PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge
            from emoji and #hashtags

Park, Ji Ho; Xu, Peng; Fung, Pascale

doi:10.18653/v1/s18-1039

Cited by 40 publications

(23 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second place winner of the SemEval leaderboard trained a word-level bidirectional LSTM with attention, and it also included non-deep learning features in its ensemble [34]. Ji Ho Park et al [35] trained two models to solve this problem: regularized linear regression and logistic regression classifier chain [11]. They tried to exploit labels' correlation to perform multi-label classification.…”

Section: Emotion Classification In Tweetsmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning-Based Approach for Multi-Label Emotion Classification in Tweets

2019

View full text Add to dashboard Cite

Currently, people use online social media such as Twitter or Facebook to share their emotions and thoughts. Detecting and analyzing the emotions expressed in social media content benefits many applications in commerce, public health, social welfare, etc. Most previous work on sentiment and emotion analysis has only focused on single-label classification and ignored the co-existence of multiple emotion labels in one instance. This paper describes the development of a novel deep learning-based system that addresses the multiple emotion classification problem in Twitter. We propose a novel method to transform it to a binary classification problem and exploit a deep learning approach to solve the transformed problem. Our system outperforms the state-of-the-art systems, achieving an accuracy score of 0.59 on the challenging SemEval2018 Task 1:E-cmulti-label emotion classification problem.

show abstract

Section: Emotion Classification In Tweetsmentioning

confidence: 99%

“…• NTUA-SLP: the system submitted by the winner team of the SemEval-2018 Task1:E-cchallenge[33].• TCS: the system submitted by the second place winner[34]. • PlusEmo2Vec: the system submitted by the third place winner[35].•Transformer: a deep learning system based on large pre-trained language models developed by the NVIDIA AI lab[39].…”

mentioning

confidence: 99%

A Deep Learning-Based Approach for Multi-Label Emotion Classification in Tweets

2019

View full text Add to dashboard Cite

show abstract

“…ethos). Instances derived from research on emoji hashtags showed that Twitter and Instagram users tag a cluster of emoji to convey a message subject [18] and to express emotional statement [32].…”

Section: Emoji Sequencesmentioning

confidence: 99%

Emoji Sequence Use in Enacting Personal Identity

2019

Companion Proceedings of the 2019 World Wide Web Conference

View full text Add to dashboard Cite

Focusing on a Chinese social media platform, this study adopts computer-mediated discourse analysis to examine how users employ emoji sequences to construct their personal identity through the expression of stance and engagement. Seven types of linguistic elements were identified by conducting stance and engagement analysis on emoji sequences in posts by social media influencers. Stance was more frequent than engagement. Attitude markers were the most common element used to convey stance, whereas directive was the most prevalent element used to express engagement. In addition, emoji sequences that did not convey stance and engagement were coded as n/a. This study also observed creative usages in the composition of emoji sequences that compensate for the lack of a prescribed emoji sequence grammar. Based on these findings, it advances recommendations for the design of emoji and of social media platforms grounded in linguistic principles.

show abstract

“…Ensemble methods have been shown very effective in many natural language processing tasks (Park et al, 2018;Winata et al, 2019). We apply an ensemble method by taking the top five translations from word-level and subword-level NMT, and rescore all translations using our pre-trained Czech language model mentioned in §2.3.…”

Section: Model Ensemblementioning

confidence: 99%

Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring

Liu¹,

Xu²,

Winata³

et al. 2019

Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)

Self Cite

View full text Add to dashboard Cite

This paper describes CAiRE's submission to the unsupervised machine translation track of the WMT'19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consistency of translations, a rescoring mechanism is proposed that reuses the pre-trained language model to select the translation candidates generated through beam search. Moreover, a series of pre-processing and post-processing approaches are applied to improve the quality of final translations.

show abstract

PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags

Cited by 40 publications

References 17 publications

A Deep Learning-Based Approach for Multi-Label Emotion Classification in Tweets

A Deep Learning-Based Approach for Multi-Label Emotion Classification in Tweets

Emoji Sequence Use in Enacting Personal Identity

Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring

Contact Info

Product

Resources

About