| Challenge: | Existing word representations based on distributional hypothesis do not provide accurate representations of emotions. |
| Approach: | They propose a method to obtain emotion-enriched word representations by remote supervision using a large training dataset of text documents and two recurrent neural network architectures. |
| Outcome: | The proposed method outperforms competing general-purpose and affective representations on two tasks. |
Similar Papers
Aff2Vec: Affect–Enriched Distributional Word Representations (C18-1)
Copied to clipboard
| Challenge: | Affective word distributions are not well understood in literature. |
| Approach: | They propose a model that embeds affective word interpretations into enriched word embeddings. |
| Outcome: | The proposed model outperforms the state-of-the-art in word-similarity tasks and in emotion analysis, personality detection, and frustration prediction tasks. |
Emotion Enriched Retrofitted Word Embeddings (2022.coling-1)
Copied to clipboard
| Challenge: | Word embeddings that encode lexical-semantic relations do not capture emotion aspects of words. |
| Approach: | They propose a retrofitting method to update the vectors of emotion bearing words . they find that the retrofitted embeddings achieve better distances between clusters . |
| Outcome: | The proposed method achieves better distances between clusters and clusters for words having the same emotions. |
Affective Retrofitted Word Embeddings (2022.aacl-main)
Copied to clipboard
| Challenge: | Word embeddings do not capture affective dimensions of valence, arousal, and dominance . valency, valance, and adolescence are present in words, but are not represented in text . |
| Approach: | They propose a method for updating word embeddings for affective meaning . they use a non-linear transformation function that maps pre-trained embedders to an affective vector space . |
| Outcome: | The proposed method improves inter-cluster and intra-c cluster distances for emotion-bearing words. |
Emotion Representation Mapping for Automatic Lexicon Construction (Mostly) Performs on Human Level (C18-1)
Copied to clipboard
| Challenge: | Emotion Representation Mapping (ERM) is an alternative to Word Emotion Induction (WEI) for automatic emotion lexicon construction. |
| Approach: | They propose a neural network approach to ERM that converts existing emotion ratings from one representation format into another by mapping Valence-Arousal-Dominance annotations into Ekman’s Basic Emotions. |
| Outcome: | The proposed model outperforms the state-of-the-art in 13 languages and is almost as reliable as human annotations even in cross-lingual settings. |
Representation Mapping: A Novel Approach to Generate High-Quality Multi-Lingual Emotion Lexicons (L18-1)
Copied to clipboard
| Challenge: | Existing representational frameworks for emotion encoding are incompatible with semantic polarity, resulting in a large amount of incompatible emotion lexicons. |
| Approach: | They propose to map different emotion representation formats onto each other for mutual compatibility and interoperability of language resources. |
| Outcome: | The proposed method produces (near-)gold quality emotion lexicons even in crosslingual settings. |
Word Emotion Induction for Multiple Languages as a Deep Multi-Task Learning Problem (N18-1)
Copied to clipboard
| Challenge: | a recent shift towards expressive emotion representation models has hampered deep learning in sentiment analysis. |
| Approach: | They propose a multi-task learning problem to solve a language data bottleneck . they propose to use word emotion induction as an individual task to predict emotion . |
| Outcome: | The proposed model outperforms a wide range of other methods on 9 languages and 15 conditions. |
Towards Label-Agnostic Emotion Embeddings (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing representation schemes for emotion analysis are based on label formats, natural languages, and even disparate model architectures. |
| Approach: | They propose a training scheme that learns a shared latent representation of emotion independent from different label formats, natural languages, and even disparate model architectures. |
| Outcome: | The proposed model performs well on a wide range of datasets without penalizing prediction quality. |
ESTeR: Combining Word Co-occurrences and Word Associations for Unsupervised Emotion Detection (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies list as many as 154 human emotions, but most researchers agree on basic emotions such as anger, fear, disgust, sadness, surprise, and happiness. |
| Approach: | They propose an unsupervised model for identifying emotions using a novel similarity function based on random walks on graphs. |
| Outcome: | The proposed model can be computed efficiently and avoids dependence on labeled datasets. |
Distributed Representations of Emotion Categories in Emotion Space (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies on emotion detection focus on how to improve performance of models . however, emotion relations are ignored in one-hot representations . |
| Approach: | They propose a framework to learn distributed representations for emotion categories in emotion space from a given emotion classification dataset. |
| Outcome: | The proposed representations can express emotion relations much better than word vectors in semantic space. |
Guilt by Association: Emotion Intensities in Lexical Representations (2021.emnlp-main)
Copied to clipboard
| Challenge: | linguistic models have a higher correlation with human ground truth ratings than labeled data . word vectors have often been evaluated on standard word relatedness benchmarks . |
| Approach: | They propose to use unsupervised, supervised, and finally supervised methods to extract emotional associations from pretrained vectors and models. |
| Outcome: | The proposed method shows higher correlation with ground truth ratings than state-of-the-art lexicons based on labeled data. |