2020

Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting

Lin, Sheng-Chieh, Yang, Jheng-Hong, Nogueira, Rodrigo et al.

Understand

Conversational search plays a vital role in conversational information seeking.

As queries in information seeking dialogues are ambiguous for traditional ad-hoc information retrieval (IR) systems due to the coreference and omission resolution problems inherent in natural language dialogue, resolving these ambiguities is crucial.
In this paper, we tackle conversational passage retrieval (ConvPR), an important component of conversational search, by addressing query ambiguities with query reformulation integrated into a multi-stage ad-hoc IR system.
Specifically, we propose two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting.

Built on

Few-Shot Generative Conversational Query Rewriting. In Proc. SIGIR . 1933–1936
Shi Yu, Jiahua Liu, Jingqin Yang, Chenyan Xiong, Paul Bennett, Jianfeng Gao, and Zhiyuan Liu. 2020 · 1936
Earlier work this paper cites.
A Performance Evaluation of Similarity Measures, Document Term Weighting Schemes and Representations in a Boolean Environment. In Proc. SIGIR . 57–76
Terry Noreault, Michael McGill, and Matthew B. Koll. 1980 · 1980
Earlier work this paper cites.
The Effect of Multiple Query Representations on Information Retrieval System Performance. In Proc. SIGIR . 339–346
Nicholas J. Belkin, C. Cool, W. Bruce Croft, and James P. Callan. 1993 · 1993
Earlier work this paper cites.
Okapi at TREC-3. In Proc. TREC
Stephen E. Robertson, Steve Walker, Susan Jones, Micheline Hancock-Beaulieu, and Mike Gatford. 1994 · 1994
Earlier work this paper cites.
Query Expansion Using Local and Global Document Analysis. In Proc. SIGIR . 4–11
J. Xu and W. B. Croft. 1996 · 1996
Earlier work this paper cites.
Relevance Based Language Models. In Proc. SIGIR . 120–127
Victor Lavrenko and W. Bruce Croft. 2001 · 2001
Earlier work this paper cites.
Predicting Query Performance. In Proc. SIGIR . 299–306
Stephen Cronen-Townsend, Yun Zhou, and W. Bruce Croft. 2002 · 2002
Earlier work this paper cites.
Robust, Web and Terabyte Retrieval with Hummingbird SearchServer at TREC 2004. In Proc. TREC
Stephen Tomlinson. 2004 · 2004
Earlier work this paper cites.
Overview of the TREC 2004 Robust Retrieval Track
Ellen M Voorhees. 2004 · 2004
Earlier work this paper cites.
Query Performance Prediction in Web Search Environments. In Proc. SIGIR . 543–550
Yun Zhou and W. Bruce Croft. 2007 · 2007
Earlier work this paper cites.
Visualizing Data using t-SNE
Laurens van der Maaten and Geoffrey Hinton. 2008 · 2008
Earlier work this paper cites.
Reciprocal Rank Fusion Outperforms Condorcet and Individual Rank Learning Methods. In Proc. SIGIR . 758–759
Gordon V. Cormack, Charles L. A. Clarke, and Stefan Buettcher. 2009 · 2009
Earlier work this paper cites.
A Comparative Study of Methods for Estimating Query Language Models with Pseudo Feedback. In Proc. CIKM
Yuanhua Lv and ChengXiang Zhai. 2009 · 2009
Earlier work this paper cites.
A Survey on Transfer Learning
Sinno Jialin Pan and Qiang Yang. 2010 · 2010
Earlier work this paper cites.
Predicting Query Performance by Query-Drift Estimation
Anna Shtok, Oren Kurland, David Carmel, Fiana Raiber, and Gad Markovits. 2012 · 2012
Earlier work this paper cites.
Document Vector Representations for Feature Extraction in Multi-Stage Document Ranking
Nima Asadi and Jimmy Lin. 2013a · 2013
Earlier work this paper cites.
Efficient and Effective Retrieval Using Selective Pruning. In Proc. WSDM . 63–72
Nicola Tonellotto, Craig Macdonald, and Iadh Ounis. 2013 · 2013
Earlier work this paper cites.
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In Proc. EMNLP . 1724–1734
Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014 · 2014
Earlier work this paper cites.
Sequence to Sequence Learning with Neural Networks. In Proc. NIPS . 3104–3112
Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014 · 2014
Earlier work this paper cites.
A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion. In Proc. CIKM . 553–562
Alessandro Sordoni, Yoshua Bengio, Hossein Vahabi, Christina Lioma, Jakob Grue Simonsen, and Jian-Yun Nie. 2015 · 2015
Earlier work this paper cites.
The Query Change Model: Modeling Session Search as a Markov Decision Process
Hui Yang, Dongyi Guan, and Sicong Zhang. 2015 · 2015
Earlier work this paper cites.
MS MARCO: A human generated MAchine Reading COmprehension dataset
Original
Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, et al · 2016
Earlier work this paper cites.
Assessing Efficiency–Effectiveness Tradeoffs in Multi-Stage Retrieval Systems Without Using Relevance Judgments
Charles L. A. Clarke, J. Shane Culpepper, and Alistair Moffat. 2016 · 2016
Earlier work this paper cites.
Dynamic Cutoff Prediction in Multi-Stage Retrieval Systems. In Proc. ADCS . 17–24
J. Shane Culpepper, Charles L. A. Clarke, and Jimmy Lin. 2016 · 2016
Earlier work this paper cites.

