Dialogue History Research Articles

Dicer: Dialogue-Centric Representation for Knowledge-Grounded Dialogue through Contrastive Learning

Knowledge-grounded dialogue is a task that utilizes external knowledge to generate appropriate and fluent responses to statements. Owing to the relevance of generating responses based on relevant knowledge in diverse fields, the knowledge selection task has been spotlighted. In this study, we propose a novel selection model that applies contrastive-learning with negative sampling loss to create dialogue-centric representation of knowledge. A two-part loss is considered knowledge selection loss and topic prediction loss. The former increases the similarity between content representations of related knowledge and dialogue history, while the latter increases the similarity between their topic representations. The proposed model was evaluated on two well-known datasets,Wizard of Wikipedia and Holl-E, in terms of the knowledge-grounded dialogue task exhibiting remarkable improvement over previously proposed methods on both knowledge selection and response generation tasks.

تەکنیکى دیالۆگ لە ڕۆمانى (ئاگرى بن کا)ى سەعید ناکامدا

This research is an attempt to analyze the dialogue techniques in the novel (Agri bn Ka) by (Saeed Nakam) and present the importance of these techniques in exposing the characters. This is because dialogue is one of the main and foundational columns and cores of the novel events through which the characters’ roles will be revealed while communicating and addressing one another. Despite this, dialogue represents the thinking method, way of living, educational level, open-mindedness, and maturity of the novel characters. Therefore, the dialogue technique in (Agri bn Ka) novel has been made the title of this research. Further, this research tries to present the novelist’s dominance and power in the dialogues and it is by the characters’ dialogues that (Saeed Nakam) is able to convey his political and social messages. This research is divided into two sections: the first section is theoretical one and deals with the definitions, history, language and significance of dialogue. While the second section is practical and application to the selected novel and analyzes the types and methods of the novel dialogues. Finally, the most important findings and conclusions as well as the consulted sources are provided.

Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema

Task-oriented dialog systems empower users to accom-plish their goals by facilitating intuitive and expres-sive natural language interactions. State-of-the-art ap-proaches in task-oriented dialog systems formulate theproblem as a conditional sequence generation task andfine-tune pre-trained causal language models in the su-pervised setting. This requires labeled training datafor each new domain or task, and acquiring such datais prohibitively laborious and expensive, thus makingit a bottleneck for scaling systems to a wide rangeof domains. To overcome this challenge, we intro-duce a novel Zero-Shot generalizable end-to-end Task-oriented Dialog system, ZS-ToD, that leverages domainschemas to allow for robust generalization to unseen do-mains and exploits effective summarization of the dia-log history. We employ GPT-2 as a backbone model andintroduce a two-step training process where the goal ofthe first step is to learn the general structure of the dialogdata and the second step optimizes the response gen-eration as well as intermediate outputs, such as dialogstate and system actions. As opposed to state-of-the-artsystems that are trained to fulfill certain intents in thegiven domains and memorize task-specific conversa-tional patterns, ZS-ToD learns generic task-completionskills by comprehending domain semantics via domainschemas and generalizing to unseen domains seam-lessly. We conduct an extensive experimental evaluationon SGD and SGD-X datasets that span up to 20 uniquedomains and ZS-ToD outperforms state-of-the-art sys-tems on key metrics, with an improvement of +17% onjoint goal accuracy and +5 on inform. Additionally,we present a detailed ablation study to demonstrate theeffectiveness of the proposed components and trainingmechanism.

