Pith. sign in

REVIEW 4 cited by

Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models

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 2004.01909 v1 pith:ZQKKWZ7X submitted 2020-04-04 cs.CL cs.AIcs.LG

Sheng-Chieh Lin , Jheng-Hong Yang , Rodrigo Nogueira , Ming-Feng Tsai , Chuan-Ju Wang , Jimmy Lin This is my paper · ORCID
classification cs.CLcs.AIcs.LG
keywords architecturesmodelsplmstaskcanardcastconversationallanguage
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs). We leverage PLMs to address the strong token-to-token independence assumption made in the common objective, maximum likelihood estimation, for the CQR task. In CQR benchmarks of task-oriented dialogue systems, we evaluate fine-tuned PLMs on the recently-introduced CANARD dataset as an in-domain task and validate the models using data from the TREC 2019 CAsT Track as an out-domain task. Examining a variety of architectures with different numbers of parameters, we demonstrate that the recent text-to-text transfer transformer (T5) achieves the best results both on CANARD and CAsT with fewer parameters, compared to similar transformer architectures.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Adaptive Personalized Conversational Information Retrieval

    cs.IR 2025-08 conditional novelty 6.0 of 10

    Explicit per-turn personalization level detection plus per-level weighted fusion of personalized and non-personalized query rewrites improves retrieval on TREC iKAT 2023 and 2024.

  2. Building Open-Retrieval Conversational Question Answering Systems by Generating Synthetic Data and Decontextualizing User Questions

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A pipeline that extracts propositions from documents, generates synthetic grounded dialogs, and uses them to train lightweight question rewriters and retrievers for open-retrieval conversational QA.

  3. Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation

    cs.CR 2025-02 conditional novelty 6.0 of 10

    A membership inference attack on RAG systems crafts natural yes/no questions from a target document to detect its presence in the datastore, achieving high AUC while evading guardrail detectors.

  4. RALI@TREC iKAT 2024: Achieving Personalization via Retrieval Fusion in Conversational Search

    cs.IR 2024-12 conditional novelty 5.0 of 10

    Fusing BM25 rankings from non-personalized, expanded, and personalized query rewrites achieved the best passage retrieval scores for RALI at TREC iKAT 2024, though no ablation isolates the fusion effect.

Pith tools