scholarly journals CERG: Chinese Emotional Response Generator with Retrieval Method

Research ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Yangyang Zhou ◽  
Fuji Ren
Keyword(s):  
Emotional Response ◽  
Dialogue Systems ◽  
Inference Process ◽  
Dialogue System ◽  
Data Set ◽  
Retrieval Method ◽  
Input Text ◽  
Proposed Model ◽  
Semantic Relevance ◽  
Task Oriented

The dialogue system has always been one of the important topics in the domain of artificial intelligence. So far, most of the mature dialogue systems are task-oriented based, while non-task-oriented dialogue systems still have a lot of room for improvement. We propose a data-driven non-task-oriented dialogue generator “CERG” based on neural networks. This model has the emotion recognition capability and can generate corresponding responses. The data set we adopt comes from the NTCIR-14 STC-3 CECG subtask, which contains more than 1.7 million Chinese Weibo post-response pairs and 6 emotion categories. We try to concatenate the post and the response with the emotion, then mask the response part of the input text character by character to emulate the encoder-decoder framework. We use the improved transformer blocks as the core to build the model and add regularization methods to alleviate the problems of overcorrection and exposure bias. We introduce the retrieval method to the inference process to improve the semantic relevance of generated responses. The results of the manual evaluation show that our proposed model can make different responses to different emotions to improve the human-computer interaction experience. This model can be applied to lots of domains, such as automatic reply robots of social application.

scholarly journals Dialogue state tracking accuracy improvement by distinguishing slot-value pairs and dialogue behaviour

2021 ◽  
Vol 21 (2) ◽  
pp. 1057
Author(s):  
Khaldoon H. Alhussayni ◽  
Alexander Zamyatin ◽  
S. Eman Alshamery
Keyword(s):  
Critical Role ◽  
Historical Context ◽  
Dialogue Systems ◽  
Tracking Accuracy ◽  
Dialogue System ◽  
Dialogue Acts ◽  
Proposed Model ◽  
State Tracking ◽  
Task Oriented ◽  
Previous User

<div><p>Dialog state tracking (DST) plays a critical role in cycle life of a task-oriented dialogue system. DST represents the goals of the consumer at each step by dialogue and describes such objectives as a conceptual structure comprising slot-value pairs and dialogue actions that specifically improve the performance and effectiveness of dialogue systems. DST faces several challenges: diversity of linguistics, dynamic social context and the dissemination of the state of dialogue over candidate values both in slot values and in dialogue acts determined in ontology. In many turns during the dialogue, users indirectly refer to the previous utterances, and that produce a challenge to distinguishing and use of related dialogue history, Recent methods used and popular for that are ineffective. In this paper, we propose a dialogue historical context self-Attention framework for DST that recognizes relevant historical context by including previous user utterance beside current user utterances and previous system actions where specific slot-value piers variations and uses that together with weighted system utterance to outperform existing models by recognizing the related context and the relevance of a system utterance. For the evaluation of the proposed model the WoZ dataset was used. The implementation was attempted with the prior user utterance as a dialogue encoder and second by the additional score combined with all the candidate slot-value pairs in the context of previous user utterances and current utterances. The proposed model obtained 0.8 per cent better results than all state-of-the-art methods in the combined precision of the target, but this is not the turnaround challenge for the submission.</p></div>

Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues

2021 ◽  
Vol 39 (4) ◽  
pp. 1-28
Author(s):  
Ruijian Xu ◽  
Chongyang Tao ◽  
Jiazhan Feng ◽  
Wei Wu ◽  
Rui Yan ◽  
...  
Keyword(s):  
Long Range ◽  
Response Selection ◽  
Dialogue Systems ◽  
Dialogue System ◽  
Type Representation ◽  
Response Pair ◽  
Proposed Model ◽  
Semantic Relevance ◽  
Matching Models ◽  
The Relationship

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is challenging in three aspects: (1) the meaning of a context–response pair is built upon language units from multiple granularities (e.g., words, phrases, and sub-sentences, etc.); (2) local (e.g., a small window around a word) and long-range (e.g., words across the context and the response) dependencies may exist in dialogue data; and (3) the relationship between the context and the response candidate lies in multiple relevant semantic clues or relatively implicit semantic clues in some real cases. However, existing approaches usually encode the dialogue with mono-type representation and the interaction processes between the context and the response candidate are executed in a rather shallow manner, which may lead to an inadequate understanding of dialogue content and hinder the recognition of the semantic relevance between the context and response. To tackle these challenges, we propose a representation [ K ] -interaction [ L ] -matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection. Particularly, we construct different types of representations for utterance–response pairs and deepen them via alternate encoding and interaction. By this means, the model can handle the relation of neighboring elements, phrasal pattern, and long-range dependencies during the representation and make a more accurate prediction through multiple layers of interactions between the context–response pair. Experiment results on three public benchmarks indicate that the proposed model significantly outperforms previous conventional context-response matching models and achieve slightly better results than the BERT model for multi-turn response selection in retrieval-based dialogue systems.

