A personal agents hybrid architecture for question answering featuring social dialog

Coronado, Miguel López; Iglesias, Carlos Á.; Mardomingo, Alberto

doi:10.1109/inista.2015.7276780

Cited by 3 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One approach is a hierarchical architecture composed of several agents. They use a classifier to select the right agent for each utterance (Coronado et al, 2015;Banchs et al, 2013;Planells et al, 2013;Pichl et al, 2018) or a ranking approach that generates answers by each DS and then selects the best answer Tanaka et al, 2019;Paranjape et al, 2020). Other approaches use a joint architecture to solve multiple dialog tasks Shuster et al, 2020).…”

Section: Hybrid Dialog Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)

2021

View full text Add to dashboard Cite

We present the results of Shared Task at Workshop DialDoc 2021 that is focused on document-grounded dialogue and conversational question answering. The primary goal of this Shared Task is to build goal-oriented information-seeking conversation systems that can identify the most relevant knowledge in the associated document for generating agent responses in natural language. It includes two subtasks on predicting agent responses: the first subtask is to predict the grounding text span in the given document for next agent response; the second subtask is to generate agent response in natural language given the context. Many submissions outperform baseline significantly. For the first task, the best-performing system achieved 67.1 Exact Match and 76.3 F1. For the second subtask, the best system achieved 41.1 SacreBLEU and highest rank by human evaluation.

show abstract

Section: Hybrid Dialog Systemsmentioning

confidence: 99%

“…Question answering has been augmented with TODS before (Banchs et al, 2013;D'Haro et al, 2015;Coronado et al, 2015;Podgorny et al, 2019). In this work, we apply the MDS framework to the combination of an ODQA system and a TODS.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 1st Workshop on Document-grounded Dialogue and Conversational Question Answering (DialDoc 2021)

2021

View full text Add to dashboard Cite

show abstract

“…One approach is a hierarchical architecture composed of several agents. They use a classifier to select the right agent for each utterance (Coronado et al, 2015;Banchs et al, 2013;Planells et al, 2013;Pichl et al, 2018) or a ranking approach that generates answers by each DS and then selects the best answer (Song et al, 2018;Tanaka et al, 2019;Paranjape et al, 2020). Other approaches use a joint architecture to solve multiple dialog tasks (Lewis et al, 2020;Shuster et al, 2020).…”

Section: Hybrid Dialog Systemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Combining Open Domain Question Answering with a Task-Oriented Dialog System

Nehring¹,

Feldhus²,

Kaur³

et al. 2021

Proceedings of the 1st Workshop on Document-Grounded Dialogue and Conversational Question Answering (DialDoc 2021)

View full text Add to dashboard Cite

We apply the modular dialog system framework to combine open-domain question answering with a task-oriented dialog system. This meta dialog system can answer questions from Wikipedia and at the same time act as a personal assistant. The aim of this system is to combine the strength of an open-domain question answering system with the conversational power of task-oriented dialog systems. After explaining the technical details of the system, we combined a new dataset out of standard datasets to evaluate the system. We further introduce an evaluation method for this system. Using this method, we compare the performance of the non-modular system with the performance of the modular system and show that the modular dialog system framework is very suitable for this combination of conversational agents and that the performance of each agent decreases only marginally through the modular setting.

show abstract