Learning Multi-turn Response Selection in Grounded Dialogues with Reinforced Knowledge and Context Distillation

Recently, knowledge-grounded dialogue systems have gained increasing attention. Great efforts have been made to build response matching models where all dialogue content and knowledge sentences are leveraged. However, knowledge redundancy and distraction of irrelevant dialogue content often exist in knowledge-grounded conversations, which may affect the matching process and lead to inferior performance. In addition, irrelevant dialogue history and excessive knowledge also hinder the exploitation of popular pre-trained language models (PLMs) due to the limitation of input length. To address these challenges, we propose a new knowledge-grounded dialogue model based on PLMs, where a knowledge selector and a context selector are designed for filtering out irrelevant knowledge sentences and redundant dialogue history, respectively. Considering the lack of labeled data for the learning of two selectors, we pre-train them with weakly-supervised tasks and then jointly conduct the optimization of knowledge and context selection and fine-tuning of PLMs for response ranking with reinforcement learning (RL). By this means, the dialogue model can distill more accurate and concise knowledge and dialogue content for subsequent response ranking module, and the overall model can converge and perform better. We conduct experiments on two benchmarks and evaluation results indicate that our model can significantly outperform the state-of-the-art methods.

On the Robustness of Dialogue History Representation in Conversational Question Answering: A Comprehensive Study and a New Prompt-based Method

Abstract Most work on modeling the conversation history in Conversational Question Answering (CQA) reports a single main result on a common CQA benchmark. While existing models show impressive results on CQA leaderboards, it remains unclear whether they are robust to shifts in setting (sometimes to more realistic ones), training data size (e.g., from large to small sets) and domain. In this work, we design and conduct the first large-scale robustness study of history modeling approaches for CQA. We find that high benchmark scores do not necessarily translate to strong robustness, and that various methods can perform extremely differently under different settings. Equipped with the insights from our study, we design a novel prompt-based history modeling approach and demonstrate its strong robustness across various settings. Our approach is inspired by existing methods that highlight historic answers in the passage. However, instead of highlighting by modifying the passage token embeddings, we add textual prompts directly in the passage text. Our approach is simple, easy to plug into practically any model, and highly effective, thus we recommend it as a starting point for future model developers. We also hope that our study and insights will raise awareness to the importance of robustness-focused evaluation, in addition to obtaining high leaderboard scores, leading to better CQA systems.1

Multi-Modal Sarcasm Detection and Humor Classification in Code-Mixed Conversations

Sarcasm detection and humor classification are inherently subtle problems, primarily due to their dependence on the contextual and non-verbal information. Furthermore, existing studies in these two topics are usually constrained in non-English languages such as Hindi, due to the unavailability of qualitative annotated datasets. In this work, we make two major contributions considering the above limitations: (1) we develop a Hindi-English code-mixed dataset, MaSaC, for the multi-modal sarcasm detection and humor classification in conversational dialog, which to our knowledge is the first dataset of its kind; (2) we propose MSH-COMICS, a novel attention-rich neural architecture for the utterance classification. We learn efficient utterance representation utilizing a hierarchical attention mechanism that attends to a small portion of the input sentence at a time. Further, we incorporate dialog-level contextual attention mechanism to leverage the dialog history for the multi-modal classification. We perform extensive experiments for both the tasks by varying multi-modal inputs and various submodules of MSH-COMICS. We also conduct comparative analysis against existing approaches. We observe that MSH-COMICS attains superior performance over the existing models by >1 F1-score point for the sarcasm detection and 10 F1-score points in humor classification. We diagnose our model and perform thorough analysis of the results to understand the superiority and pitfalls.

Multi-view semantic understanding for visual dialog

Visual dialog, as a challenging cross-media task, requires answering a sequence of questions based on a given image and dialog history. Hence the key problem becomes how to answer visually grounded questions based on ambiguous reference information from dialog. In this work, we propose a novel method called Multi-View Semantic Understanding for Visual Dialog (MVSU) to resolve the visual coreference resolution problem. The model consists of two main textual processing modules, SRR (Semantic Retention RNN) and CRoT (Coreference Resolution on Text). Specifically, the SRR module generates word features that have semantical meaning by considering contextual information. The CRoT module is from a textual perspective to divide all useful nouns and pronouns into different clusters that serve as the supplement of the detailed information for semantic understanding. In experiments, we demonstrate that MVSU enhances the ability to understand the semantical information on the VisDial v1.0 dataset.