Robust Cross-lingual Task-oriented Dialogue

2021 ◽  
Vol 20 (6) ◽  
pp. 1-24
Author(s):  
Lu Xiang ◽  
Junnan Zhu ◽  
Yang Zhao ◽  
Yu Zhou ◽  
Chengqing Zong
Keyword(s):  
Customer Service ◽  
Dialogue Systems ◽  
Learning To Learn ◽  
Inference Process ◽  
Dialogue System ◽  
Adversarial Learning ◽  
Before And After ◽  
Adversarial Examples ◽  
Cross Lingual ◽  
Task Oriented

Cross-lingual dialogue systems are increasingly important in e-commerce and customer service due to the rapid progress of globalization. In real-world system deployment, machine translation (MT) services are often used before and after the dialogue system to bridge different languages. However, noises and errors introduced in the MT process will result in the dialogue system's low robustness, making the system's performance far from satisfactory. In this article, we propose a novel MT-oriented noise enhanced framework that exploits multi-granularity MT noises and injects such noises into the dialogue system to improve the dialogue system's robustness. Specifically, we first design a method to automatically construct multi-granularity MT-oriented noises and multi-granularity adversarial examples, which contain abundant noise knowledge oriented to MT. Then, we propose two strategies to incorporate the noise knowledge: (i) Utterance-level adversarial learning and (ii) Knowledge-level guided method. The former adopts adversarial learning to learn a perturbation-invariant encoder, guiding the dialogue system to learn noise-independent hidden representations. The latter explicitly incorporates the multi-granularity noises, which contain the noise tokens and their possible correct forms, into the training and inference process, thus improving the dialogue system's robustness. Experimental results on three dialogue models, two dialogue datasets, and two language pairs have shown that the proposed framework significantly improves the performance of the cross-lingual dialogue system.

scholarly journals UniMF: A Unified Framework to Incorporate Multimodal Knowledge Bases intoEnd-to-End Task-Oriented Dialogue Systems

2021 ◽  
Author(s):  
Shiquan Yang ◽  
Rui Zhang ◽  
Sarah M. Erfani ◽  
Jey Han Lau
Keyword(s):  
Large Scale ◽  
Knowledge Bases ◽  
Language Models ◽  
Dialogue Systems ◽  
Unified Framework ◽  
Proposed Model ◽  
Multimodal Information ◽  
Task Oriented ◽  
Novel Model ◽  
Single Modality

Knowledge bases (KBs) are usually essential for building practical dialogue systems. Recently we have seen rapidly growing interest in integrating knowledge bases into dialogue systems. However, existing approaches mostly deal with knowledge bases of a single modality, typically textual information. As today's knowledge bases become abundant with multimodal information such as images, audios and videos, the limitation of existing approaches greatly hinders the development of dialogue systems. In this paper, we focus on task-oriented dialogue systems and address this limitation by proposing a novel model that integrates external multimodal KB reasoning with pre-trained language models. We further enhance the model via a novel multi-granularity fusion mechanism to capture multi-grained semantics in the dialogue history. To validate the effectiveness of the proposed model, we collect a new large-scale (14K) dialogue dataset MMDialKB, built upon multimodal KB. Both automatic and human evaluation results on MMDialKB demonstrate the superiority of our proposed framework over strong baselines.

scholarly journals A Pre-Training Based Personalized Dialogue Generation Model with Persona-Sparse Data

2020 ◽  
Vol 34 (05) ◽  
pp. 9693-9700
Author(s):  
Yinhe Zheng ◽  
Rongsheng Zhang ◽  
Minlie Huang ◽  
Xiaoxi Mao
Keyword(s):  
State Of The Art ◽  
Language Model ◽  
Sparse Data ◽  
Generation Model ◽  
Dialogue Systems ◽  
Inference Process ◽  
Training Process ◽  
Natural Languages ◽  
Dialogue Model ◽  
Proposed Model

