Pith. sign in

REVIEW 3 cited by

Learning to Coordinate Multiple Reinforcement Learning Agents for Diverse Query Reformulation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1809.10658 v2 pith:LCGVJF23 submitted 2018-09-27 cs.LG stat.ML

Rodrigo Nogueira , Jannis Bulian , Massimiliano Ciaramita This is my paper · ORCID
classification cs.LGstat.ML
keywords learningreformulationsub-agentstrainedagentsdatadiversefull
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We propose a method to efficiently learn diverse strategies in reinforcement learning for query reformulation in the tasks of document retrieval and question answering. In the proposed framework an agent consists of multiple specialized sub-agents and a meta-agent that learns to aggregate the answers from sub-agents to produce a final answer. Sub-agents are trained on disjoint partitions of the training data, while the meta-agent is trained on the full training set. Our method makes learning faster, because it is highly parallelizable, and has better generalization performance than strong baselines, such as an ensemble of agents trained on the full data. We show that the improved performance is due to the increased diversity of reformulation strategies.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The False Promise of Imitating Proprietary LLMs

    cs.CL 2023-05 conditional novelty 6.0 of 10

    Finetuning open LMs on ChatGPT outputs creates models that mimic style and fool human raters but fail to close the performance gap to proprietary systems on tasks not well-represented in the imitation data.

  2. Multi-passage BERT: A Globally Normalized BERT Model for Open-domain Question Answering

    cs.CL 2019-08 accept novelty 6.0 of 10

    Applying global normalization across passages, 100-word sliding windows, and a passage ranker to BERT yields state-of-the-art open-domain QA results on four benchmarks.

  3. Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System

    cs.IR 2019-08 conditional novelty 5.0 of 10

    QREFINE, a BERT- and character-aware Seq2Seq model trained with PPO and answer-aware rewards, generates cleaned questions that improve answer retrieval over previous refinement methods.

Pith tools