Martin Buber's Dialogical History: Theopolitics as a Critique of the History of Human Power

This essay explores the relationship between Buber's philosophy of history and his political theory, known also as theopolitics. Buber's first book on theopolitics, Kingship of God (1932), implemented the principle of dialogue as a critique of leadership. Dialogue reconciles the paradox of authoritarian theocracy and absolute freedom of anarchy: it unites the interhuman relationship (religious anarchy) and the divine-human relationship (direct theocracy). Without dialogue, anarchy would become chaotic and theocracy would actually mean the tyranny of the priests (hierocracy). But Buber's theopolitics also revealed a particular understanding of history. As this essay demonstrates, Buber held a notion of dialogical history (contrary to Hegelian dialectic history), which ultimately functioned as a critique of the history of victory and power. Dialogical history criticizes not only secular but also any kind of religious or sacred history claiming to authorize human power by divine justification. Dialogical history, therefore, should be seen as "counter-history," not only because it is based on a rehabilitation of myth (Hasidic tales and biblical myths) but also because it is engaged in an alternate philosophy of history, whose fulfillment is vouchsafed neither by the necessary unfolding of a spirit, nor by "great" historical deeds, but by everyday human agency and responsibility alone.

Jacob’s Younger Brother: Christian-Jewish Relations after Vatican II by Karma Ben-Johanan

Reviewed by: Jacob’s Younger Brother: Christian-Jewish Relations after Vatican II by Karma Ben-Johanan Michael Skaggs Jacob’s Younger Brother: Christian-Jewish Relations after Vatican II. By Karma Ben-Johanan. Cambridge, MA: Belknap Press, 2022. 352pp. $35.00. Among the more vivid anecdotes recalled by historians of Catholic-Jewish relations is the 1959 Good Friday liturgy celebrated in St. Peter’s Basilica in Rome, as relayed by Michael Phayer in The Catholic Church and the Holocaust, 1930–1965. When the prescribed prayer for the conversion of “the perfidious Jews” [perfidis Judaeis] was chanted, the pope halted the liturgy. He told the deacon to say the prayer again, without perfidis. Six years later, an ecumenical council proclaimed joyfully—specifically in regard to Jews—that “the Church awaits that day, known to God alone, on which all peoples will address the Lord in a single voice and ‘serve him shoulder to shoulder’” (Nostra Aetate, 4). From one perspective, and as often reported in the secular media, the promulgation of Nostra Aetate heralded the end of Catholic-Jewish enmity. Yet accepting this neat bookend to centuries of antisemitism, argues Karma Ben-Johanan, requires overlooking an intricately nuanced development of thought among both Catholic and Jewish thinkers before the council and since. In Jacob’s Younger Brother, Ben-Johanan explores “the relation to the Other as a key component in the consolidation of religious identities in the second half of the twentieth century” (2). The book is not a narrative history of Christian-Jewish dialogue. Instead, Ben-Johanan focuses closely on internal dialogue within each tradition, about the other. Significantly, Ben-Johanan has not offered an uplifting story of ever-approaching unity: “this book is about the problems of rapprochement and not about its successes” (4). Finally, she restricts her well-argued analysis to the thinking and writing of the intellectual elite of each tradition, acknowledging that what she calls “unresolvable tensions” between the two are “confined to specific realms of writing and thinking, to the doctrinal and halakhic cores of the respective traditions” (8). My own work and that of others has demonstrated the [End Page 83] remarkably fraternal relations that have characterized Catholic-Jewish collaboration on several concrete, societal problems. While the book’s main contribution reveals the deeply problematic relationship between Catholicism and Judaism after Vatican II, which ostensibly put an end to the difficulties between Catholics and Jews, Ben-Johanan necessarily guides the reader through the histories of Catholic and Jewish thought. The book is helpfully divided into two main parts, “Judaism in Catholic Theology” and “Christianity in Orthodox Jewish Thought.” Ben-Johanan brilliantly synthesizes centuries of debate within Catholicism and Judaism while maintaining an ultimate focus on thinkers and leaders closer to our own day, including Popes John Paul II, Benedict XVI, and Francis, as well as leading rabbinical authorities such as David Rosen of the Chief Rabbinate of Israel (sometimes mistakenly perceived as something like a “Jewish Vatican”) and Eugene Korn of the Center for Jewish-Christian Understanding and Cooperation. Ben-Johanan offers a lucid narrative of Catholicism and European Judaism metaphorically switching places: while the Catholic Church’s landmark statement on Jews in Nostra Aetate in 1965 appeared as the church’s influence on state power waned, the founding of the state of Israel in 1948 meant Judaism now held an amount of sovereign authority not seen for millennia. Pretensions to fraternity could be lowered in intra-Jewish (particularly intra-Orthodox) discussions of Christianity. In this way, Ben-Johanan argues, public, Orthodox rejections of Catholic-Jewish dialogue became possible precisely because of modern conceptions of religious liberty that the church itself had come to advance. An extreme example is Zvi Yehudah Kook’s full embrace of the charge of “deicide” that had been leveled at Jews for centuries: rather than ascribing the crucifixion of Jesus to the Romans, Kook cited Maimonides: “If it was a rabbinical court, then it was a rabbinical court! A Jewish court . . . not an instance of the gentiles” (203). Ben-Johanan describes Kook’s writing as a thoroughly modern stance for a Jew to take precisely because it rejects the need to placate a majority Christian society. Perhaps the single notable...

