposing concrete deep learning models for each. We present an empirical study based on data obtained from a language learning platform showing that both of our proposed settings offer promising results.

cs.CL↗

arXiv2018

IIIDYT at SemEval-2018 Task 3: Irony detection in English tweets

In this paper we introduce our system for the task of Irony detection in English tweets, a part of SemEval 2018. We propose representation learning approach that relies on a multi-layered bidirectional LSTM, without using external features that provide additional semantic information. Although our model is able to outperform the baseline in the validation set, our results show limited generalization power over the test set. Given the limited size of the dataset, we think the usage of more pre-training schemes would greatly improve the obtained results.

cs.CL↗

arXiv2018

Improving Bi-directional Generation between Different Modalities with Variational Autoencoders

We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. A major approach to achieve this objective is to train a model that integrates all the information of different modalities into a joint representation and then to generate one modality from the corresponding other modality via this joint representation. We simply applied this approach to variational autoencoders (VAEs), which we call a joint multimodal variational autoencoder (JMVAE). However, we found that when this model attempts to generate a large dimensional modality missing at the input, the joint representation collapses and this modality cannot be generated successfully. Furthermore, we confirmed that this difficulty cannot be resolved even using a known solution. Therefore, in this study, we propose two models to prevent this difficulty: JMVAE-kl and JMVAE-h. Results of our experiments demonstrate that these methods can prevent the difficulty above and that they generate modalities bi-directionally with equal or higher likelihood than conventional VAE methods, which generate in only one direction. Moreover, we confirm that these methods can obtain the joint representation appropriately, so that they can generate various variations of modality by moving over the joint representation or changing the value of another modality.

stat.ML↗

arXiv2017

Reflection states in Ding-Iohara-Miki algebra and brane-web for D-type quiver

Reflection states are introduced in the vertical and horizontal modules of the Ding-Iohara-Miki (DIM) algebra (quantum toroidal $\mathfrak{gl}_1$). Webs of DIM representations are in correspondence with $(p,q)$-web diagrams of type IIB string theory, under the identification of the algebraic intertwiner of Awata, Feigin and Shiraishi with the refined topological vertex. Extending the correspondence to the vertical reflection states, it is possible to engineer the $\mathcal{N}=1$ quiver gauge theory of D-type (with unitary gauge groups). In this way, the Nekrasov instanton partition function is reproduced from the evaluation of expectation values of intertwiners. This computation leads to the identification of the vertical reflection state with the orientifold plane of string theory. We also provide a translation of this construction in the Iqbal-Kozcaz-Vafa refined topological vertex formalism.

hep-th↗

arXiv2017

EmoAtt at EmoInt-2017: Inner attention sentence embedding for Emotion Intensity

In this paper we describe a deep learning system that has been designed and built for the WASSA 2017 Emotion Intensity Shared Task. We introduce a representation learning approach based on inner attention on top of an RNN. Results show that our model offers good capabilities and is able to successfully identify emotion-bearing words to predict intensity without leveraging on lexicons, obtaining the 13th place among 22 shared task competitors.

cs.CL↗

arXiv2017

Mining fine-grained opinions on closed captions of YouTube videos with an attention-RNN

Video reviews are the natural evolution of written product reviews. In this paper we target this phenomenon and introduce the first dataset created from closed captions of YouTube product review videos as well as a new attention-RNN model for aspect extraction and joint aspect extraction and sentiment classification. Our model provides state-of-the-art performance on aspect extraction without requiring the usage of hand-crafted features on the SemEval ABSA corpus, while it outperforms the baseline on the joint task. In our dataset, the attention-RNN model outperforms the baseline for both tasks, but we observe important performance drops for all models in comparison to SemEval. These results, as well as further experiments on domain adaptation for aspect extraction, suggest that differences between speech and written text, which have been discussed extensively in the literature, also extend to the domain of product reviews, where they are relevant for fine-grained opinion mining.

cs.CL↗

arXiv2017

Refining Raw Sentence Representations for Textual Entailment Recognition via Attention

In this paper we present the model used by the team Rivercorners for the 2017 RepEval shared task. First, our model separately encodes a pair of sentences into variable-length representations by using a bidirectional LSTM. Later, it creates fixed-length raw representations by means of simple aggregation functions, which are then refined using an attention mechanism. Finally it combines the refined representations of both sentences into a single vector to be used for classification. With this model we obtained test accuracies of 72.057% and 72.055% in the matched and mismatched evaluation tracks respectively, outperforming the LSTM baseline, and obtaining performances similar to a model that relies on shared information between sentences (ESIM). When using an ensemble both accuracies increased to 72.247% and 72.827% respectively.

cs.CL↗

arXiv2017

Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection

Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.

cs.CV↗

arXiv2017

Maulik-Okounkov's R-matrix from Ding-Iohara-Miki algebra

The integrability of 4d $\mathcal{N}=2$ gauge theories has been explored in various contexts, for example the Seiberg-Witten curve and its quantization. Recently, Maulik and Okounkov proposed that an integrable lattice model is associated with the gauge theory, through an R-matrix, to which we refer as MO's R-matrix in this paper, constructed in the instanton moduli space. In this paper, we study the R-matrix using the Ding-Iohara-Miki (DIM) algebra. We provide a concrete boson realization of the universal R-matrix in DIM and show that the defining conditions for MO's R-matrix can be derived from this free boson oscillator expression. Several consistency checks for the oscillator expression are also performed.

hep-th↗

arXiv2017

A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes

We propose a model to automatically describe changes introduced in the source code of a program using natural language. Our method receives as input a set of code commits, which contains both the modifications and message introduced by an user. These two modalities are used to train an encoder-decoder architecture. We evaluated our approach on twelve real world open source projects from four different programming languages. Quantitative and qualitative results showed that the proposed approach can generate feasible and semantically sound descriptions not only in standard in-project settings, but also in a cross-project setting.

