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。
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).
Natural language generation (NLG) tasks on pro-drop languages are known to suffer from zero pronoun (ZP) problems, and the problems remain challenging due to the scarcity of ZP-annotated NLG corpora.
In this paper, as an alternative, we propose a novel approach to few-shot learning with pre-trained token-replaced detection models like ELECTRA.
To this end, we propose two pre-training tasks.
We hope that knowledge gained while learning for English AMR parsing and text generation can be transferred to the counterparts of other languages.
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.
Most existing RC models are developed on formal datasets such as news articles and Wikipedia documents, which severely limit their performances when directly applied to the noisy and informal texts in social media.
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.
In the literature, the research on abstract meaning representation (AMR) parsing is much restricted by the size of human-curated dataset which is critical to build an AMR parser with good performance.
Ranked #10 on AMR Parsing on LDC2017T10 (using extra training data)
This justifies the importance of the document-level sentiment preference information to ASC and the effectiveness of our approach capturing such information.
Due to its great importance in deep natural language understanding and various down-stream applications, text-level parsing of discourse rhetorical structure (DRS) has been drawing more and more attention in recent years.
In this paper, we introduce a discrete latent variable with an explicit semantic meaning to improve the CVAE on short-text conversation.
In this paper, we propose a hierarchical model to learn the global context for document-level neural machine translation (NMT).
This approach incorporates clause selection and word selection strategies to tackle the data noise problem in the task of DASC.
Recent studies on AMR-to-text generation often formalize the task as a sequence-to-sequence (seq2seq) learning problem by converting an Abstract Meaning Representation (AMR) graph into a word sequence.
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.
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.
In the literature, most of the previous studies on English implicit discourse relation recognition only use sentence-level representations, which cannot provide enough semantic information in Chinese due to its unique paratactic characteristics.
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.
On the one hand, our approach represents each utterance and each speaker as a node.
Ranked #30 on Emotion Recognition in Conversation on MELD
Document-level event factuality identification is an important subtask in event factuality and is crucial for discourse understanding in Natural Language Processing (NLP).
We tackle discourse-level relation recognition, a problem of determining semantic relations between text spans.
On the basis, we propose a three-stage hierarchical matching network to explore deep sentiment information in a QA text pair.
Question-Answer (QA) matching is a fundamental task in the Natural Language Processing community.
In particular, we incorporate image processing into the acquisition of similar event instances, including the utilization of images for visually representing event scenes, and the use of the neural network based image matching for approximate calculation between events.
In view of the differences between the annotations of micro and macro discourse rela-tionships, this paper describes the relevant experiments on the construction of the Macro Chinese Discourse Treebank (MCDTB), a higher-level Chinese discourse corpus.
In this paper, we come up with a feature adaptation approach for cross-lingual relation classification, which employs a generative adversarial network (GAN) to transfer feature representations from one language with rich annotated data to another language with scarce annotated data.
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.
In addition, since the influences of different linguistic information are different, we propose a hierarchical attention network to weigh the importance of various linguistic information, and learn the mutual attention between the document and the linguistic information.
The task of nuclearity recognition in Chinese discourse remains challenging due to the demand for more deep semantic information.
Discourse parsing is a challenging task and plays a critical role in discourse analysis.
Due to the ability of encoding and mapping semantic information into a high-dimensional latent feature space, neural networks have been successfully used for detecting events to a certain extent.
Aspect sentiment classification, a challenging taskin sentiment analysis, has been attracting more andmore attention in recent years.
Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text.
Even though a linguistics-free sequence to sequence model in neural machine translation (NMT) has certain capability of implicitly learning syntactic information of source sentences, this paper shows that source syntax can be explicitly incorporated into NMT effectively to provide further improvements.
Previous studies on temporal relation extraction focus on mining sentence-level information or enforcing coherence on different temporal relation types among various event mentions in the same sentence or neighboring sentences, largely ignoring those discourse-level temporal relations in nonadjacent sentences.
Visualization of the attention layers illustrates that the model selects qualitatively informative words.
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.