Information Seeking in the Spirit of Learning: A Dataset for Conversational Curiosity

Rodríguez, Pedro; Crook, Paul A.; Moon, Seungwhan

doi:10.18653/v1/2020.emnlp-main.655

Cited by 6 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For both training and pretraining we use four different datasets: Curiosity (Rodriguez et al 2020) is a collection of conversations on a specific topic with separate knowledge (memory) from which they are based. Dialogue-based REAding comprehension exaMination (DREAM) (Sun et al 2019) is a dataset that is aimed at text comprehension, we adopt the text as our memory and the question as input to the system.…”

Section: Datasetsmentioning

confidence: 99%

Memory-Augmenting Decoder-Only Language Models through Encoders (Student Abstract)

Galatolo,

Winkle

2024

AAAI

View full text Add to dashboard Cite

The Transformer architecture has seen a lot of attention in recent years also thanks to its ability to scale well and allow massive parallelism during training. This has made possible the development of Language Models (LMs) of increasing size and the discovery of latent abilities that completely outclass traditional methods e.g. rule-based systems. However, they also introduced new issues, like their inability to retain the history of previous interactions due to their stateless nature or the difficulty in controlling their generation. Different attempts have been made to address these issues, e.g. a `brute force' approach to solving the memory issue is to include the full conversation history in the context window, a solution that is limited by the quadratic scalability of Transformers. In this work, we explore computationally practical solutions to the memory problem. We propose to augment the decoder-only architecture of (most) Large LMs with a (relatively small) memory encoder. Its output is prepended to the decoder's input in a similar fashion to recent works in Adapters and the original Transformer architecture. Initial experiments show promising results, however future work is needed to compare with State-of-the-Art methods.

show abstract

Section: Datasetsmentioning

confidence: 99%

Memory-Augmenting Decoder-Only Language Models through Encoders (Student Abstract)

Galatolo,

Winkle

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Knowledge-grounded social chat systems (Ghazvininejad et al, 2018;Dinan et al, 2019;Zhou et al, 2018;Moghe et al, 2018) incorporate external knowledge with the purpose of making the conversations more engaging and informative. Rodriguez et al (2020) collect a dataset for training a conversational agent to select knowledge to present based on the user's background, with the aim to maintain the user's interest in the conversation.…”

Section: Related Workmentioning

confidence: 99%

INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions

Wu¹,

Cheng²,

Min³

et al. 2022

Preprint

View full text Add to dashboard Cite

In an information-seeking conversation, a user converses with an agent to ask a series of questions that can often be under-or over-specified. An ideal agent would first identify that they were in such a situation by searching through their underlying knowledge source and then appropriately interacting with a user to resolve it. However, most existing studies either fail to or artificially incorporate such agent-side initiatives. In this work, we present INSCIT (pronounced Insight), a dataset for Information-Seeking Conversations with mixed-initiative Interactions. It contains a total of 4.7K useragent turns from 805 human-human conversations where the agent searches over Wikipedia and either asks for clarification or provides relevant information to address user queries. We define two subtasks, namely evidence passage identification and response generation, as well as a new human evaluation protocol to assess the model performance. We report results of two strong baselines based on state-of-theart models of conversational knowledge identification and open-domain question answering. Both models significantly underperform humans and fail to generate coherent and informative responses, suggesting ample room for improvement in future studies. 1

show abstract

“…The datasets to train models in CIS are designed to facilitate a mixedinitiative dialogue, where the agent can also ask clarifying or follow-up questions to gather information concerning the IS query (Zhang and Bansal 2019). Alongside, datasets like ShARC help CIS models to improve response generation (Saeidi et al 2018). However, in this study, we restrict ourselves to solving an open sub-problem in CIS that generates ISQs.…”

Section: Related Workmentioning

confidence: 99%

“…Both QAD and QAMR consist of D only IS queries. Facebook Curiosity (FBC) (Rodriguez et al 2020) is another dataset that challenges ISEEQ to have both semantic relations and logical coherence. This is because queries are described in the form of Tp & Asp.…”

Section: Datasetsmentioning

confidence: 99%

ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphs

Gunaratna¹,

Srinivasan²,

Jin³

2021

Preprint

View full text Add to dashboard Cite

Conversational Information Seeking (CIS) is a relatively new research area within conversational AI that attempts to seek information from end-users in order to understand and satisfy users' needs. If realized, such a system has far-reaching benefits in the real world; for example, a CIS system can assist clinicians in pre-screening or triaging patients in healthcare. A key open sub-problem in CIS that remains unaddressed in the literature is generating Information Seeking Questions (ISQs) based on a short initial query from the enduser. To address this open problem, we propose Information SEEking Question generator (ISEEQ), a novel approach for generating ISQs from just a short user query, given a large text corpus relevant to the user query. Firstly, ISEEQ uses a knowledge graph to enrich the user query. Secondly, ISEEQ uses the knowledge-enriched query to retrieve relevant context passages to ask coherent ISQs adhering to a conceptual flow. Thirdly, ISEEQ introduces a new deep generativeadversarial reinforcement learning-based approach for generating ISQs. We show that ISEEQ can generate high-quality ISQs to promote the development of CIS agents. ISEEQ significantly outperforms comparable baselines on five ISQ evaluation metrics across four datasets having user queries from diverse domains. Further, we argue that ISEEQ is transferable across domains for generating ISQs, as it shows the acceptable performance when trained and tested on different pairs of domains. The qualitative human evaluation confirms ISEEQ-generated ISQs are comparable in quality to human-generated questions and outperform the best comparable baseline.

show abstract

Information Seeking in the Spirit of Learning: A Dataset for Conversational Curiosity

Cited by 6 publications

References 41 publications

Memory-Augmenting Decoder-Only Language Models through Encoders (Student Abstract)

Memory-Augmenting Decoder-Only Language Models through Encoders (Student Abstract)

INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions

ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphs

Contact Info

Product

Resources

About