Endowing dialogue systems with personas is essential to deliver more human-like conversations. However, this problem is still far from well explored due to the difficulties of both embodying personalities in natural languages and the persona sparsity issue observed in most dialogue corpora. This paper proposes a pre-training based personalized dialogue model that can generate coherent responses using persona-sparse dialogue data. In this method, a pre-trained language model is used to initialize an encoder and decoder, and personal attribute embeddings are devised to model richer dialogue contexts by encoding speakers' personas together with dialogue histories. Further, to incorporate the target persona in the decoding process and to balance its contribution, an attention routing structure is devised in the decoder to merge features extracted from the target persona and dialogue contexts using dynamically predicted weights. Our model can utilize persona-sparse dialogues in a unified manner during the training process, and can also control the amount of persona-related features to exhibit during the inference process. Both automatic and manual evaluation demonstrates that the proposed model outperforms state-of-the-art methods for generating more coherent and persona consistent responses with persona-sparse data.

scholarly journals A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing

2018 ◽  
Vol 2018 ◽  
pp. 1-11
Author(s):  
A-Yeong Kim ◽  
Hyun-Je Song ◽  
Seong-Bae Park
Keyword(s):  
Attention Mechanism ◽  
Data Set ◽  
Dialog Systems ◽  
Dialog System ◽  
Fast Training ◽  
Proposed Model ◽  
Spoken Dialog System ◽  
State Tracking ◽  
Dialog State Tracking ◽  
Task Oriented

Dialog state tracking in a spoken dialog system is the task that tracks the flow of a dialog and identifies accurately what a user wants from the utterance. Since the success of a dialog is influenced by the ability of the system to catch the requirements of the user, accurate state tracking is important for spoken dialog systems. This paper proposes a two-step neural dialog state tracker which is composed of an informativeness classifier and a neural tracker. The informativeness classifier which is implemented by a CNN first filters out noninformative utterances in a dialog. Then, the neural tracker estimates dialog states from the remaining informative utterances. The tracker adopts the attention mechanism and the hierarchical softmax for its performance and fast training. To prove the effectiveness of the proposed model, we do experiments on dialog state tracking in the human-human task-oriented dialogs with the standard DSTC4 data set. Our experimental results prove the effectiveness of the proposed model by showing that the proposed model outperforms the neural trackers without the informativeness classifier, the attention mechanism, or the hierarchical softmax.

Aspect-Aware Response Generation for Multimodal Dialogue System

2021 ◽  
Vol 12 (2) ◽  
pp. 1-33
Author(s):  
Mauajama Firdaus ◽  
Nidhi Thakur ◽  
Asif Ekbal
Keyword(s):  
User Satisfaction ◽  
Dialogue Systems ◽  
Conversational Agents ◽  
Dialogue System ◽  
Multimodal Systems ◽  
Dialog System ◽  
Language And Vision ◽  
Memory Network ◽  
Multimodal Dialogue ◽  
Task Oriented

Multimodality in dialogue systems has opened up new frontiers for the creation of robust conversational agents. Any multimodal system aims at bridging the gap between language and vision by leveraging diverse and often complementary information from image, audio, and video, as well as text. For every task-oriented dialog system, different aspects of the product or service are crucial for satisfying the user’s demands. Based upon the aspect, the user decides upon selecting the product or service. The ability to generate responses with the specified aspects in a goal-oriented dialogue setup facilitates user satisfaction by fulfilling the user’s goals. Therefore, in our current work, we propose the task of aspect controlled response generation in a multimodal task-oriented dialog system. We employ a multimodal hierarchical memory network for generating responses that utilize information from both text and images. As there was no readily available data for building such multimodal systems, we create a Multi-Domain Multi-Modal Dialog (MDMMD++) dataset. The dataset comprises the conversations having both text and images belonging to the four different domains, such as hotels, restaurants, electronics, and furniture. Quantitative and qualitative analysis on the newly created MDMMD++ dataset shows that the proposed methodology outperforms the baseline models for the proposed task of aspect controlled response generation.

