Personal assistant systems, such as Apple Siri, Google Now, Amazon Alexa, and Microsoft Cortana, are becoming ever more widely used. Understanding user intent such as clarification questions, potential answers and user feedback in information-seeking conversations is critical for retrieving good responses. In this paper, we analyze user intent patterns in information-seeking conversations and propose an intent-aware neural response ranking model ``IART'', which refers to ``Intent-Aware Ranking with Transformers''. IART is built on top of the integration of user intent modeling and language representation learning with the Transformer architecture, which relies entirely on a self-attention mechanism instead of recurrent nets. It incorporates intent-aware utterance attention to derive an importance weighting scheme of utterances in conversation context with the aim of better conversation history understanding. We conduct extensive experiments with three information-seeking conversation data sets including both standard benchmarks and commercial data. Our proposed model outperforms all baseline methods with respect to a variety of metrics. We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results. Our research findings provide insights on intent-aware neural ranking models based on Transformers for response selection, and have implications for the design of the next generation of information-seeking conversation systems.
more »
« less
This content will become publicly available on May 18, 2024
InSCIt : Information-Seeking Conversations with Mixed-Initiative Interactions
Abstract In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most current studies either fail to or artificially incorporate such agent-side initiative. This work presents InSCIt, a dataset for Information-Seeking Conversations with mixed-initiative Interactions. It contains 4.7K user-agent turns from 805 human-human conversations where the agent searches over Wikipedia and either directly answers, asks for clarification, or provides relevant information to address user queries. The data supports two subtasks, evidence passage identification and response generation, as well as a human evaluation protocol to assess model performance. We report results of two systems based on state-of-the-art models of conversational knowledge identification and open-domain question answering. Both systems significantly underperform humans, suggesting ample room for improvement in future studies.1
more »
« less
- Award ID(s):
- 2044660
- NSF-PAR ID:
- 10462304
- Date Published:
- Journal Name:
- Transactions of the Association for Computational Linguistics
- Volume:
- 11
- ISSN:
- 2307-387X
- Page Range / eLocation ID:
- 453 to 468
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Many AI system designers grapple with how best to collect human input for different types of training data. Online crowds provide a cheap on-demand source of intelligence, but they often lack the expertise required in many domains. Experts offer tacit knowledge and more nuanced input, but they are harder to recruit. To explore this trade off, we compared novices and experts in terms of performance and perceptions on human intelligence tasks in the context of designing a text-based conversational agent. We developed a preliminary chatbot that simulates conversations with someone seeking mental health advice to help educate volunteer listeners at 7cups.com. We then recruited experienced listeners (domain experts) and MTurk novice workers (crowd workers) to conduct tasks to improve the chatbot with different levels of complexity. Novice crowds perform comparably to experts on tasks that only require natural language understanding, such as correcting how the system classifies a user statement. For more generative tasks, like creating new lines of chatbot dialogue, the experts demonstrated higher quality, novelty, and emotion. We also uncovered a motivational gap: crowd workers enjoyed the interactive tasks, while experts found the work to be tedious and repetitive. We offer design considerations for allocating crowd workers and experts on input tasks for AI systems, and for better motivating experts to participate in low-level data work for AI.more » « less
-
As social robots become increasingly prevalent in day-to-day environments, they will participate in conversations and appropriately manage the information shared with them. However, little is known about how robots might appropriately discern the sensitivity of information, which has major implications for human-robot trust. As a first step to address a part of this issue, we designed a privacy controller, CONFIDANT, for conversational social robots, capable of using contextual metadata (e.g., sentiment, relationships, topic) from conversations to model privacy boundaries. Afterwards, we conducted two crowdsourced user studies. The first study (n = 174) focused on whether a variety of human-human interaction scenarios were perceived as either private/sensitive or non-private/non-sensitive. The findings from our first study were used to generate association rules. Our second study (n = 95) evaluated the effectiveness and accuracy of the privacy controller in human-robot interaction scenarios by comparing a robot that used our privacy controller against a baseline robot with no privacy controls. Our results demonstrate that the robot with the privacy controller outperforms the robot without the privacy controller in privacy-awareness, trustworthiness, and social-awareness. We conclude that the integration of privacy controllers in authentic human-robot conversations can allow for more trustworthy robots. This initial privacy controller will serve as a foundation for more complex solutions.more » « less
-
A major challenge in designing conversational agents is to handle unknown concepts in user utterances. This is particularly difficult for general-purpose task-oriented agents, as the unknown concepts and the tasks can be outside of the agent’s existing domain of knowledge. In this work, we propose a new multi-modal mixed-initiative approach towards this problem. Our agent Pumice guides the user to recursively explain unknown concepts through conversations, and to ground these concepts by demonstrating on the graphical user interfaces (GUIs) of existing third-party mobile apps. Pumice also supports the generalization of learned concepts to other different contexts and task domains.more » « less
-
Understanding and characterizing how people interact in information-seeking conversations will be a crucial component in developing effective conversational search systems. In this paper, we introduce a new dataset designed for this purpose and use it to analyze information-seeking conversations by user intent distribution, co-occurrence, and flow patterns. The MSDialog dataset is a labeled conversation dataset of question answering (QA) interactions between information seekers and providers from an online forum on Microsoft products. The dataset contains more than 2,000 multi-turn QA dialogs with 10,000 utterances that are annotated with user intents on the utterance level. Annotations were done using crowdsourcing. With MSDialog, we find some highly recurring patterns in user intent during an information-seeking process. They could be useful for designing conversational search systems. We will make our dataset freely available to encourage exploration of information-seeking conversation models.more » « less