Similar

Incomplete Follow-up Question Resolution Using Retrieval Based Sequence to Sequence Learning. In Proc. SIGIR . 705–714
Vineet Kumar and Sachindra Joshi. 2017 · 2017
Cited alongside, same era.
An Extended Relevance Model for Session Search. In Proc. SIGIR . 865–868
Nir Levine, Haggai Roitman, and Doron Cohen. 2017 · 2017
Cited alongside, same era.
Task-Oriented Query Reformulation with Reinforcement Learning. In Proc. EMNLP . 574–583
Rodrigo Nogueira and Kyunghyun Cho. 2017 · 2017
Cited alongside, same era.
A Theoretical Framework for Conversational Search. In Proc. CHIIR . 117–126
Filip Radlinski and Nick Craswell. 2017 · 2017
Cited alongside, same era.
Nematus: a Toolkit for Neural Machine Translation. In Proc. EACL: Software Demonstrations . 65–68
Rico Sennrich, Orhan Firat, Kyunghyun Cho, Alexandra Birch, Barry Haddow, Julian Hitschler, Marcin Junczys-Dowmunt, Samuel Läubli, Antonio Valerio Miceli Barone, Jozef Mokry, and Maria Nădejde. 2017 · 2017
Cited alongside, same era.
An Exploration of Approaches to Integrating Neural Reranking Models in Multi-Stage Ranking Architectures
Original
Zhucheng Tu, Matt Crane, Royal Sequiera, Junchen Zhang, and Jimmy Lin. 2017 · 2017
Cited alongside, same era.
Attention Is All You Need
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017 · 2017
Cited alongside, same era.
Multi-Task Learning for Document Ranking and Query Suggestion. In Proc. ICLR
Wasi Uddin Ahmad, Kai-Wei Chang, and Hongning Wang. 2018 · 2018
Cited alongside, same era.
QuAC: Question Answering in Context
Original
Eunsol Choi, He He, Mohit Iyyer, Mark Yatskar, Wen-tau Yih, Yejin Choi, Percy Liang, and Luke Zettlemoyer. 2018 · 2018
Cited alongside, same era.
Research Frontiers in Information Retrieval: Report from the Third Strategic Workshop on Information Retrieval in Lorne
J. Shane Culpepper, Fernando Diaz, and Mark D. Smucker. 2018 · 2018
Cited alongside, same era.
TREC Complex Answer Retrieval Overview
Laura Dietz and Nick Craswell. 2018 · 2018
Cited alongside, same era.
Dynamic Shard Cutoff Prediction for Selective Search. In Proc. SIGIR . 85–94
Hafeezul Rahman Mohammad, Keyang Xu, Jamie Callan, and J. Shane Culpepper. 2018 · 2018
Cited alongside, same era.