Knowledge grounded medical dialogue generation using augmented graphs

Smart healthcare systems that make use of abundant health data can improve access to healthcare services, reduce medical costs and provide consistently high-quality patient care. Medical dialogue systems that generate medically appropriate and human-like conversations have been developed using various pre-trained language models and a large-scale medical knowledge base based on Unified Medical Language System (UMLS). However, most of the knowledge-grounded dialogue models only use local structure in the observed triples, which suffer from knowledge graph incompleteness and hence cannot incorporate any information from dialogue history while creating entity embeddings. As a result, the performance of such models decreases significantly. To address this problem, we propose a general method to embed the triples in each graph into large-scalable models and thereby generate clinically correct responses based on the conversation history using the recently recently released MedDialog(EN) dataset. Given a set of triples, we first mask the head entities from the triples overlapping with the patient’s utterance and then compute the cross-entropy loss against the triples’ respective tail entities while predicting the masked entity. This process results in a representation of the medical concepts from a graph capable of learning contextual information from dialogues, which ultimately aids in leading to the gold response. We also fine-tune the proposed Masked Entity Dialogue (MED) model on smaller corpora which contain dialogues focusing only on the Covid-19 disease named as the Covid Dataset. In addition, since UMLS and other existing medical graphs lack data-specific medical information, we re-curate and perform plausible augmentation of knowledge graphs using our newly created Medical Entity Prediction (MEP) model. Empirical results on the MedDialog(EN) and Covid Dataset demonstrate that our proposed model outperforms the state-of-the-art methods in terms of both automatic and human evaluation metrics.

FADO: Feedback-Aware Double COntrolling Network for Emotional Support Conversation

Emotional Support Conversation (ESConv) aims to reduce help-seekers’ emotional distress with a supportive strategy and response. It is essential for the supporter to select an appropriate strategy according to the feedback of the help-seeker (e.g., emotion change during dialog turns, etc.) in ESConv. However, previous methods mainly rely on the dialog history to select the strategy and ignore the help-seeker’s feedback, causing wrong and user-irrelevant strategy predictions. Meanwhile, these methods only model the context-to-strategy flow but pay less attention to the strategy-to-context flow involving the strategy-related context for generating strategy-constrained responses. In this paper, a Feedback-Aware Double COntrolling Network (FADO) is proposed to make a strategy schedule and generate supportive responses. The core modules in FADO include a dual-level feedback strategy selector and a double control reader, where the former leverages the turn-level and conversation-level feedback to encourage or penalize strategies, and the latter constructs a novel strategy-to-context flow to generate strategy-constrain responses. Besides, a strategy dictionary is designed to enrich the semantic information of the strategy and improve the quality of the strategy-constrained response. Experimental results on ESConv indicate that the proposed FADO achieves SOTA performance in terms of strategy selection and response generation. Our code is available at https://github.com/Thedatababbler/FADO.

