dialog systems
Recently Published Documents


TOTAL DOCUMENTS

375
(FIVE YEARS 94)

H-INDEX

18
(FIVE YEARS 4)

2022 ◽  
Vol 40 (1) ◽  
pp. 1-33
Author(s):  
Yang Deng ◽  
Yuexiang Xie ◽  
Yaliang Li ◽  
Min Yang ◽  
Wai Lam ◽  
...  

Answer selection, which is involved in many natural language processing applications, such as dialog systems and question answering (QA), is an important yet challenging task in practice, since conventional methods typically suffer from the issues of ignoring diverse real-world background knowledge. In this article, we extensively investigate approaches to enhancing the answer selection model with external knowledge from knowledge graph (KG). First, we present a context-knowledge interaction learning framework, Knowledge-aware Neural Network, which learns the QA sentence representations by considering a tight interaction with the external knowledge from KG and the textual information. Then, we develop two kinds of knowledge-aware attention mechanism to summarize both the context-based and knowledge-based interactions between questions and answers. To handle the diversity and complexity of KG information, we further propose a Contextualized Knowledge-aware Attentive Neural Network, which improves the knowledge representation learning with structure information via a customized Graph Convolutional Network and comprehensively learns context-based and knowledge-based sentence representation via the multi-view knowledge-aware attention mechanism. We evaluate our method on four widely used benchmark QA datasets, including WikiQA, TREC QA, InsuranceQA, and Yahoo QA. Results verify the benefits of incorporating external knowledge from KG and show the robust superiority and extensive applicability of our method.


Knowledge ◽  
2022 ◽  
Vol 2 (1) ◽  
pp. 55-87
Author(s):  
Sargam Yadav ◽  
Abhishek Kaushik

Conversational systems are now applicable to almost every business domain. Evaluation is an important step in the creation of dialog systems so that they may be readily tested and prototyped. There is no universally agreed upon metric for evaluating all dialog systems. Human evaluation, which is not computerized, is now the most effective and complete evaluation approach. Data gathering and analysis are evaluation activities that need human intervention. In this work, we address the many types of dialog systems and the assessment methods that may be used with them. The benefits and drawbacks of each sort of evaluation approach are also explored, which could better help us understand the expectations associated with developing an automated evaluation system. The objective of this study is to investigate conversational agents, their design approaches and evaluation metrics. This approach can help us to better understand the overall process of dialog system development, and future possibilities to enhance user experience. Because human assessment is costly and time consuming, we emphasize the need of having a generally recognized and automated evaluation model for conversational systems, which may significantly minimize the amount of time required for analysis.


2021 ◽  
pp. 1-12
Author(s):  
Manaal Faruqui ◽  
Dilek Hakkani-Tür

Abstract As more users across the world are interacting with dialog agents in their daily life, there is a need for better speech understanding that calls for renewed attention to the dynamics between research in automatic speech recognition (ASR) and natural language understanding (NLU). We briefly review these research areas and lay out the current relationship between them. In light of the observations we make in this paper, we argue that (1) NLU should be cognizant of the presence of ASR models being used upstream in a dialog system’s pipeline, (2) ASR should be able to learn from errors found in NLU, (3) there is a need for end-to-end datasets that provide semantic annotations on spoken input, (4) there should be stronger collaboration between ASR and NLU research communities.


2021 ◽  
Vol 15 (04) ◽  
pp. 419-439
Author(s):  
Nhat Le ◽  
A. B. Siddique ◽  
Fuad Jamour ◽  
Samet Oymak ◽  
Vagelis Hristidis

Most existing commercial goal-oriented chatbots are diagram-based; i.e. they follow a rigid dialog flow to fill the slot values needed to achieve a user’s goal. Diagram-based chatbots are predictable, thus their adoption in commercial settings; however, their lack of flexibility may cause many users to leave the conversation before achieving their goal. On the other hand, state-of-the-art research chatbots use Reinforcement Learning (RL) to generate flexible dialog policies. However, such chatbots can be unpredictable, may violate the intended business constraints, and require large training datasets to produce a mature policy. We propose a framework that achieves a middle ground between the diagram-based and RL-based chatbots: we constrain the space of possible chatbot responses using a novel structure, the chatbot dependency graph, and use RL to dynamically select the best valid responses. Dependency graphs are directed graphs that conveniently express a chatbot’s logic by defining the dependencies among slots: all valid dialog flows are encapsulated in one dependency graph. Our experiments in both single-domain and multi-domain settings show that our framework quickly adapts to user characteristics and achieves up to 23.77% improved success rate compared to a state-of-the-art RL model.


2021 ◽  
Vol 11 (22) ◽  
pp. 10675
Author(s):  
Yinpei Dai ◽  
Yichi Zhang ◽  
Hong Liu ◽  
Zhijian Ou ◽  
Yi Huang ◽  
...  

Slot filling is a crucial component in task-oriented dialog systems that is used to parse (user) utterances into semantic concepts called slots. An ontology is defined by the collection of slots and the values that each slot can take. The most widely used practice of treating slot filling as a sequence labeling task suffers from two main drawbacks. First, the ontology is usually pre-defined and fixed and therefore is not able to detect new labels for unseen slots. Second, the one-hot encoding of slot labels ignores the correlations between slots with similar semantics, which makes it difficult to share knowledge learned across different domains. To address these problems, we propose a new model called elastic conditional random field (eCRF), where each slot is represented by the embedding of its natural language description and modeled by a CRF layer. New slot values can be detected by eCRF whenever a language description is available for the slot. In our experiment, we show that eCRFs outperform existing models in both in-domain and cross-domain tasks, especially in predicting unseen slots and values.


