Edison Marrese-Taylor


2020

pdf bib
A Multi-modal Approach to Fine-grained Opinion Mining on Video Reviews
Edison Marrese-Taylor | Cristian Rodriguez | Jorge Balazs | Stephen Gould | Yutaka Matsuo
Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)

Despite the recent advances in opinion mining for written reviews, few works have tackled the problem on other sources of reviews. In light of this issue, we propose a multi-modal approach for mining fine-grained opinions from video reviews that is able to determine the aspects of the item under review that are being discussed and the sentiment orientation towards them. Our approach works at the sentence level without the need for time annotations and uses features derived from the audio, video and language transcriptions of its contents.We evaluate our approach on two datasets and show that leveraging the video and audio modalities consistently provides increased performance over text-only baselines, providing evidence these extra modalities are key in better understanding video reviews.

pdf bib
VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling
Machel Reid | Edison Marrese-Taylor | Yutaka Matsuo
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, combining distributional and lexical semantics in an implicit rather than direct way. To tackle this issue we propose a generative model for the task, introducing a continuous latent variable to explicitly model the underlying relationship between a phrase used within a context and its definition. We rely on variational inference for estimation and leverage contextualized word embeddings for improved performance. Our approach is evaluated on four existing challenging benchmarks with the addition of two new datasets, “Cambridge” and the first non-English corpus “Robert”, which we release to complement our empirical study. Our Variational Contextual Definition Modeler (VCDM) achieves state-of-the-art performance in terms of automatic and human evaluation metrics, demonstrating the effectiveness of our approach.

2019

pdf bib
An Edit-centric Approach for Wikipedia Article Quality Assessment
Edison Marrese-Taylor | Pablo Loyola | Yutaka Matsuo
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)

We propose an edit-centric approach to assess Wikipedia article quality as a complementary alternative to current full document-based techniques. Our model consists of a main classifier equipped with an auxiliary generative module which, for a given edit, jointly provides an estimation of its quality and generates a description in natural language. We performed an empirical study to assess the feasibility of the proposed model and its cost-effectiveness in terms of data and quality requirements.

2018

pdf bib
IIIDYT at SemEval-2018 Task 3: Irony detection in English tweets
Edison Marrese-Taylor | Suzana Ilic | Jorge Balazs | Helmut Prendinger | Yutaka Matsuo
Proceedings of The 12th International Workshop on Semantic Evaluation

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.

pdf bib
Learning to Automatically Generate Fill-In-The-Blank Quizzes
Edison Marrese-Taylor | Ai Nakajima | Yutaka Matsuo | Ono Yuichi
Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications

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.

pdf bib
Deep contextualized word representations for detecting sarcasm and irony
Suzana Ilić | Edison Marrese-Taylor | Jorge Balazs | Yutaka Matsuo
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

Predicting context-dependent and non-literal utterances like sarcastic and ironic expressions still remains a challenging task in NLP, as it goes beyond linguistic patterns, encompassing common sense and shared knowledge as crucial components. To capture complex morpho-syntactic features that can usually serve as indicators for irony or sarcasm across dynamic contexts, we propose a model that uses character-level vector representations of words, based on ELMo. We test our model on 7 different datasets derived from 3 different data sources, providing state-of-the-art performance in 6 of them, and otherwise offering competitive results.

pdf bib
IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations
Jorge Balazs | Edison Marrese-Taylor | Yutaka Matsuo
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

In this paper we describe our system designed for the WASSA 2018 Implicit Emotion Shared Task (IEST), which obtained 2nd place out of 30 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 them, 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.

pdf bib
Content Aware Source Code Change Description Generation
Pablo Loyola | Edison Marrese-Taylor | Jorge Balazs | Yutaka Matsuo | Fumiko Satoh
Proceedings of the 11th International Conference on Natural Language Generation

We propose to study the generation of descriptions from source code changes by integrating the messages included on code commits and the intra-code documentation inside the source in the form of docstrings. Our hypothesis is that although both types of descriptions are not directly aligned in semantic terms —one explaining a change and the other the actual functionality of the code being modified— there could be certain common ground that is useful for the generation. To this end, we propose an architecture that uses the source code-docstring relationship to guide the description generation. We discuss the results of the approach comparing against a baseline based on a sequence-to-sequence model, using standard automatic natural language generation metrics as well as with a human study, thus offering a comprehensive view of the feasibility of the approach.

2017

pdf bib
A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes
Pablo Loyola | Edison Marrese-Taylor | Yutaka Matsuo
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

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.

pdf bib
Replication issues in syntax-based aspect extraction for opinion mining
Edison Marrese-Taylor | Yutaka Matsuo
Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics

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.

pdf bib
Mining fine-grained opinions on closed captions of YouTube videos with an attention-RNN
Edison Marrese-Taylor | Jorge Balazs | Yutaka Matsuo
Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

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.

pdf bib
EmoAtt at EmoInt-2017: Inner attention sentence embedding for Emotion Intensity
Edison Marrese-Taylor | Yutaka Matsuo
Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis

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 13t place among 22 shared task competitors.

pdf bib
Refining Raw Sentence Representations for Textual Entailment Recognition via Attention
Jorge Balazs | Edison Marrese-Taylor | Pablo Loyola | Yutaka Matsuo
Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP

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.