Heterogeneous Knowledge Network for Visual Dialog

Visual dialog requires an agent to answer successive questions considering an image and dialog history, which is a classic vision-language task. Despite progress, there are still two key challenges: 1) parsing long or complex questions and answers and 2) dealing with the visual scene containing complicated interactions among entities. These challenges bring about the unsatisfactory consequence of current visual dialog methods. In this paper, we propose a novel Heterogeneous Knowledge Network (HKNet), which leverages textual sequence knowledge and graph knowledge to address the above issues. Specifically, the textual sequence knowledge is derived from the sentences that are retrieved from the image captions of the visual dialog dataset. The textual sequence knowledge can supplement essential common sense for parsing long or complex questions and answers. The graph knowledge is constructed via scene graph, which provides complete visual relationships for understanding the complicated interactions. These two kinds of heterogeneous knowledge complement each other and jointly improve the logical reasoning ability of the visual dialog. Extensive experimental results on two benchmark datasets: VisDial v0.9 and v1.0 demonstrate the superiority of the proposed HKNet. Ablation studies and visualization results further verify the effectiveness of our method.

A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation

Recently, research on open domain dialogue systems have attracted extensive interests of academic and industrial researchers. The goal of an open domain dialogue system is to imitate humans in conversations. Previous works on single turn conversation generation have greatly promoted the research of open domain dialogue systems. However, understanding multiple single turn conversations is not equal to the understanding of multi turn dialogue due to the coherent and context dependent properties of human dialogue. Therefore, in open domain multi turn dialogue generation, it is essential to modeling the contextual semantics of the dialogue history rather than only according to the last utterance. Previous research had verified the effectiveness of the hierarchical recurrent encoder-decoder framework on open domain multi turn dialogue generation. However, using an RNN-based model to hierarchically encoding the utterances to obtain the representation of dialogue history still face the problem of a vanishing gradient. To address this issue, in this article, we proposed a static and dynamic attention-based approach to model the dialogue history and then generate open domain multi turn dialogue responses. Experimental results on the Ubuntu and Opensubtitles datasets verify the effectiveness of the proposed static and dynamic attention-based approach on automatic and human evaluation metrics in various experimental settings. Meanwhile, we also empirically verify the performance of combining the static and dynamic attentions on open domain multi turn dialogue generation.

Enhanced Multi-Domain Dialogue State Tracker With Second-Order Slot Interactions

Dialogue state tracking (DST) is often used to track the system's understanding of the user goal in task-oriented dialogue systems. Existing DST methods mainly fall into two categories according to their adopted model structure: non-hierarchical and hierarchical models. The former takes the whole dialogue history as inputs during each conversation round, while the latter leverages both an utterance encoder and a dialogue encoder to efficiently model the long-term dialogue dependency. However, few of them exploit the second-order slot interaction, which refers to the pair-wise semantic relationships between different slots. As a result, these methods fall short in the context understanding throughout conversations, leading to sub-optimal performance. Towards this end, in this paper, we present a novel hierarchy-based DST framework equipped with a well-designed value copy mechanism. In particular, to model the second-order slot interaction, we firstly encode the utterance via a state reuse module to yield slot-sensitive context representation. We then selectively and effectively copy the filled values from other slots to attain more accurate state tracking. In order to evaluate the effectiveness of the proposed method, we perform extensive experiments on the widely adopted benchmark dataset MultiWOZ2.1. Our experimental results demonstrate the superiority in context understanding, as well as the strong generalization capability under a zero-shot setting compared with several DST baselines.

