Abstractive Snippet Generation

Chen, Wei-Fan; Syed, Shahbaz; Stein, Benno; Hagen, Matthias; Potthast, Martin

doi:10.1145/3366423.3380206

Cited by 21 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, extractive explanations by LIME are likely to be relevant to the document, and do not require the same evaluations as abstractive explanations by GenEx. Note that abstractive generation of texts at the level of noun-phrase has a lower risk of topic drift compared to abstractive snippet generation which has been motivated recently [7], and is confirmed by the results of human evaluation on relevance to document content.…”

Section: Explanations Qualitysupporting

confidence: 63%

“…Bast and Celikik [5] proposed an efficient solution for extractive snippets by taking advantage of inverted index, a popular data structure used in most information retrieval systems. Recently, Chen et al [7] proposed abstractive snippet generation as a potential solution to circumvent copyright issues. The authors demonstrated that despite the popularity of extractive snippets in the current search engines, abstractive summarization is equally powerful in terms of user acceptance and expressiveness.…”

Section: Snippet Generationmentioning

confidence: 99%

See 1 more Smart Citation

Explaining Documents' Relevance to Search Queries

Rahimi¹,

Kim²,

Zamani³

et al. 2021

Preprint

View full text Add to dashboard Cite

We present GenEx, a generative model to explain search results to users beyond just showing matches between query and document words. Adding GenEx explanations to search results greatly impacts user satisfaction and search performance. Search engines mostly provide document titles, URLs, and snippets for each result. Existing model-agnostic explanation methods similarly focus on word matching or content-based features. However, a recent user study shows that word matching features are quite obvious to users and thus of slight value. GenEx explains a search result by providing a terse description for the query aspect covered by that result. We cast the task as a sequence transduction problem and propose a novel model based on the Transformer architecture. To represent documents with respect to the given queries and yet not generate the queries themselves as explanations, two query-attention layers and masked-query decoding are added to the Transformer architecture. The model is trained without using any human-generated explanations. Training data are instead automatically constructed to ensure a tolerable noise level and a generalizable learned model. Experimental evaluation shows that our explanation models significantly outperform the baseline models.Evaluation through user studies also demonstrates that our explanation model generates short yet useful explanations.

show abstract

Section: Explanations Qualitysupporting

confidence: 63%

Section: Snippet Generationmentioning

confidence: 99%

Explaining Documents' Relevance to Search Queries

Rahimi¹,

Kim²,

Zamani³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, search snippet generation can be considered as one kind of Query-focused Summarization (QFS). Similar to generic document summarization, this body of work can also be divided into extractive approaches (Zhu et al, 2019;Feigenblat et al, 2017;Roitman et al, 2020) and abstractive approaches (Laskar et al, 2020a;Baumel et al, 2018;Chen et al, 2020a;Su et al, 2020;Laskar et al, 2020b). As some PTMs are proved to be effective in text generation, most existing work adopted PTMs to generate abstractive snippets.…”

Section: Snippet Generationmentioning

confidence: 99%

Pre-training Methods in Information Retrieval

Fan¹,

Xie²,

Cai³

et al. 2021

Preprint

View full text Add to dashboard Cite

The core of information retrieval (IR) is to identify relevant information from large-scale resources and return it as a ranked list to respond to user's information need. Recently, the resurgence of deep learning has greatly advanced this field and leads to a hot topic named NeuIR (i.e., neural information retrieval), especially the paradigm of pre-training methods (PTMs). Owing to sophisticated pre-training objectives and huge model size, pre-trained models can learn universal language representations from massive textual data, which are beneficial to the ranking task of IR. Since there have been a large number of works dedicating to the

show abstract

“…Suitable datasets include DUC 2004, DUC 2005, and DUC 2006, which contain query-based (multi-)document summaries (DUC). Webis-Snippet-20 consists of 10M web pages together with their query-based abstractive snippets (Chen et al, 2020). In these datasets, each document (or set of documents) has one or more summaries with respect to a single query.…”

Section: Related Workmentioning

confidence: 99%

SUBSUME: A Dataset for Subjective Summary Extraction from Wikipedia Documents

Yadav¹,

Brucato²,

Fariha³

et al. 2021

Proceedings of the Third Workshop on New Frontiers in Summarization

View full text Add to dashboard Cite

Many applications require generation of summaries tailored to the user's information needs, i.e., their intent. Methods that express intent via explicit user queries fall short when query interpretation is subjective. Several datasets exist for summarization with objective intents where, for each document and intent (e.g., "weather"), a single summary suffices for all users. No datasets exist, however, for subjective intents (e.g., "interesting places") where different users will provide different summaries. We present SUBSUME, the first dataset for evaluation of SUBjective SUMmary Extraction systems. SUBSUME contains 2,200 (document, intent, summary) triplets over 48 Wikipedia pages, with ten intents of varying subjectivity, provided by 103 individuals over Mechanical Turk. We demonstrate statistically that the intents in SUBSUME vary systematically in subjectivity. To indicate SUB-SUME's usefulness, we explore a collection of baseline algorithms for subjective extractive summarization and show that (i) as expected, example-based approaches better capture subjective intents than query-based ones, and (ii) there is ample scope for improving upon the baseline algorithms, thereby motivating further research on this challenging problem.

show abstract

Abstractive Snippet Generation

Cited by 21 publications

References 27 publications

Explaining Documents' Relevance to Search Queries

Explaining Documents' Relevance to Search Queries

Pre-training Methods in Information Retrieval

SUBSUME: A Dataset for Subjective Summary Extraction from Wikipedia Documents

Contact Info

Product

Resources

About