We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information salience for pretraining strategy design, they struggle to generate abstractive and reflective summaries, which are critical properties for MDS. To this end, we present PELMS, a pre-trained model that uses pre-training objectives based on semantic coherence heuristics and faithfulness constraints together with unlabeled multi-document inputs, to promote the generation of concise, fluent, and faithful summaries. To support the training of PELMS, we compile MultiPT, a multidocument pre-training corpus containing over 93 million documents to form more than 3 million unlabeled topic-centric document clusters, covering diverse genres such as product reviews, news, and general knowledge. We perform extensive evaluation of PELMS in lowshot settings on a wide range of MDS datasets. Our approach consistently outperforms competitive comparisons with respect to overall informativeness, abstractiveness, coherence, and faithfulness, and with minimal fine-tuning can match performance of language models at a much larger scale (e.g., GPT-4).
more »
« less
The Removal of Irrelevant Human Factors in a Multi-Review Corpus through Text Filtering
Generating a high-quality explainable summary of a multi-review corpus can help people save time in reading the reviews. With natural language processing and text clustering, people can generate both abstractive and extractive summaries on a corpus containing up to 967 product reviews (Moody et al. 2022). However, the overall quality of the summaries needs further improvement. Noticing that online reviews in the corpus come from a diverse population, we take an approach of removing irrelevant human factors through pre-processing. Apply available pre-trained models together with reference based and reference free metrics, we filter out noise in each review automatically prior to summary generation. Our computational experiments evident that one may significantly improve the overall quality of an explainable summary from such a pre-processed corpus than from the original one. It is suggested of applying available high-quality pre-trained tools to filter noises rather than start from scratch. Although this work is on the specific multi-review corpus, the methods and conclusions should be helpful for generating summaries for other multi-review corpora.
more » « less- Award ID(s):
- 1946391
- PAR ID:
- 10498137
- Publisher / Repository:
- AHFE International
- Date Published:
- Journal Name:
- Accelerating Open Access Science in Human Factors Engineering and Human-Centered Computing
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Medical systematic reviews play a vital role in healthcare decision making and policy. However, their production is time-consuming, limiting the availability of high-quality and up-to-date evidence summaries. Recent advancements in LLMs offer the potential to automatically generate literature reviews on demand, addressing this issue. However, LLMs sometimes generate inaccurate (and potentially misleading) texts by hallucination or omission. In healthcare, this can make LLMs unusable at best and dangerous at worst. We conducted 16 interviews with international systematic review experts to characterize the perceived utility and risks of LLMs in the specific context of medical evidence reviews. Experts indicated that LLMs can assist in the writing process by drafting summaries, generating templates, distilling information, and crosschecking information. They also raised concerns regarding confidently composed but inaccurate LLM outputs and other potential downstream harms, including decreased accountability and proliferation of low-quality reviews. Informed by this qualitative analysis, we identify criteria for rigorous evaluation of biomedical LLMs aligned with domain expert views.more » « less
-
Recent work has shown that large language models (LLMs) are capable of generating summaries zero-shot—i.e., without explicit supervision—that, under human assessment, are often comparable or even preferred to manually composed reference summaries. However, this prior work has focussed almost exclusively on evaluating news article summarization. How do zero-shot summarizers perform in other (potentially more specialized) domains?In this work we evaluate zero-shot generated summaries across specialized domains including: biomedical articles, and legal bills (in addition to standard news benchmarks for reference). We focus especially on the factuality of outputs. We acquire annotations from domain experts to identify inconsistencies in summaries and systematically categorize these errors. We analyze whether the prevalence of a given domain in the pretraining corpus affects extractiveness and faithfulness of generated summaries of articles in this domain. We release all collected annotations to facilitate additional research toward measuring and realizing factually accurate summarization, beyond news articles (The dataset can be downloaded from https://anonymous.4open.science/r/zero_shot_faceval_domains-9B83)more » « less
-
The increased prevalence of online meetings has significantly en- hanced the practicality of a model that can automatically generate the summary of a given meeting. This paper introduces a novel and effective approach to automate the generation of meeting sum- maries. Current approaches to this problem generate general and basic summaries, considering the meeting simply as a long dialogue. However, our novel algorithms can generate abstractive meeting summaries that are driven by the action items contained in the meet- ing transcript. This is done by recursively generating summaries and employing our action-item extraction algorithm for each sec- tion of the meeting in parallel. All of these sectional summaries are then combined and summarized together to create a coherent and action-item-driven summary. In addition, this paper introduces three novel methods for dividing up long transcripts into topic- based sections to improve the time efficiency of our algorithm, as well as to resolve the issue of large language models (LLMs) forget- ting long-term dependencies. Our pipeline achieved a BERTScore of 64.98 across the AMI corpus, which is an approximately 4.98% increase from the current state-of-the-art result produced by a fine-tuned BART (Bidirectional and Auto-Regressive Transformers) model.more » « less
-
Abstract Eliciting informative user opinions from online reviews is a key success factor for innovative product design and development. The unstructured, noisy, and verbose nature of user reviews, however, often complicate large-scale need finding in a format useful for designers without losing important information. Recent advances in abstractive text summarization has created the opportunity to systematically generate opinion summaries from online reviews to inform the early stages of product design and development. However, two knowledge gaps hinder the applicability of opinion summarization methods in practice. First, there is a lack of formal mechanisms to guide the generative process with respect to different categories of product attributes and user sentiments. Second, the annotated training datasets needed for supervised training of abstractive summarization models are often difficult and costly to create. This article addresses these gaps by (1) devising an efficient computational framework for abstractive opinion summarization guided by specific product attributes and sentiment polarities, and (2) automatically generating a synthetic training dataset that captures various degrees of granularity and polarity. A hierarchical multi-instance attribute-sentiment inference mode is developed for assembling a high-quality synthetic dataset, which is utilized to fine-tune a pretrained language model for abstractive summary generation. Numerical experiments conducted on a large dataset scraped from three major e-Commerce retail store for apparel and footwear products indicate the performance, feasibility, and potentials of the developed framework. Several directions are provided for future exploration in the area of automated opinion summarization for user-centered design.more » « less
