Search Results for author:
Found 39 papers, 5 papers with code
基于对话约束的回复生成研究(Research on Response Generation via Dialogue Constraints)
现有的对话系统中存在着生成“好的”、“我不知道”等无意义的安全回复问题。日常对话中, 对话者通常围绕特定的主题进行讨论且每句话都有明显的情感和意图。因此该文提出了基于对话约束的回复生成模型, 即在Seq2Seq模型的基础上, 结合对对话的主题、情感、意图的识别。该方法对生成回复的主题、情感和意图进行约束, 从而生成具有合理的情感和意图且与对话主题相关的回复。实验证明, 该文提出的方法能有效地提高生成回复的质量。
Multi-modal Multi-label Emotion Detection with Modality and Label Dependence
In this paper, we focus on multi-label emotion detection in a multi-modal scenario.
Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection
Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA).
One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification
Knowledge distillation is an effective method to transfer knowledge from a large pre-trained teacher model to a compacted student model.
Aspect-based Sentiment Analysis with Opinion Tree Generation
Furthermore, we propose a pre-trained model to integrate both syntax and semantic features for opinion tree generation.
Pre-trained Token-replaced Detection Model as Few-shot Learner
In this paper, as an alternative, we propose a novel approach to few-shot learning with pre-trained token-replaced detection models like ELECTRA.
More than Text: Multi-modal Chinese Word Segmentation
Chinese word segmentation (CWS) is undoubtedly an important basic task in natural language processing.
Multimodal Topic-Enriched Auxiliary Learning for Depression Detection
To this end, we propose a new Multimodal Topic-enriched Auxiliary Learning (MTAL) approach, aiming at capturing the topic information inside different modalities (i. e., texts and images) for depression detection.
Sentiment Forecasting in Dialog
Sentiment forecasting in dialog aims to predict the polarity of next utterance to come, and can help speakers revise their utterances in sentimental utterances generation.
End-to-End Emotion-Cause Pair Extraction with Graph Convolutional Network
Emotion-cause pair extraction (ECPE), which aims at simultaneously extracting emotion-cause pairs that express emotions and their corresponding causes in a document, plays a vital role in understanding natural languages.
Ranked #6 on
Emotion-Cause Pair Extraction
on ECPE
Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue
As an important research topic, customer service dialogue generation tends to generate generic seller responses by leveraging current dialogue information.
Aspect Sentiment Classification with Document-level Sentiment Preference Modeling
This justifies the importance of the document-level sentiment preference information to ASC and the effectiveness of our approach capturing such information.
Human-Like Decision Making: Document-level Aspect Sentiment Classification via Hierarchical Reinforcement Learning
This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC.
Emotion Detection with Neural Personal Discrimination
Accordingly, we propose a Neural Personal Discrimination (NPD) approach to address above challenges by determining personal attributes from posts, and connecting relevant posts with similar attributes to jointly learn their emotions.
Adversarial Attention Modeling for Multi-dimensional Emotion Regression
In this paper, we propose a neural network-based approach, namely Adversarial Attention Network, to the task of multi-dimensional emotion regression, which automatically rates multiple emotion dimension scores for an input text.
Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network
This paper extends the research to interactive reviews and proposes a new research task, namely Aspect Sentiment Classification towards Question-Answering (ASC-QA), for real-world applications.
Modeling both context- and speaker-sensitive dependence for emotion detection in multi-speaker conversations
On the one hand, our approach represents each utterance and each speaker as a node.
Ranked #40 on
Emotion Recognition in Conversation
on MELD
Joint Learning for Emotion Classification and Emotion Cause Detection
We present a neural network-based joint approach for emotion classification and emotion cause detection, which attempts to capture mutual benefits across the two sub-tasks of emotion analysis.
Sentiment Classification towards Question-Answering with Hierarchical Matching Network
On the basis, we propose a three-stage hierarchical matching network to explore deep sentiment information in a QA text pair.
One vs. Many QA Matching with both Word-level and Sentence-level Attention Network
Question-Answer (QA) matching is a fundamental task in the Natural Language Processing community.
Cross-media User Profiling with Joint Textual and Social User Embedding
In realistic scenarios, a user profiling model (e. g., gender classification or age regression) learned from one social media might perform rather poorly when tested on another social media due to the different data distributions in the two media.
Aspect Sentiment Classification with both Word-level and Clause-level AttentionNetworks
Aspect sentiment classification, a challenging taskin sentiment analysis, has been attracting more andmore attention in recent years.
User Classification with Multiple Textual Perspectives
Textual information is of critical importance for automatic user classification in social media.
Two-View Label Propagation to Semi-supervised Reader Emotion Classification
In this paper, we propose a two-view label propagation approach to semi-supervised reader emotion classification by exploiting two views, namely source text and response text in a label propagation algorithm.
Corpus Fusion for Emotion Classification
Machine learning-based methods have obtained great progress on emotion classification.
Semi-supervised Gender Classification with Joint Textual and Social Modeling
In gender classification, labeled data is often limited while unlabeled data is ample.
A Bilingual Attention Network for Code-switched Emotion Prediction
Visualization of the attention layers illustrates that the model selects qualitatively informative words.
Annotating Events in an Emotion Corpus
This paper presents the development of a Chinese event-based emotion corpus.