2021 ◽  
Vol 4 (1) ◽  
pp. 16-53
Author(s):  
Stephan Habscheid ◽  
Tim Moritz Hector ◽  
Christine Hrncal ◽  
David Waldecker

The paper presents research results emerging from the analysis of Intelligent Personal Assistants (IPA) log data. Based on the assump­tion that media and data, as part of practice, are produced and used cooperatively, the paper discusses how IPA log data can be used to analyze (1) how the IPA systems operate through their connection to platforms and infrastructures, (2) how the dialog systems are de­signed today and (3) how users integrate them into their everyday social interaction. It also asks in which everyday practical contexts the IPA are placed on the system side and on the user side, and how privacy issues in particular are negotiated. It is argued that, in order to be able to investigate these questions, the technical-institutional and the cultural-theoretical perspective on media, which is common in German media linguistics, has to be complemented by a more fun­damental, i.e. social-theoretical and interactionist perspective.


2021 ◽  
Author(s):  
Frank Röder ◽  
Ozan Özdemir ◽  
Phuong D. H. Nguyen ◽  
Stefan Wermter ◽  
Manfred Eppe

Human language is inherently embodied and grounded in sensorimotor representations of the self and the world around it. This suggests that the body schema and ideomotor action-effect associations play an important role in language understanding, language generation, and verbal/physical interaction with others. There are computational models that focus purely on non-verbal interaction between humans and robots, and there are computational models for dialog systems that focus only on verbal interaction. However, there is a lack of research that integrates these approaches. We hypothesize that the development of computational models of the self is very appropriate for considering joint verbal and physical interaction. Therefore, they provide the substantial potential to foster the psychological and cognitive understanding of language grounding, and they have significant potential to improve human-robot interaction methods and applications. This review is a first step toward developing models of the self that integrate verbal and non-verbal communication. To this end, we first analyze the relevant findings and mechanisms for language grounding in the psychological and cognitive literature on ideomotor theory. Second, we identify the existing computational methods that implement physical decision-making and verbal interaction. As a result, we outline how the current computational methods can be used to create advanced computational interaction models that integrate language grounding with body schemas and self-representations.


2021 ◽  
Vol 12 ◽  
Author(s):  
Frank Röder ◽  
Ozan Özdemir ◽  
Phuong D. H. Nguyen ◽  
Stefan Wermter ◽  
Manfred Eppe

Human language is inherently embodied and grounded in sensorimotor representations of the self and the world around it. This suggests that the body schema and ideomotor action-effect associations play an important role in language understanding, language generation, and verbal/physical interaction with others. There are computational models that focus purely on non-verbal interaction between humans and robots, and there are computational models for dialog systems that focus only on verbal interaction. However, there is a lack of research that integrates these approaches. We hypothesize that the development of computational models of the self is very appropriate for considering joint verbal and physical interaction. Therefore, they provide the substantial potential to foster the psychological and cognitive understanding of language grounding, and they have significant potential to improve human-robot interaction methods and applications. This review is a first step toward developing models of the self that integrate verbal and non-verbal communication. To this end, we first analyze the relevant findings and mechanisms for language grounding in the psychological and cognitive literature on ideomotor theory. Second, we identify the existing computational methods that implement physical decision-making and verbal interaction. As a result, we outline how the current computational methods can be used to create advanced computational interaction models that integrate language grounding with body schemas and self-representations.


Author(s):  
Djallel Bouneffouf ◽  
Raphael Feraud ◽  
Sohini Upadhyay ◽  
Irina Rish ◽  
Yasaman Khazaeni

In various recommender system applications, from medical diagnosis to dialog systems, due to observation costs only a small subset of a potentially large number of context variables can be observed at each iteration; however, the agent has a freedom to choose which variables to observe. In this paper, we analyze and extend an online learning framework known as Context-Attentive Bandit, We derive a novel algorithm, called Context-Attentive Thompson Sampling (CATS), which builds upon the Linear Thompson Sampling approach, adapting it to Context-Attentive Bandit setting. We provide a theoretical regret analysis and an extensive empirical evaluation demonstrating advantages of the proposed approach over several baseline methods on a variety of real-life datasets.


Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1813
Author(s):  
Krzysztof Wołk

We live in a time when dialogue systems are becoming a very popular tool. It is estimated that in 2021 more than 80% of communication with customers on the first line of service will be based on chatbots. They enter not only the retail market but also various other industries, e.g., they are used for medical interviews, information gathering or preliminary assessment and classification of problems. Unfortunately, when these work incorrectly it leads to dissatisfaction. Such systems have the possibility of contacting a human consultant with a special command, but this is not the point. The dialog system should provide a good, uninterrupted and fluid experience and not show that it is an artificial creation. Analysing the sentiment of the entire dialogue in real time can provide a solution to this problem. In our study, we focus on studying the methods of analysing the sentiment of dialogues based on machine learning for the English language and the morphologically complex Polish language, which also represents a language with a small amount of training resources. We analyse the methods directly and use the machine translator as an intermediary, thus checking the quality changes between models based on limited resources and those based on much larger English but machine translated texts. We manage to obtain over 89% accuracy using BERT-based models. We make recommendations in this regard, also taking into account the cost aspect of implementing and maintaining such a system.


Sign in / Sign up

Export Citation Format

Share Document