相关论文: Rethinking Attribute Representation and Injection …

Emotion labels in emotion recognition corpora are highly noisy and ambiguous, due to the annotators' subjective perception of emotions. Such ambiguity may introduce errors in automatic classification and affect the overall performance. We…

Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to…

Sentiment analysis on large-scale social media data is important to bridge the gaps between social media contents and real world activities including political election prediction, individual and public emotional status monitoring and…

Aspect sentiment classification (ASC) aims at determining sentiments expressed towards different aspects in a sentence. While state-of-the-art ASC models have achieved remarkable performance, they are recently shown to suffer from the issue…

This paper proposes joint attention estimation in a single image. Different from related work in which only the gaze-related attributes of people are independently employed, (I) their locations and actions are also employed as contextual…

Recently, sentiment-aware pre-trained language models (PLMs) demonstrate impressive results in downstream sentiment analysis tasks. However, they neglect to evaluate the quality of their constructed sentiment representations; they just…

Model editing aims at selectively updating a small subset of a neural model's parameters with an interpretable strategy to achieve desired modifications. It can significantly reduce computational costs to adapt to large language models…

Aspect-level sentiment classification (ASC) aims to detect the sentiment polarity of a given opinion target in a sentence. In neural network-based methods for ASC, most works employ the attention mechanism to capture the corresponding…

In recommender systems, models mostly use a combination of embedding layers and multilayer feedforward neural networks. The high-dimensional sparse original features are downscaled in the embedding layer and then fed into the fully…

Sentiment transfer aims at revising the input text to satisfy a given sentiment polarity while retaining the original semantic content. The nucleus of sentiment transfer lies in precisely separating the sentiment information from the…

With the growth of social medias, such as Twitter, plenty of user-generated data emerge daily. The short texts published on Twitter -- the tweets -- have earned significant attention as a rich source of information to guide many…

While existing machine learning models have achieved great success for sentiment classification, they typically do not explicitly capture sentiment-oriented word interaction, which can lead to poor results for fine-grained analysis at the…

By computing the rank correlation between attention weights and feature-additive explanation methods, previous analyses either invalidate or support the role of attention-based explanations as a faithful and plausible measure of salience.…

Sentiment analysis benefits from large, hand-annotated resources in order to train and test machine learning models, which are often data hungry. While some languages, e.g., English, have a vast array of these resources, most…

Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences. We propose to view text classification as a label-word joint embedding…

[Purpose] To understand the meaning of a sentence, humans can focus on important words in the sentence, which reflects our eyes staying on each word in different gaze time or times. Thus, some studies utilize eye-tracking values to optimize…

Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…

In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention…

The classic supervised classification algorithms are efficient, but time-consuming, complicated and not interpretable, which makes it difficult to analyze their results that limits the possibility to improve them based on real observations.…

Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. However, due to data sampling and algorithmic stochasticity, expressive models can be unstable,…