Study on Development of Humor Discriminator for Dialogue System

2020 ◽  
Vol 24 (3) ◽  
pp. 422-435
Author(s):  
Tomohiro Yoshikawa ◽  
◽  
Ryosuke Iwakura
Keyword(s):  
Human Subjects ◽  
The Other ◽  
P Value ◽  
Dialogue Systems ◽  
Generation System ◽  
Dialogue System ◽  
Evaluation Scores ◽  
Significant Difference ◽  
Computer Based ◽  
Task Oriented

Studies on automatic dialogue systems, which allow people and computers to communicate with each other using natural language, have been attracting attention. In particular, the main objective of a non-task-oriented dialogue system is not to achieve a specific task but to amuse users through chat and free dialogue. For this type of dialogue system, continuity of the dialogue is important because users can easily get tired if the dialogue is monotonous. On the other hand, preceding studies have shown that speech with humorous expressions is effective in improving the continuity of a dialogue. In this study, we developed a computer-based humor discriminator to perform user- or situation-independent objective discrimination of humor. Using the humor discriminator, we also developed an automatic humor generation system and conducted an evaluation experiment with human subjects to test the generated jokes. A t-test on the evaluation scores revealed a significant difference (P value: 3.5×10-5) between the proposed and existing methods of joke generation.

scholarly journals TODO: A Core Ontology for Task-Oriented Dialogue Systems in Industry 4.0

2021 ◽  
Author(s):  
Cristina Aceta ◽  
Izaskun Fernández ◽  
Aitor Soroa
Keyword(s):  
Industry 4.0 ◽  
Use Cases ◽  
Dialogue Systems ◽  
Dialogue System ◽  
Industrial Systems ◽  
Dialogue Management ◽  
Core Ontology ◽  
Dialogue Modelling ◽  
The One ◽  
Task Oriented

Nowadays, the demand in industry of dialogue systems to be able to naturally communicate with industrial systems is increasing, as they allow to enhance productivity and security in these scenarios. However, adapting these systems to different use cases is a costly process, due to the complexity of the scenarios and the lack of available data. This work presents the Task-Oriented Dialogue management Ontology (TODO), which aims to provide a core and complete base for semantic-based task-oriented dialogue systems in the context of industrial scenarios in terms of, on the one hand, domain and dialogue modelling and, on the other hand, dialogue management and tracing support. Furthermore, its modular structure, besides grouping specific knowledge in independent components, allows to easily extend each of the modules, attending the necessities of the different use cases. These characteristics allow an easy adaptation of the ontology to different use cases, with a considerable reduction of time and costs. So as to demonstrate the capabilities of the the ontology by integrating it in a task-oriented dialogue system, TODO has been validated in real-world use cases. Finally, an evaluation is also presented, covering different relevant aspects of the ontology.

scholarly journals More to diverse: Generating diversified responses in a task oriented multimodal dialog system

PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0241271
Author(s):  
Mauajama Firdaus ◽  
Arunav Pratap Shandeelya ◽  
Asif Ekbal
Keyword(s):  
Large Scale ◽  
Contextual Information ◽  
Empirical Evaluation ◽  
Dialogue Systems ◽  
Beam Search ◽  
Dialogue System ◽  
Text And Image ◽  
Dialog System ◽  
Multimodal Dialogue ◽  
Task Oriented

Multimodal dialogue system, due to its many-fold applications, has gained much attention to the researchers and developers in recent times. With the release of large-scale multimodal dialog dataset Saha et al. 2018 on the fashion domain, it has been possible to investigate the dialogue systems having both textual and visual modalities. Response generation is an essential aspect of every dialogue system, and making the responses diverse is an important problem. For any goal-oriented conversational agent, the system’s responses must be informative, diverse and polite, that may lead to better user experiences. In this paper, we propose an end-to-end neural framework for generating varied responses in a multimodal dialogue setup capturing information from both the text and image. Multimodal encoder with co-attention between the text and image is used for focusing on the different modalities to obtain better contextual information. For effective information sharing across the modalities, we combine the information of text and images using the BLOCK fusion technique that helps in learning an improved multimodal representation. We employ stochastic beam search with Gumble Top K-tricks to achieve diversified responses while preserving the content and politeness in the responses. Experimental results show that our proposed approach performs significantly better compared to the existing and baseline methods in terms of distinct metrics, and thereby generates more diverse responses that are informative, interesting and polite without any loss of information. Empirical evaluation also reveals that images, while used along with the text, improve the efficiency of the model in generating diversified responses.

Sign in / Sign up

Export Citation Format

Share Document