Aspect Sentiment Quad Prediction (ASQP) aims to identify quadruples consisting of an aspect term, aspect category, opinion term, and sentiment polarity from a given sentence, which is the most representative and challenging task in aspect-based sentiment analysis. A major challenge arises when implicit sentiment is present, as existing models often confuse implicit and explicit sentiment, making it difficult to extract the quadruples effectively. To tackle this issue, we propose a framework that leverages distinct labeled features from diverse reviews and incorporates pseudo-token prompts to harness the semantic knowledge of pre-trained models, effectively capturing both implicit and explicit sentiment expressions. Our approach begins by categorizing reviews based on the presence of implicit sentiment elements. We then build new samples that combine those with implicit sentiment and those with explicit sentiment. Next, we employ prompts with pseudo-tokens to guide the model in distinguishing between implicit and explicit sentiment expressions. Extensive experimental results show that our proposed method enhances the model’s ability across four public datasets, averaging 1.99% F1 improvement, particularly in instances involving implicit sentiment. We release our code at https://github.com/chienarmor/absa-implicit.

Temporal Knowledge graph completion (TKGC) is a crucial task that involves reasoning at known timestamps to complete the missing part of facts and has attracted more and more attention in recent years. Most existing methods focus on learning representations based on graph neural networks while inaccurately extracting information from timestamps and insufficiently utilizing the implied information in relations. To address these problems, we propose a novel TKGC model, namely Pre-trained Language Model with Prompts for TKGC (PPT). We convert a series of sampled quadruples into pre-trained language model inputs and convert intervals between timestamps into different prompts to make coherent sentences with implicit semantic information. We train our model with a masking strategy to convert TKGC task into a masked token prediction task, which can leverage the semantic information in pre-trained language models. Experiments on three benchmark datasets and extensive analysis demonstrate that our model has great competitiveness compared to other models with four metrics. Our model can effectively incorporate information from temporal knowledge graphs into the language models.