Then

Deeper Text Understanding for IR with Contextual Neural Language Modeling. In Proc. SIGIR . 985–988
Zhuyun Dai and Jamie Callan. 2019 · 2019
Later among the works it cites.
CAsT 2019: The Conversational Assistance Track Overview. In Proc. TREC
Jeffrey Dalton, Chenyan Xiong, and Jamie Callan. 2019 · 2019
Later among the works it cites.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. NAACL . 4171–4186
Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019 · 2019
Later among the works it cites.
Unified Language Model Pre-training for Natural Language Understanding and Generation. In Proc. NIPS
Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, and Hsiao-Wuen Hon. 2019 · 2019
Later among the works it cites.
Can You Unpack That? Learning to Rewrite Questions-in-Context. In Proc. EMNLP . 5917–5923
Ahmed Elgohary, Denis Peskov, and Jordan Boyd-Graber. 2019 · 2019
Later among the works it cites.
Joint Optimization of Cascade Ranking Models. In Proc. WSDM . 15–23
Luke Gallagher, Ruey-Cheng Chen, Roi Blanco, and J. Shane Culpepper. 2019 · 2019
Later among the works it cites.
Using Pre-Training Can Improve Model Robustness and Uncertainty. In Proc. ICML , Vol. 97. 2712–2721
Dan Hendrycks, Kimin Lee, and Mantas Mazeika. 2019 · 2019
Later among the works it cites.
Natural Questions: a Benchmark for Question Answering Research
Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Matthew Kelcey, Jacob Devlin, Kenton Lee, Kristina N. Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019 · 2019
Later among the works it cites.
Passage Re-ranking with BERT
Original
Rodrigo Nogueira and Kyunghyun Cho. 2019 · 2019
Later among the works it cites.
From doc2query to docTTTTTquery
Rodrigo Nogueira and Jimmy Lin. 2019 · 2019
Later among the works it cites.
Multi-stage Document Ranking with BERT
Original
Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019 · 2019
Later among the works it cites.
Introducing MANtIS: a novel Multi-Domain Information Seeking Dialogues Dataset
Original
Gustavo Penha, Alexandru Balan, and Claudia Hauff. 2019 · 2019
Later among the works it cites.
Normalized Query Commitment Revisited. In Proc. SIGIR . 1085–1088
Haggai Roitman. 2019 · 2019
Later among the works it cites.
On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
Original
Sandeep Subramanian, Raymond Li, Jonathan Pilault, and Christopher Pal. 2019 · 2019
Later among the works it cites.
ILPS at TREC 2019 Conversational Assistant Track. In Proc. TREC
Nikos Voskarides, Dan Li, Andreas Panteli, and Pengjie Ren. 2019 · 2019
Later among the works it cites.
Query and Answer Expansion from Conversation History. In Proc. TREC
Jheng-Hong Yang, Sheng-Chieh Lin, Chuan-Ju Wang, Jimmy Lin, and Ming-Feng Tsai. 2019 · 2019
Later among the works it cites.
Information Needs, Queries, and Query Performance Prediction. In Proc. SIGIR . 395–404
Oleg Zendel, Anna Shtok, Fiana Raiber, Oren Kurland, and J. Shane Culpepper. 2019 · 2019
Later among the works it cites.
Harnessing Evolution of Multi-Turn Conversations for Effective Answer Retrieval. In Proc. CHIIR . 33–42
Mohammad Aliannejadi, Manajit Chakraborty, Esteban Andrés Ríssola, and Fabio Crestani. 2020 · 2020
Closest in time.
Context-Aware Term Weighting For First Stage Passage Retrieval. In Proc. SIGIR . 1533–1536
Zhuyun Dai and Jamie Callan. 2020 · 2020
Closest in time.
Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models
Original
Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, and Jimmy Lin. 2020 · 2020
Closest in time.
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020 · 2020
Closest in time.
Question Rewriting for Conversational Question Answering
Original
Svitlana Vakulenko, Shayne Longpre, Zhucheng Tu, and Raviteja Anantha. 2020 · 2020
Closest in time.
Query Resolution for Conversational Search with Limited Supervision. In Proc. SIGIR
Nikos Voskarides, Dan Li, Pengjie Ren, Evangelos Kanoulas, and Maarten de Rijke. 2020 · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…