TL;DR
This paper demonstrates how Transformer architectures can be effectively used to develop open-domain conversational search assistants that provide context-aware, abstractive answers, achieving state-of-the-art results in key IR tasks.
Contribution
The paper introduces a novel pipeline combining query rewriting, Transformer-based re-ranking, and abstractive answer generation for open-domain conversational search.
Findings
Transformers outperform TREC CAsT 2019 baseline in conversational search tasks.
The proposed pipeline effectively models conversation context for improved search accuracy.
Abstractive Transformer architectures generate concise, relevant answers from top passages.
Abstract
Open-domain conversational search assistants aim at answering user questions about open topics in a conversational manner. In this paper we show how the Transformer architecture achieves state-of-the-art results in key IR tasks, leveraging the creation of conversational assistants that engage in open-domain conversational search with single, yet informative, answers. In particular, we propose an open-domain abstractive conversational search agent pipeline to address two major challenges: first, conversation context-aware search and second, abstractive search-answers generation. To address the first challenge, the conversation context is modeled with a query rewriting method that unfolds the context of the conversation up to a specific moment to search for the correct answers. These answers are then passed to a Transformer-based re-ranker to further improve retrieval performance. The…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsLinear Layer · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Dropout · Softmax · Multi-Head Attention · Dense Connections · Layer Normalization · Residual Connection · Attention Is All You Need
