Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems
كازينو: جوربوس من حوارات التفاوض في المخيم لأنظمة التفاوض التلقائي
250
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
الأنظمة الآلية التي تتفاوض مع البشر لديها تطبيقات واسعة في علم التربية والاتحاد الدولي للتنصيص. لتعزيز تطوير أنظمة التفاوض العملية، نقدم كازينو: جثة رواية تزيد عن ألف حوارات مفاوضات باللغة الإنجليزية. يأخذ المشاركون دور جيران المخيمات والتفاوض على حزم الأغذية والمياه والحطب لرحلتهم القادمة. ينتج عن تصميمنا مفاوضات غنية متنوعة ومتناهية اللغوية مع الحفاظ على بيئة مجال مغلقة. مستوحاة من الأدبيات في المفاوضات البشرية البشرية، نعلن استراتيجيات الإقناع وأداء تحليل الارتباط لفهم كيفية ارتباط سلوكيات الحوار بأداء التفاوض. ونحن نقترح وتقييم إطار عمل متعدد المهام للتعرف على هذه الاستراتيجيات في كلام معطى. نجد أن التعلم متعدد المهام يحسن بشكل كبير الأداء لجميع ملصقات الاستراتيجية، خاصة بالنسبة للذين هم الأكثر انحاءا. نطلق سراح البيانات والشروح والعهد لدفع العمل المستقبلي في مفاوضات الجهاز البشري: https://github.com/kushalchawla/casino
Automated systems that negotiate with humans have broad applications in pedagogy and conversational AI. To advance the development of practical negotiation systems, we present CaSiNo: a novel corpus of over a thousand negotiation dialogues in English. Participants take the role of campsite neighbors and negotiate for food, water, and firewood packages for their upcoming trip. Our design results in diverse and linguistically rich negotiations while maintaining a tractable, closed-domain environment. Inspired by the literature in human-human negotiations, we annotate persuasion strategies and perform correlation analysis to understand how the dialogue behaviors are associated with the negotiation performance. We further propose and evaluate a multi-task framework to recognize these strategies in a given utterance. We find that multi-task learning substantially improves the performance for all strategy labels, especially for the ones that are the most skewed. We release the dataset, annotations, and the code to propel future work in human-machine negotiations: https://github.com/kushalchawla/CaSiNo
References used
https://aclanthology.org/
rate research
Read More
Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is usually not affo
rdable for large-scale experiments. Though researchers have attempted to use metrics for language generation tasks (e.g., perplexity, BLEU) or some model-based reinforcement learning methods (e.g., self-play evaluation) for automatic evaluation, these methods only show very weak correlation with the actual human evaluation in practice. To bridge such a gap, we propose a new framework named ENIGMA for estimating human evaluation scores based on recent advances of off-policy evaluation in reinforcement learning. ENIGMA only requires a handful of pre-collected experience data, and therefore does not involve human interaction with the target policy during the evaluation, making automatic evaluations feasible. More importantly, ENIGMA is model-free and agnostic to the behavior policies for collecting the experience data, which significantly alleviates the technical difficulties of modeling complex dialogue environments and human behaviors. Our experiments show that ENIGMA significantly outperforms existing methods in terms of correlation with human evaluation scores.
The acquisition of a dialogue corpus is a key step in the process of training a dialogue model. In this context, corpora acquisitions have been designed either for open-domain information retrieval or slot-filling (e.g. restaurant booking) tasks. How
ever, there has been scarce research in the problem of collecting personal conversations with users over a long period of time. In this paper we focus on the types of dialogues that are required for mental health applications. One of these types is the follow-up dialogue that a psychotherapist would initiate in reviewing the progress of a Cognitive Behavioral Therapy (CBT) intervention. The elicitation of the dialogues is achieved through textual stimuli presented to dialogue writers. We propose an automatic algorithm that generates textual stimuli from personal narratives collected during psychotherapy interventions. The automatically generated stimuli are presented as a seed to dialogue writers following principled guidelines. We analyze the linguistic quality of the collected corpus and compare the performances of psychotherapists and non-expert dialogue writers. Moreover, we report the human evaluation of a corpus-based response-selection model.
The Israel government led by Rabin reached an advanced stage in peace negotiations with Syria, but his assassination in 1995 prevented the completion of the peace process. The Likud returned to power, making the extremist Netanyahu as a prime ministe
r, who insisted on returning to the zero point in the negotiations with Syria. But with Barak's Labor government in power, negotiations resumed again from the point where they stopped in 1996, but the dispute between Syria and Israel for a few meters prevented negotiations from succeeding. When Sharon became Israeli prime minister and America evaded its role in pursuing negotiations, the peace process was halted again by the beginning of the century. Things continued as they were until 2007. when Kadima leader Olmert asked Turkey to resume indirect negotiations with Syria, rather, despite Ankara's embrace of the negotiations, the situation worsened after the renewal of Netanyahu's election in 2009 as a prime minister.
We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as machine reading comprehension task based on a single given document
or passage. In this work, we aim to address more realistic scenarios where a goal-oriented information-seeking conversation involves multiple topics, and hence is grounded on different documents. To facilitate such task, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains. We also explore modeling the dialogue-based and document-based contexts in the dataset. We present strong baseline approaches and various experimental results, aiming to support further research efforts on such a task.
Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and CommonsenseQA) mainly focus on the discriminative task of choosing the right an
swer from a set of candidates, and do not involve interactive language generation as in dialogue. Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet. In this paper, we present an empirical study of commonsense in dialogue response generation. We first auto-extract commonsensical dialogues from existing dialogue datasets by leveraging ConceptNet, a commonsense knowledge graph. Furthermore, building on social contexts/situations in SocialIQA, we collect a new dialogue dataset with 25K dialogues aimed at exhibiting social commonsense in an interactive setting. We evaluate response generation models trained using these datasets and find that models trained on both extracted and our collected data produce responses that consistently exhibit more commonsense than baselines. Finally we propose an approach for automatic evaluation of commonsense that relies on features derived from ConceptNet and pre-trained language and dialog models, and show reasonable correlation with human evaluation of responses' commonsense quality.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