The first ever edition of the Quran Latin translation published in 1543 — Milestone in the history of Christian-Muslim dialogue

The article focuses on a Book that formed the basis of knowledge about Islam and the Quran in Europe in the early modern period. It was the first edition of the Latin translation of the Quran, published in Zurich in 1543. It was prepared by the Swiss theologian and orientalist T. Bibliander. T. Bibliander’s edition is notable for being one of the first in Europe for applying a humanistic methodology of philological analysis to the text of the Quran. Moreover, in his study T. Bibliander stepped out of both the paradigm of radical medieval anti-Islamic polemics and the mainstream of new reformist apologetics, and tried to present Islam and Muslims in a humanistic way, trying not to close the way of salvation in the Christian sense to them. T. Bibliander’s edition of the Quran, accompanied by extensive commentaries and a number of works on Islam and Muslims (including prefaces by the leaders of the Reform movement, M. Luther and F. Melanchthon), had a truly encyclopaedic character and marked a significant step towards the creation of a scientific Islamic studies in Europe, thus paving the way for further Christian-Muslim dialogue.

HiBERT: Detecting the illogical patterns with hierarchical BERT for multi-turn dialogue reasoning

Dialogue reasoning is a new task beyond the traditional dialogue system, because it requires recognizing not only semantic relevance but also logical consistency between the candidate response and the dialogue history. Like “all happy families are happy alike, all unhappy families are unhappy in their own way”, various illogical patterns exist in the data. For example, some candidate responses use many similar words but with contradicted meanings with history; while some candidates may employ totally different words but convey consistent meanings. Therefore, an ideal dialogue reasoning model should gather clues from both coarse-grained utterance-level and fine-grained word-level to determine the logical relation between candidates and the dialogue history. However, traditional models mainly rely on the widely used BERT to read all the history and candidates word by word but ignore the utterance-level signals, which cannot well capture various illogical patterns in this task. To tackle this problem, we propose a novel Hierarchical BERT (HiBERT) to recognize both utterance-level and word-level illogical patterns in this paper. Specifically, BERT is firstly utilized to encode the dialogue history and each candidate response as the contextualized representation. Secondly, hierarchical reasoning architecture is conducted with this contextualized representation to obtain the word-level and the utterance-level attention distributions, respectively. In detail, we utilize the word-grained attention mechanism to obtain the word-level representation, and propose two different types of attention function, i.e, hard attention and soft attention, to obtain the utterance-grained representation. Finally, we fuse both the word-grained representation and the utterance-grained representation to calculate the logical ranking scores for the given candidate. Experimental results on two public dialogue datasets show that our model obtains higher ranking measures than the widely used BERT model, validating the effectiveness of hierarchical reading of HiBERT. Further analysis on the impact of context length and attention weights shows that the HiBERT actually has the ability to recognize different illogical patterns.

Capture Salient Historical Information: A Fast and Accurate Non-autoregressive Model for Multi-turn Spoken Language Understanding

Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference facing the impatience of human users. Existing work increases inference speed by designing non-autoregressive models for single-turn SLU tasks but fails to apply to multi-turn SLU in confronting the dialogue history. The intuitive idea is to concatenate all historical utterances and utilize the non-autoregressive models directly. However, this approach seriously misses the salient historical information and suffers from the uncoordinated-slot problems. To overcome those shortcomings, we propose a novel model for multi-turn SLU named Salient History Attention with Layer-Refined Transformer (SHA-LRT), which comprises a SHA module, a Layer-Refined Mechanism (LRM), and a Slot Label Generation (SLG) task. SHA captures salient historical information for the current dialogue from both historical utterances and results via a well-designed history-attention mechanism. LRM predicts preliminary SLU results from Transformer’s middle states and utilizes them to guide the final prediction, and SLG obtains the sequential dependency information for the non-autoregressive encoder. Experiments on public datasets indicate that our model significantly improves multi-turn SLU performance (17.5% on Overall) with accelerating (nearly 15 times) the inference process over the state-of-the-art baseline as well as effective on the single-turn SLU tasks.

