Macaw: An Extensible Conversational Information Seeking Platform
Hamed Zamani,Nick Craswell +1 more
- pp 2193-2196
Reads0
Chats0
TLDR
Macaw is an open-source framework with a modular architecture for CIS research that supports multi-turn, multi-modal, and mixed-initiative interactions, and enables research for tasks such as document retrieval, question answering, recommendation, and structured data exploration.Abstract:
Conversational information seeking (CIS) has been recognized as a major emerging research area in information retrieval. Such research will require data and tools, to allow the implementation and study of conversational systems. This paper introduces Macaw, an open-source framework with a modular architecture for CIS research. Macaw supports multi-turn, multi-modal, and mixed-initiative interactions, and enables research for tasks such as document retrieval, question answering, recommendation, and structured data exploration. It has a modular design to encourage the study of new CIS algorithms, which can be evaluated in batch mode. It can also integrate with a user interface, which allows user studies and data collection in an interactive mode, where the back end can be fully algorithmic or a wizard of oz setup. Macaw is distributed under the MIT License.read more
Citations
More filters
Proceedings ArticleDOI
Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search
TL;DR: This paper enrich the representations learned by Transformer networks using a novel attention mechanism from external information sources that weights each term in the conversation to implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection.
Proceedings ArticleDOI
Analyzing and Learning from User Interactions for Search Clarification
Hamed Zamani,Bhaskar Mitra,Everest Chen,Gord Lueck,Fernando Diaz,Paul N. Bennett,Nick Craswell,Susan T. Dumais +7 more
TL;DR: This paper conducts a comprehensive study by analyzing large-scale user interactions with clarifying questions in a major web search engine and proposes a model for learning representation for clarifying Questions based on the user interaction data as implicit feedback.
Proceedings ArticleDOI
Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking
TL;DR: This paper adopt an intra-document cascading strategy, which prunes passages of a candidate document using a less expensive model, called ESM, before running a scoring model that is more expensive and effective, called ETM.
Posted Content
Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search
TL;DR: The authors enrich the representations learned by Transformer networks using a novel attention mechanism from external information sources that weights each term in the conversation and evaluate this Guided Transformer model in a conversational search scenario that includes clarifying questions.
Proceedings ArticleDOI
Wizard of Search Engine: Access to Information Through Conversations with Search Engines
Pengjie Ren,Zhongkun Liu,Xiaomeng Song,Hongtao Tian,Zhumin Chen,Zhaochun Ren,Maarten de Rijke +6 more
TL;DR: Wang et al. as mentioned in this paper formulated a pipeline for conversational information seeking with six subtasks: intent detection, keyphrase extraction, action prediction, query selection, passage selection, and response generation.
References
More filters
Posted Content
Reading Wikipedia to Answer Open-Domain Questions
TL;DR: In this paper, a multi-layer recurrent neural network model was proposed to detect answer spans in Wikipedia paragraphs, which combines a search component based on bigram hashing and TF-IDF matching.
Journal ArticleDOI
CoQA: A Conversational Question Answering Challenge
TL;DR: The CoQA dataset as mentioned in this paper contains 127k questions with answers, obtained from 8k conversations about text passages from seven diverse domains, and the answers are free-form text with their corresponding evidence highlighted in the passage.
Proceedings ArticleDOI
QuAC: Question Answering in Context
Eunsol Choi,He He,Mohit Iyyer,Mohit Iyyer,Mark Yatskar,Wen-tau Yih,Yejin Choi,Yejin Choi,Percy Liang,Luke Zettlemoyer +9 more
TL;DR: QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as it shows in a detailed qualitative evaluation.
Proceedings ArticleDOI
Reading Wikipedia to Answer Open-Domain Questions
TL;DR: This approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs, indicating that both modules are highly competitive with respect to existing counterparts.
Proceedings ArticleDOI
A Theoretical Framework for Conversational Search
Filip Radlinski,Nick Craswell +1 more
TL;DR: This paper studies conversational approaches to information retrieval, presenting a theory and model of information interaction in a chat setting, and shows that while theoretical, the model could be practically implemented to satisfy the desirable properties presented.