Query Generation for Multimodal Documents

Lee, Kyung-Jae; Hwang, Seung Won; Song, Young In; Lee, Seung-Wook

doi:10.18653/v1/2021.eacl-main.54

Cited by 4 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Question Generation (QG) has a wide range of applications, such as generating questions for exams (Jia et al, 2021;Lelkes et al, 2021;Dugan et al, 2022) or children's story books (Zhao et al, 2022;Yao et al, 2022), recommending questions for users in a dialogue system (Shukla et al, 2019;Laban et al, 2020), improving visual (Li et al, 2018;Lu et al, 2022) or textual question-answering tasks (Duan et al, 2017;Lewis et al, 2019a;Zhang and Bansal, 2019;Sultan et al, 2020;Lyu et al, 2021), asking clarification questions (Rao and Daumé III, 2019;Ren et al, 2021), and generating queries for SQL or multimodal documents (Kim et al, 2021). * Equal Contribution Previous works on QG are mainly under the openbook setting, which aims to generate questions based on factoid or human-generated short answers under the assumption that there is access to external knowledge like retrieved documents or passages (Du et al, 2017;Zhao et al, 2018;Kim et al, 2019;Fei et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…After demonstrated that feeding a large pre-trained model input questions alone without any external knowledge can lead to competitive results with retrieval-based methods on open-domain question-answering benchmarks, there is an increasing interest in the closed-book setting. This closed-book setting is appealing in practice and can be widely applied, e.g., in question suggestion (Laban et al, 2020;, query recommendation (Kim et al, 2021), and other practical settings where extensive external knowledge is unavailable.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Closed-book Question Generation via Contrastive Learning

Dong,

Lu,

Wang

et al. 2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

Question Generation (QG) is a fundamental NLP task for many downstream applications.Recent studies on open-book QG, where supportive answer-context pairs are provided to models, have achieved promising progress. However, generating natural questions under a more practical closed-book setting that lacks these supporting documents still remains a challenge. In this work, we propose a new QG model for this closed-book setting that is designed to better understand the semantics of long-form abstractive answers and store more information in its parameters through contrastive learning and an answer reconstruction module. Through experiments, we validate the proposed QG model on both public datasets and a new WikiCQA dataset. Empirical results show that the proposed QG model outperforms baselines in both automatic evaluation and human evaluation. In addition, we show how to leverage the proposed model to improve existing question-answering systems. These results further indicate the effectiveness of our QG model for enhancing closed-book questionanswering tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Closed-book Question Generation via Contrastive Learning

Dong,

Lu,

Wang

et al. 2023

Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Lexical approaches use the terms that appear in a user's query to identify and score documents that contain the same terms (e.g., using an approach like BM25 over an inverted index). Lexical approaches like BM25 [35] fail to understand semantic relationships in different scenarios [17]. A major drawback of this approach is that it is limited to documents that use the exact terms that the user searches for, which can potentially affect the recall.…”

Section: Introductionmentioning

confidence: 99%

Lexically-Accelerated Dense Retrieval

Kulkarni

MacAvaney

Goharian

2023

Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Retrieval approaches that score documents based on learned dense vectors (i.e., dense retrieval) rather than lexical signals (i.e., conventional retrieval) are increasingly popular. Their ability to identify related documents that do not necessarily contain the same terms as those appearing in the user's query (thereby improving recall) is one of their key advantages. However, to actually achieve these gains, dense retrieval approaches typically require an exhaustive search over the document collection, making them considerably more expensive at query-time than conventional lexical approaches. Several techniques aim to reduce this computational overhead by approximating the results of a full dense retriever. Although these approaches reasonably approximate the top results, they suffer in terms of recall -one of the key advantages of dense retrieval. We introduce 'LADR' (Lexically-Accelerated Dense Retrieval), a simpleyet-effective approach that improves the efficiency of existing dense retrieval models without compromising on retrieval effectiveness. LADR uses lexical retrieval techniques to seed a dense retrieval exploration that uses a document proximity graph. Through extensive experiments, we find that LADR establishes a new dense retrieval effectiveness-efficiency Pareto frontier among approximate 𝑘 nearest neighbor techniques. When tuned to take around 8ms per query in retrieval latency on our hardware, LADR consistently achieves both precision and recall that are on par with an exhaustive search on standard benchmarks. Importantly, LADR accomplishes this using only a single CPU -no hardware accelerators such as GPUs -which reduces the deployment cost of dense retrieval systems. CCS CONCEPTS• Information systems → Retrieval models and ranking.

show abstract

Leveraging Customer Reviews for E-commerce Query Generation

Lien

Zhang

Harper

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Customer reviews are an effective source of information about what people deem important in products (e.g. “strong zipper” for tents). These crowd-created descriptors not only highlight key product attributes, but can also complement seller-provided product descriptions. Motivated by this, we propose to leverage customer reviews to generate queries pertinent to target products in an e-commerce setting. While there has been work on automatic query generation, it often relied on proprietary user search data to generate query-document training pairs for learning supervised models. We take a different view and focus on leveraging reviews without training on search logs, making reproduction more viable by the public. Our method adopts an ensemble of the statistical properties of review terms and a zero-shot neural model trained on adapted external corpus to synthesize queries. Compared to competitive baselines, we show that the generated queries based on our method both better align with actual customer queries and can benefit retrieval effectiveness.

show abstract

Query Generation for Multimodal Documents

Cited by 4 publications

References 16 publications

Closed-book Question Generation via Contrastive Learning

Closed-book Question Generation via Contrastive Learning

Lexically-Accelerated Dense Retrieval

Leveraging Customer Reviews for E-commerce Query Generation

Contact Info

Product

Resources

About