OhioState at IJCNLP-2017 Task 4: Exploring Neural Architectures for Multilingual Customer Feedback Analysis

2017-10-18 · IJCNLP 2017 12 · Dushyanta Dhyani

This paper describes our systems for IJCNLP 2017 Shared Task on Customer Feedback Analysis. We experimented with simple neural architectures that gave competitive performance on certain tasks. This includes shallow CNN and Bi-Directional LSTM architectures with Facebook's Fasttext as a baseline model. Our best performing model was in the Top 5 systems using the Exact-Accuracy and Micro-Average-F1 metrics for the Spanish (85.28% for both) and French (70% and 73.17% respectively) task, and outperformed all the other models on comment (87.28%) and meaningless (51.85%) tags using Micro Average F1 by Tags metric for the French task.

📄 PDF Abstract BibTeX arXiv:1710.06931

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

fastText fastText embeddings exploit subword information to construct word embeddings. Representations are learnt of character $n$-grams, and words represented as the sum of the…

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

All-In-1 at IJCNLP-2017 Task 4: Short Text Classification with One Model for All Languages

2017-12-01 · IJCNLP 2017 12 · Barbara Plank

We present All-In-1, a simple model for multilingual text classification that does not require any parallel data. It is based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and…

All General Classification Multilingual text classification Multilingual Word Embeddings+3

MainiwayAI at IJCNLP-2017 Task 2: Ensembles of Deep Architectures for Valence-Arousal Prediction

2017-12-01 · IJCNLP 2017 12 · Yassine Benajiba, Jin Sun, Yong Zhang, Zhiliang Weng 외

This paper introduces Mainiway AI Labs submitted system for the IJCNLP 2017 shared task on Dimensional Sentiment Analysis of Chinese Phrases (DSAP), and related experiments. Our approach consists of deep neural networks …

Prediction Sentiment Analysis Task 2 Word Embeddings

ALL-IN-1: Short Text Classification with One Model for All Languages

2017-10-26 · Barbara Plank

We present ALL-IN-1, a simple model for multilingual text classification that does not require any parallel data. It is based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and…

All General Classification Multilingual text classification Multilingual Word Embeddings+3

IJCNLP-2017 Task 5: Multi-choice Question Answering in Examinations

2017-12-01 · IJCNLP 2017 12 · Shangmin Guo, Kang Liu, Shizhu He, Cao Liu 외

The IJCNLP-2017 Multi-choice Question Answering(MCQA) task aims at exploring the performance of current Question Answering(QA) techniques via the realworld complex questions collected from Chinese Senior High School Entr…

Question Answering

IIITT at CASE 2021 Task 1: Leveraging Pretrained Language Models for Multilingual Protest Detection

2021-08-01 · ACL (CASE) 2021 8 · Pawan Kalyan, Duddukunta Reddy, Adeep Hande, Ruba Priyadharshini 외

In a world abounding in constant protests resulting from events like a global pandemic, climate change, religious or political conflicts, there has always been a need to detect events/protests before getting amplified by…

Sentence Sentence Classification