iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration

@article{Hirsch2021iFacetSumCI,
  title={iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration},
  author={Eran Hirsch and Alon Eirew and Ori Shapira and Avi Caciularu and Arie Cattan and Ori Ernst and Ramakanth Pasunuru and Hadar Ronen and Mohit Bansal and Ido Dagan},
  journal={ArXiv},
  year={2021},
  volume={abs/2109.11621}
}
We introduce iFᴀᴄᴇᴛSᴜᴍ, a web application for exploring topical document collections. iFᴀᴄᴇᴛSᴜᴍ integrates interactive summarization together with faceted search, by providing a novel faceted navigation scheme that yields abstractive summaries for the user’s selections. This approach offers both a comprehensive overview as well as particular details regard-ing subtopics of choice. The facets are automatically produced based on cross-document coreference pipelines, rendering generic concepts… 
[PDF] Semantic Reader
10 Citations
Background Citations
6
Methods Citations
4

Figures and Tables from this paper

10 Citations

EntSUM: A Data Set for Entity-Centric Extractive Summarization

This work introduces a human-annotated data set EntSUM for controllable summarization with a focus on named entities as the aspects to control and proposes extensions to state-of-the-art summarization approaches that achieve substantially better results.

EntSUM: A Data Set for Entity-Centric Summarization

This work introduces a human-annotated data set (E NT SUM) for controllable summarization with a focus on named entities as the aspects to control and proposes extensions to state-of-the-art summarization approaches that achieve substantially better results on this data set.

Interactive Query-Assisted Summarization via Deep Reinforcement Learning

Two novel deep reinforcement learning models are proposed for the interactive summarization task that address, respectively, the subtask of summarizing salient information that adheres to user queries, and the subtasking of listing suggested queries to assist users throughout their exploration.

I N T Interactive Query-Assisted Summarization via Deep Reinforcement Learning

Two novel deep reinforcement learning models are proposed for the interactive summarization task that address, respectively, the subtask of summarizing salient information that adheres to user queries, and the subtasking of listing suggested queries to assist users throughout their exploration.

Overview of the First Shared Task on Multi Perspective Scientific Document Summarization (MuP)

The task provides a testbed representing challenges for summarization of scientific documents, and facilitates development of better models to leverage summaries generated from multiple perspectives, and there is still significant room for improving summarization leveraging multiple references.

Controlled Text Reduction

This paper formalizes Controlled Text Reduction as a standalone task, whose input is a source text with marked spans of targeted content (“highlighting”), and advocates the potential of such models, both for modular fully-automatic summarization, as well as for semi-automated human-in-the-loop use cases.

What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization Research

This work finds that the current research directions of the automatic summarization community do not fully align with students’ needs, and proposes research directions that impact the design, the development and the evaluation of automatically generated summaries.

CDLM: Cross-Document Language Modeling

This work introduces a new pretraining approach geared for multi-document language modeling, incorporating two key ideas into the masked language modeling self-supervised objective: pretrain over sets of multiple related documents, encouraging the model to learn cross-document relationships.

Popularity Sensitive and Domain-aware Summarization for Web Tables

Towards Proactive Information Retrieval in Noisy Text with Wikipedia Concepts

This work explores how exploiting the context of a query using Wikipedia concepts can improve proactive information retrieval on noisy text and formulates two models that use entity linking to associate Wikipedia topics with the relevance model.

References

SHOWING 1-10 OF 47 REFERENCES

Exploring Content Models for Multi-Document Summarization

The final model, HierSum, utilizes a hierarchical LDA-style model (Blei et al., 2004) to represent content specificity as a hierarchy of topic vocabulary distributions and yields state-of-the-art ROUGE performance and in pairwise user evaluation strongly outperforms Toutanova et al. (2007)'s state of theart discriminative system.

Extending Multi-Document Summarization Evaluation to the Interactive Setting

This paper develops an end-to-end evaluation framework for interactive summarization, focusing on expansion-based interaction, which considers the accumulating information along a user session.

Coarse-to-Fine Query Focused Multi-Document Summarization

This work proposes a coarse-to-fine modeling framework which employs progressively more accurate modules for estimating whether text segments are relevant, likely to contain an answer, and central and presents an instantiation of this framework with a trained evidence estimator.

Sherlock: A System for Interactive Summarization of Large Text Collections

A new approximate summarization model is integrated into Sherlock that can guarantee interactive speeds even for large text collections to keep the user engaged in the process.

CorefQA: Coreference Resolution as Query-based Span Prediction

CorefQA is presented, an accurate and extensible approach for the coreference resolution task, formulated as a span prediction task, like in question answering, which provides the flexibility of retrieving mentions left out at the mention proposal stage.

Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution

This work jointly model entity and event coreference, and proposes a neural architecture for cross-document coreference resolution using its lexical span, surrounding context, and relation to entity (event) mentions via predicate-arguments structures.

WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia

Wikipedia Event Coreference (WEC) is presented, an efficient methodology for gathering a large-scale dataset for cross-document event coreference from Wikipedia, where coreference links are not restricted within predefined topics.

Understanding Points of Correspondence between Sentences for Abstractive Summarization

This paper presents an investigation into fusing sentences drawn from a document by introducing the notion of points of correspondence, which are cohesive devices that tie any two sentences together into a coherent text.

Product Review Summarization based on Facet Identification and Sentence Clustering

This work builds a product review summarization system that can automatically process a large collection of reviews and aggregate them to generate a concise summary, by applying clustering, prior to selecting representative candidates for summarization.

Cross-document Coreference Resolution over Predicted Mentions

This work introduces the first end-to-end model for CD coreference resolution from raw text, which extends the prominent model for withindocument coreference to the CD setting and achieves competitive results for event and entity coreferenceresolution on gold mentions.