With the development of deep learning, the method of large-scale dialogue generation based on deep learning has received extensive attention. The current research has aimed to solve the problem of the quality of generated dialogue content, but has failed to fully consider the emotional factors of generated dialogue content. In order to solve the problem of emotional response in the open domain dialogue system, we proposed a dynamic emotional session generation model (DESG). On the basis of the Seq2Seq (sequence-to-sequence) framework, the model abbreviation incorporates a dictionary-based attention mechanism that encourages the substitution of words in response with synonyms in emotion dictionaries. Meanwhile, in order to improve the model, internal emotion regulator and emotion classifier mechanisms are introduced in order to build a large-scale emotion-session generation model. Experimental results show that our DESG model can not only produce an appropriate output sequence in terms of content (related grammar) for a given post and emotion category, but can also express the expected emotional response explicitly or implicitly.

No abstract

Aspect-level sentiment analysis is a fundamental task in NLP, and it aims to predict the sentiment polarity of each specific aspect term in a given sentence. Recent researches show that the finegrained sentiment analysis for aspect-level has become a research hotspot. However, previous work did not consider the influence of grammatical rules on aspect-level sentiment analysis. In addition, attention mechanism is too simple to learn attention information from context and target interactively. Therefore, we propose an interactive rule attention network (IRAN) for aspect-level sentiment analysis. IRAN not only designs a grammar rule encoder, which simulates the grammatical functions at the sentence by standardizing the output of adjacent positions, but also constructs an interaction attention network to learn attention information from context and target. Experimental results on SemEval 2014 Dataset and ACL 2014 Twitter Dataset demonstrate IRAN can learn effective features and obtain superior performance over the baseline models. INDEX TERMS Aspect-level sentiment analysis, grammatical rules, IRAN, interaction attention network.

Aspect-Based (also known as aspect-level) Sentiment Classification (ABSC) aims at determining the sentimental tendency of a particular target in a sentence. With the successful application of the attention network in multiple fields, attention-based ABSC has aroused great interest. However, most of the previous methods are difficult to parallelize, insufficiently obtain, and fuse the interactive information. In this paper, we proposed a Multiple Interactive Attention Network (MIN). First, we used the Bidirectional Encoder Representations from Transformers (BERT) model to pre-process the data. Then, we used the partial transformer to obtain a hidden state in parallel. Finally, we took the target word and the context word as the core to obtain and fuse the interactive information. Experimental results on the different datasets showed that our model was much more effective.Appl. Sci. 2020, 10, 2052 2 of 15 words [7]. However, these models simply average the aspect or context vector to guide learning the attention weight on the context or aspect words. Therefore, these models are still in the preliminary stage in dealing with fine-grained sentiment analysis.In conclusion, there are two problems with previous approaches. The first problem is that previous approaches are difficult to obtain the hidden state interactively in parallel. Another problem is to insufficiently obtain and fuse contextual information and aspect information.This paper proposed a model named Multiple Interactive Attention Network (MIN) to address these problems. To address the first problem, we took advantage of Multi-Head Attention (MHA) to obtain useful interactive information. To address another problem, we adopted target-context pair and Context-Target-Interaction (CTI) in our model.The main contributions of this paper are presented as follows:1.We took advantage of MHA and Location-Point-Wise Feed-Forward Networks (LPFFN) to obtain the hidden state interactively in parallel. Besides, we applied pre-trained Bidirectional Encoder Representations from Transformers (BERT) [8] in our model. 2.We used the CTI and target-context pair to help us obtain and fuse useful information. We also verified the effectiveness of these two methods. 3.We experimented on different public authoritative datasets: restaurant reviews and laptop reviews of the SemEval-2014 Task 4 dataset, the ACL(Annual Meeting of the Association for Computational Linguistics) 14 Twitter dataset, SemEval-2015 Task 12 dataset, SemEval-2016 Task 5 dataset. The experimental results showed our model outperformed state-of-the-art methods.

No abstract