When Everyone Wins: Dialogue, Play, and Black History for Critical Games Education

In this article, we reflect on the process and outcomes of using dialogue, play, and a focus on Black women’s history to support critical media literacy in game design education. Over three years we developed a dialogue-based introductory undergraduate course in the game design program at Rensselaer Polytechnic Institute intended to deepen engagement by students in game design practice. We specifically focused on critical approaches to explore the history and culture of games, utilizing dialogic pedagogy to develop transformative learning environments rooted in social justice education, and helped students develop skills for intercultural dialogue and communicating “across difference.” The dialogue experience created a powerful learning environment that resulted in higher quality and more critical student game design work. This was evident in the 2019 iteration of the course, which included two sections of students and in which we had a semester-long group project on the history of Harriet Tubman, culminating in a selection of student games being shown at a local gallery in an exhibition celebrating Tubman’s legacy. The Tubman project was liberatory not only for students, but also instructors, as we learned together how to navigate discomfort and gain a more critical understanding of the material realities of white supremacy in games, self, and each other. This article shares details from the design and methodology of our course, outcomes as evidenced by student work, survey responses, and instructor observations, and concludes with reflections on areas for further research and opportunities for other educators to incorporate new methods in design education.

Adaptation of a robotic dialog system for medication reminder in elderly care

Social robots can assist older adults in their daily life. Verbal conversation is a natural and convenient way for older adults to interact with social robots. However, most of the existing conversation-based robot services, such as medication reminders, are rule-based systems. These systems require many hand-crafted rules and a significant amount of expert knowledge, therefore they cannot adapt to older adults’ characteristics and dialog history. There are many reinforcement learning (RL) based methods for task-oriented dialogues, but they mainly focus on completing the tasks through text-based conversations. Those methods cannot be directly used for elderly care applications involving human–robot interactions (HRI). Considering the above shortcomings, we proposed a dialog system adaptation method (DSAM) for social robots. The DSAM is based on reinforcement learning which considers the characteristics of older adults, the dialog history and user preference to adapt the dialog policy and improve the dialog module. We implemented DSAM in our custom-made ASCCBot social robot. To evaluate DSAM, we firstly tested the dialog agent which was trained by a user simulator with different settings. The results show that the obtained agent achieves a good result with the desired dialog flow compared to the baseline agent. Based on the obtained dialog policy, the adaptation process is evaluated. The results show that with a good success rate, the number of dialog turns is decreased and the NLU module performance is improved by the adaptation process, which proves the effectiveness of DSAM. We also tested DSAM with human subjects. The results show that the average adaptation success rate is 94.7% and the preference distance reaches 0 after 6 rounds of adaptation while creating reminders successfully with a limited amount of user feedback. • A robotic dialog adaptation system for medication reminder in elderly care. • Reinforcement learning based methods for task-oriented dialogues. • Characteristics of older adults, dialog history and user preference considered in adaptation. • User simulator and user modeling combined to adapt the dialog agent.

History and Perspectives of Intercultural Dialog Between Poland and Belarus. Based on Biographies of Prominent Personalities

Abstract The aim of this article is to draw attention to the constant relevance of intercultural dialogue as the way to go beyond stereotypes and ignorance between nations and as a key factor in preventing conflicts and developing intercultural communication skills. A special emphasis is put on the mutual awareness of the historical and cultural heritage and the great input made to it by the outstanding personalities living in the Rzeczpospolita I, the interwar and post-war periods. The text briefly describes the biographies of Kościuszko, Ogiński, Skirmunt and Niemen as characters belonging to two cultures. The literature on the subject was selected in a way to emphasize the intercultural nature of the above-mentioned personalities. The article also names the scientists, writers, political activists who are currently working on maintaining a dialogue between Poland and Belarus. The present state of cultural exchange between the two countries is briefly described in the text, the existing difficulties are defined and the attitudes aimed at preventing the mutual alienation of the two neighboring countries in the next generations are designated. In conclusion it is stated that Polish-Belarusian dialogue, considered from the perspective of mutual cultural heritage, has the potential for further development, under the condition of mutual appreciation of the cultural background of the past and the memories of it preserved by the nations.