Dialogue summarization (DS) plays a vital role in improving customer service efficiency by automatically generating concise summaries from lengthy multi-turn dialogues. However, existing studies largely overlook the fine-grained sentiment dynamics expressed by customers, and most DS datasets lack detailed sentiment annotations. These limitations hinder both accurate service quality assessment and the development of sentiment-aware summarization models. To address these challenges, we propose a three-stage approach to building an aspect-aware sentiment dataset, comprising: (1) aspect-anchored dialogue rewriting, (2) dialogue-anchored explainable label generation, and (3) label-dialogue integrated summarization. Building upon this scheme, we construct FOCUS, a Fine-grained customer-Oriented Chinese dialogUe Summarization dataset. FOCUS is the first Chinese dataset with 12,948 dialogues annotated for multi-level aspects, sentiment polarity, opinion content, emotions, as well as customer-oriented formatted and free-style sentiment summaries. To demonstrate the challenges and utility of FOCUS, we benchmark a range of summarization models on FOCUS and observe that current methods often exhibit misalignment between aspects and sentiments. Meanwhile, we find that a Chain-of-Thought approach can enhance faithfulness and interpretability, highlighting promising directions for future research on this dataset. FOCUS serves as a valuable resource to advance research in sentiment-aware DS and related tasks.

Textual Emotion-Cause Pair Extraction in Conversations (TECPE) requires identifying emotion utterances, their categories, and the textual cause spans that explain them. Although recent systems improve aggregate scores, clean supervision can induce evidence bias: models exploit explicit emotion cues, cause–emotion proximity, and speaker/discourse priors rather than evidence sufficient for causal explanation. We introduce SAAM-EC, a sufficiency-aware adversarial evidence masking framework for span-grounded TECPE. SAAM-EC adversarially masks high-impact conversational evidence units during training, but treats masking as a semantic intervention rather than a label-preserving perturbation. When masking removes the cause span or necessary bridge context, the original span may no longer be extractable or justified. SAAM-EC therefore combines adversarial masking with a sufficiency gate and an extractability guard, training masked examples to recover the original span only when the remaining dialogue still supports the emotion–cause relation and preserves the annotated span; otherwise, it trains the model with an unanswerability objective. All auxiliary components are discarded at inference, leaving the backbone unchanged. Experiments on span-level TECPE and utterance-level ECPE benchmarks show consistent performance gains over clean backbones and masking-based alternatives. Diagnostics further show better recovery on distant and cross-speaker causes and stronger abstention under destructive masks.

Current emotion analysis in social media is predominantly author-centric, failing to capture the subjective nature of emotional responses across diverse readers. This paradigm overlooks the crucial link between individual perception, implicit propagation intent, propagation behavior, and the underlying social network. To bridge this gap, we introduce EmoIntenNet, a novel bilingual (English and Chinese) large-scale benchmark that uniquely integrates six critical dimensions for social perception: author-created content, actual readers’ emotional feedback (derived from their comments), implicit propagation intent, explicit propagation behavior, user attributes, and the social relationship graph. This benchmark advances the shift towards more granular, reader-centric analysis, where different readers’ emotional responses to the same content are grounded in their actual social interactions rather than simulated annotations. By annotating implicit emotions from reader comments and synchronously capturing implicit multi-label propagation intents, EmoIntenNet provides a unique resource to model the intrinsic triadic coupling among implicit emotion, implicit intent, and explicit behavior, grounded in social context. We establish a comprehensive evaluation protocol, testing state-of-the-art methods, including large language models (LLMs) with advanced reasoning enhancement. Our findings reveal significant shortcomings in existing approaches when handling this multifaceted, user-aware task. EmoIntenNet offers a foundational resource and clear direction for future research in socially-intelligent NLP, pushing models towards a more unified understanding of emotion on social media.

Joint relation extraction models effectively mitigate the error propagation problem inherently present in pipeline models. Nevertheless, joint models face challenges including high computational complexity, complex network architectures, difficult parameter tuning, and notably, limited interpretability. In contrast, recent advances in pipeline relation extraction models (PURE, PL-Marker) have attracted considerable attention due to their lightweight design and high extraction accuracy. A key advancement is the introduction of a marker mechanism, which enhances relation extraction (RE) process by highlighting entities. However, these models primarily focus on generating correct labels. In doing so, they neglect the label selection process. Moreover, they fail to adequately capture the intricate interactions between entity pairs. To overcome these limitations, we develop a Candidate Label Markers (CLMs) mechanism that prioritizes strategic label selection over simple label generation. Furthermore, we facilitate interactions among diverse relation pairs, enabling the identification of more intricate relational patterns. Experimental results show that we achieve a new SOTA performance. Specifically, based on the same Named Entity Recognition (NER) results as theirs, we improve the SOTA methods by 2.5%, 1.9%, 1.2% in terms of strict F1 scores on SciERC, ACE05 and ACE04.

知识图谱问题生成任务是从给定的知识图谱中生成与其相关的问题。目前,知识图谱问题生成模型主要使用基于RNN或Transformer对知识图谱子图进行编码,但这种方式丢失了显式的图结构化信息,在解码器中忽视了局部信息对节点的重要性。本文提出迭代信息传递图编码器来编码子图,获取子图显式的图结构化信息,此外,我们还使用滑动窗口注意力机制提高RNN解码器,提升子图局部信息对节点的重要度。从WQ和PQ数据集上的实验结果看,我们提出的模型比KTG模型在BLEU4指标上分别高出2.16和15.44,证明了该模型的有效性。