ECNU at SemEval-2017 Task 1: Leverage Kernel-based Traditional NLP features and Neural Networks to Build a Universal Model for Multilingual and Cross-lingual Semantic Textual Similarity

2017-08-01 · SEMEVAL 2017 8 · Junfeng Tian, Zhiheng Zhou, Man Lan, Yuanbin Wu

To address semantic similarity on multilingual and cross-lingual sentences, we firstly translate other foreign languages into English, and then feed our monolingual English system with various interactive features. Our system is further supported by combining with deep learning semantic similarity and our best run achieves the mean Pearson correlation 73.16{\%} in primary track.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Lingual Semantic Textual SimilarityMachine Translation Semantic Similarity Semantic Textual Similarity

ECNU at SemEval-2018 Task 2: Leverage Traditional NLP Features and Neural Networks Methods to Address Twitter Emoji Prediction Task

2018-06-01 · SEMEVAL 2018 6 · Xingwu Lu, Xin Mao, Man Lan, Yuanbin Wu

This paper describes our submissions to Task 2 in SemEval 2018, i.e., Multilingual Emoji Prediction. We first investigate several traditional Natural Language Processing (NLP) features, and then design several deep learn…

Deep Learning Prediction Task 2

ECNU at SemEval-2016 Task 3: Exploring Traditional Method and Deep Learning Method for Question Retrieval and Answer Ranking in Community Question Answering

2016-06-01 · SEMEVAL 2016 6 · Guoshun Wu, Man Lan

Community Question Answering Question Answering Question Similarity Retrieval+1

ECNU at SemEval-2016 Task 4: An Empirical Investigation of Traditional NLP Features and Word Embedding Features for Sentence-level and Topic-level Sentiment Analysis in Twitter

2016-06-01 · SEMEVAL 2016 6 · Yunxiao Zhou, Zhihua Zhang, Man Lan

Feature Engineering Language Modeling Language Modelling Sentence+1

ECNU at SemEval-2018 Task 1: Emotion Intensity Prediction Using Effective Features and Machine Learning Models

2018-06-01 · SEMEVAL 2018 6 · Huimin Xu, Man Lan, Yuanbin Wu

This paper describes our submissions to SemEval 2018 task 1. The task is affect intensity prediction in tweets, including five subtasks. We participated in all subtasks of English tweets. We extracted several traditional…

BIG-bench Machine Learning Emotion Classification Feature Engineering General Classification+2

ECNU at SemEval-2017 Task 4: Evaluating Effective Features on Machine Learning Methods for Twitter Message Polarity Classification

2017-08-01 · SEMEVAL 2017 8 · Yunxiao Zhou, Man Lan, Yuanbin Wu

This paper reports our submission to subtask A of task 4 (Sentiment Analysis in Twitter, SAT) in SemEval 2017, i.e., Message Polarity Classification. We investigated several traditional Natural Language Processing (NLP) …

BIG-bench Machine Learning Feature Engineering General Classification Lemmatization+2