cs.CL↗

arXiv2017

(p,q)-webs of DIM representations, 5d N=1 instanton partition functions and qq-characters

Instanton partition functions of $\mathcal{N}=1$ 5d Super Yang-Mills reduced on $S^1$ can be engineered in type IIB string theory from the $(p,q)$-branes web diagram. To this diagram is superimposed a web of representations of the Ding-Iohara-Miki (DIM) algebra that acts on the partition function. In this correspondence, each segment is associated to a representation, and the (topological string) vertex is identified with the intertwiner operator constructed by Awata, Feigin and Shiraishi. We define a new intertwiner acting on the representation spaces of levels $(1,n)\otimes(0,m)\to(1,n+m)$, thereby generalizing to higher rank $m$ the original construction. It allows us to use a folded version of the usual $(p,q)$-web diagram, bringing great simplifications to actual computations. As a result, the characterization of Gaiotto states and vertical intertwiners, previously obtained by some of the authors, is uplifted to operator relations acting in the Fock space of horizontal representations. We further develop a method to build qq-characters of linear quivers based on the horizontal action of DIM elements. While fundamental qq-characters can be built using the coproduct, higher ones require the introduction of a (quantum) Weyl reflection acting on tensor products of DIM generators.

hep-th↗

arXiv2017

Replication issues in syntax-based aspect extraction for opinion mining

Reproducing experiments is an important instrument to validate previous work and build upon existing approaches. It has been tackled numerous times in different areas of science. In this paper, we introduce an empirical replicability study of three well-known algorithms for syntactic centric aspect-based opinion mining. We show that reproducing results continues to be a difficult endeavor, mainly due to the lack of details regarding preprocessing and parameter setting, as well as due to the absence of available implementations that clarify these details. We consider these are important threats to validity of the research on the field, specifically when compared to other problems in NLP where public datasets and code availability are critical validity components. We conclude by encouraging code-based research, which we think has a key role in helping researchers to understand the meaning of the state-of-the-art better and to generate continuous advances.

cs.CL↗

arXiv2016

Neural Machine Translation with Latent Semantic of Image and Text

Although attention-based Neural Machine Translation have achieved great success, attention-mechanism cannot capture the entire meaning of the source sentence because the attention mechanism generates a target word depending heavily on the relevant parts of the source sentence. The report of earlier studies has introduced a latent variable to capture the entire meaning of sentence and achieved improvement on attention-based Neural Machine Translation. We follow this approach and we believe that the capturing meaning of sentence benefits from image information because human beings understand the meaning of language not only from textual information but also from perceptual information such as that gained from vision. As described herein, we propose a neural machine translation model that introduces a continuous latent variable containing an underlying semantic extracted from texts and images. Our model, which can be trained end-to-end, requires image information only when training. Experiments conducted with an English--German translation task show that our model outperforms over the baseline.

cs.CL↗

arXiv2016

Generative Adversarial Nets from a Density Ratio Estimation Perspective

Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger gradients when learning the generator. We propose a novel algorithm that repeats the density ratio estimation and f-divergence minimization. Our algorithm offers a new perspective toward the understanding of GANs and is able to make use of multiple viewpoints obtained in the research of density ratio estimation, e.g. what divergence is stable and relative density ratio is useful.

stat.ML↗

arXiv2016

Joint Multimodal Learning with Deep Generative Models

We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. Recently, some studies handle multiple modalities on deep generative models, such as variational autoencoders (VAEs). However, these models typically assume that modalities are forced to have a conditioned relation, i.e., we can only generate modalities in one direction. To achieve our objective, we should extract a joint representation that captures high-level concepts among all modalities and through which we can exchange them bi-directionally. As described herein, we propose a joint multimodal variational autoencoder (JMVAE), in which all modalities are independently conditioned on joint representation. In other words, it models a joint distribution of modalities. Furthermore, to be able to generate missing modalities from the remaining modalities properly, we develop an additional method, JMVAE-kl, that is trained by reducing the divergence between JMVAE's encoder and prepared networks of respective modalities. Our experiments show that our proposed method can obtain appropriate joint representation from multiple modalities and that it can generate and reconstruct them more properly than conventional VAEs. We further demonstrate that JMVAE can generate multiple modalities bi-directionally.

stat.ML↗

arXiv2016

Coherent states in quantum $\mathcal{W}_{1+\infty}$ algebra and qq-character for 5d Super Yang-Mills

The instanton partition functions of $\mathcal{N}=1$ 5d super Yang-Mills are built using elements of the representation theory of quantum $\mathcal{W}_{1+\infty}$ algebra: Gaiotto state, intertwiner, vertex operator. This algebra is also known under the names of Ding-Iohara-Miki and quantum toroidal $\widehat{\mathfrak{gl}}(1)$ algebra. Exploiting the explicit action of the algebra on the partition function, we prove the regularity of the 5d qq-characters. These characters provide a solution to the Schwinger-Dyson equations, and they can also be interpreted as a quantum version of the Seiberg-Witten curve.

hep-th↗

arXiv2016

Nambu bracket and M-theory

Nambu proposed an extension of dynamical system through the introduction of a new bracket (Nambu bracket) in 1973. This article is a short review of the developments after his paper. Some emphasis are put on a viewpoint that the Nambu bracket naturally describes extended objects which appear in M-theory and the fluid dynamics. The latter part of the paper is devoted to a review of the studies on the Nambu bracket (Lie 3-algebra) in Bagger-Lambert-Gustavsson theory of multiple M2-branes. This paper is a contribution to the proceedings of Nambu memorial symposium (Osaka City University, September 29, 2015).

hep-th↗