Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search
By Helia Hashemi, Hamed Zamani, W. Bruce Croft. 2020
72 citations recorded by the source corpus.
Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, especially conversational search systems with limited bandwidth interfaces. Analyzing and generating clarifying questions have been studied recently but the accurate utilization of user responses to clarifying questions has been relatively less explored. In this paper, we enrich the representations learned by Transformer networks using a novel attention mechanism from external information sources that weights each term in the conversation. We evaluate this Guided Transformer model in a conversational search scenario that includes clarifying questions. In our experiments, we use two separate external sources, including the top retrieved documents and a set of different possible clarifying questions for the query. We implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection. Our experiments use a public dataset for search clarification and demonstrate significant improvements compared to competitive baselines.
Subfields: Information Retrieval & Search, Natural Language Processing, Multimodal Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Information Retrieval & Search
- Hamed Zamani
- Nick Craswell
- Fernando Diaz
- Michael Bendersky
- Mostafa Dehghani
- Donald Metzler
- Bhaskar Mitra
- Jimmy J. Lin
In Natural Language Processing
- Hamed Zamani
- Nick Craswell
- Mostafa Dehghani
- Donald Metzler
- Fernando Diaz
- Michael Bendersky
- Simon Osindero
- Jack W. Rae
In Multimodal Learning
- Simon Osindero
- Oriol Vinyals
- Karen Simonyan
- Marcus Rohrbach
- Ruslan Salakhutdinov
- Devi Parikh
- Jianfeng Gao
- Qi Wu
Citations in the corpus
- Improving language models by retrieving from trillions of tokens (2021, methodology): “This involves collecting a dataset of human dialogues with associated search queries, which limits the scalability of this approach.”
- MIMICS: A Large-Scale Data Collection for Search Clarification (2020, methodology): “Selecting clarification has been previously studied in [1, 13, 30].”
- Retrieval-Enhanced Machine Learning (2022, background): “Access to external knowledge, via knowledge grounding , may help with this issue [11, 22, 34, 39, 76].”