SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment (P18-1)
Copied to clipboard
| Challenge: | SemAxis characterizes word semantics using many semantic axes in word-vector spaces beyond sentiment . lexicon-based text analysis assumes that meaning of words does not change across contexts . but, recent advances in vector-space representations can tackle this challenge . |
| Approach: | They propose a framework to characterize word semantics using many semantic axes beyond sentiment . they demonstrate that SemAxis can capture nuanced semantic representations in multiple online communities . |
| Outcome: | The proposed framework outperforms state-of-the-art approaches in building domain-specific sentiment lexicons. |
Similar Papers
WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations (N19-1)
Copied to clipboard
| Challenge: | Existing word embeddings cannot model the dynamic nature of words’ semantics, i.e., the property of words to correspond to potentially different meanings. |
| Approach: | They propose a large-scale Word in Context dataset, called WiC, which is curated by experts and can be used to evaluate context-sensitive representations. |
| Outcome: | The proposed models outperform the standard evaluation dataset for the purpose and highlight their shortcomings. |
Top-Rank-Focused Adaptive Vote Collection for the Evaluation of Domain-Specific Semantic Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Embedding-based models are increasingly needed for domain-specific evaluation datasets. |
| Approach: | They propose a protocol for the construction of a relatedness-based evaluation dataset based on adaptive pairwise comparisons and appropriate metrics to evaluate a semantic model via the aforementioned dataset. |
| Outcome: | The proposed protocol is particularly accurate in top-rank evaluation. |
Domain-Specific Sentiment Lexicons Induced from Labeled Documents (2020.coling-main)
Copied to clipboard
| Challenge: | Existing sentiment lexicons reflect abstract notion of polarity and do not do justice to substantial differences of word polarities between domains. |
| Approach: | They propose to use domain-specific sentiment lexicons to induce initial word intensity scores and train new deep models based on word vector representations to overcome the scarcity of the seed data. |
| Outcome: | The proposed models show that they perform well on review classification and cross-lingual word sentiment prediction. |
Cross-Domain Sentiment Classification using Semantic Representation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on cross-domain sentiment classification ignore the semantic relevance between domains. |
| Approach: | They propose to use Abstract Meaning Representation to help with cross-domain sentiment classification by combining sentence-level AMRs with text-graph interaction models. |
| Outcome: | The proposed model is effective over strong baselines and shows its importance over strong models. |
On the Importance of Distinguishing Word Meaning Representations: A Case Study on Reverse Dictionary Mapping (N19-1)
Copied to clipboard
| Challenge: | Sense representations target meaning conflation deficiency but their potential impact has not been investigated in downstream NLP applications. |
| Approach: | They propose to use a reverse dictionary system to address meaning conflation deficiency . they propose to integrate senses into the system to improve semantic understanding . |
| Outcome: | The proposed approach can improve the performance of a downstream NLP application. |
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. |
How do Words Contribute to Sentence Semantics? Revisiting Sentence Embeddings with a Perturbation Method (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on sentence representation learning focus on human annotation, but they neglect the critical property that essential contents should contribute to sentence semantics more than non-essential contents when encoding a sentence. |
| Approach: | They propose a perturbation method for unsupervised semantic analysis that uses a sentence compression metric to adapt sentence compression datasets for automatic evaluation. |
| Outcome: | The proposed method can capture the main semantics of sentences better than several SOTA unsupervised sentence embedding models. |
Discovering Differences in the Representation of People using Contextualized Semantic Axes (2022.emnlp-main)
Copied to clipboard
| Challenge: | Past work has compared embeddings against “semantic axes” that represent two opposing concepts. |
| Approach: | They extend this paradigm to BERT embeddings and construct contextualized axes that mitigate pitfall where antonyms have neighboring representations. |
| Outcome: | The proposed axes can characterize differences among instances of the same word type on two people-centric datasets. |
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. |
Learning Domain-Sensitive and Sentiment-Aware Word Embeddings (P18-1)
Copied to clipboard
| Challenge: | Existing word embeddings cannot produce domain-sensitive embeddables due to domain-specific nature of words. |
| Approach: | They propose a method for learning domain-sensitive and sentiment-aware embeddings that captures sentiment semantics and domain sensitivity of individual words. |
| Outcome: | The proposed method can produce domain-common embeddings and domain-specific embedds. |