Large Language Models (LLMs) have shown promising performance in summary evaluation tasks, yet they face challenges such as high computational costs and the Lost-in-the-Middle problem where important information in the middle of long documents is often overlooked. To address these issues, this paper introduces a novel approach, Extract-then-Evaluate, which involves extracting key sentences from a long source document and then evaluating the summary by prompting LLMs. The results reveal that the proposed method not only significantly reduces evaluation costs but also exhibits a higher correlation with human evaluations. Furthermore, we provide practical recommendations for optimal document length and sentence extraction methods, contributing to the development of cost-effective yet more accurate methods for LLM-based text generation evaluation.
While large language models (LMs) demonstrate remarkable performance, they encounter challenges in providing accurate responses when queried for information beyond their pre-trained memorization. Although augmenting them with relevant external information can mitigate these issues, failure to consider the necessity of retrieval may adversely affect overall performance. Previous research has primarily focused on examining how entities influence retrieval models and knowledge recall in LMs, leaving other aspects relatively unexplored. In this work, our goal is to offer a more detailed, fact-centric analysis by exploring the effects of combinations of entities and relations. To facilitate this, we construct a new question answering (QA) dataset called WiTQA (Wikipedia Triple Question Answers). This dataset includes questions about entities and relations of various popularity levels, each accompanied by a supporting passage. Our extensive experiments with diverse LMs and retrievers reveal when retrieval does not consistently enhance LMs from the viewpoints of fact-centric popularity. Confirming earlier findings, we observe that larger LMs excel in recalling popular facts. However, they notably encounter difficulty with infrequent entity-relation pairs compared to retrievers. Interestingly, they can effectively retain popular relations of less common entities. We demonstrate the efficacy of our finer-grained metric and insights through an adaptive retrieval system that selectively employs retrieval and recall based on the frequencies of entities and relations in the question.
Lexically constrained text generation is one of the constrained text generation tasks, which aims to generate text that covers all the given constraint lexicons. While the existing approaches tackle this problem using a lexically constrained beam search algorithm or dedicated model using non-autoregressive decoding, there is a trade-off between the generated text quality and the hard constraint satisfaction. We introduce AutoTemplate, a simple yet effective lexically constrained text generation framework divided into template generation and lexicalization tasks. The template generation is to generate the text with the placeholders, and lexicalization replaces them into the constraint lexicons to perform lexically constrained text generation. We conducted the experiments on two tasks: keywords-to-sentence generations and entity-guided summarization. Experimental results show that the AutoTemplate outperforms the competitive baselines on both tasks while satisfying the hard lexical constraints. The code is available at https://github.com/megagonlabs/autotemplate
Opinion summarization research has primarily focused on generating summaries reflecting important opinions from customer reviews without paying much attention to the writing style. In this paper, we propose the stylized opinion summarization task, which aims to generate a summary of customer reviews in the desired (e.g., professional) writing style. To tackle the difficulty in collecting customer and professional review pairs, we develop a non-parallel training framework, Noisy Pairing and Partial Supervision (NAPA), which trains a stylized opinion summarization system from non-parallel customer and professional review sets. We create a benchmark ProSum by collecting customer and professional reviews from Yelp and Michelin. Experimental results on ProSum and FewSum demonstrate that our non-parallel training framework consistently improves both automatic and human evaluations, successfully building a stylized opinion summarization model that can generate professionally-written summaries from customer reviews. The code is available at https://github.com/megagonlabs/napa
Text editing is a crucial task of modifying text to better align with user intents. However, existing text editing benchmark datasets contain only coarse-grained instructions and lack explainability, thus resulting in outputs that deviate from the intended changes outlined in the gold reference. To comprehensively investigate the text editing capabilities of large language models (LLMs), this paper introduces XATU, the first benchmark specifically designed for fine-grained instruction-based explainable text editing. XATU considers finer-grained text editing tasks of varying difficulty (simplification, grammar check, fact-check, etc.), incorporating lexical, syntactic, semantic, and knowledge-intensive edit aspects. To enhance interpretability, we combine LLM-based annotation and human annotation, resulting in a benchmark that includes fine-grained instructions and gold-standard edit explanations. By evaluating existing LLMs against our benchmark, we demonstrate the effectiveness of instruction tuning and the impact of underlying architecture across various editing tasks. Furthermore, extensive experimentation reveals the significant role of explanations in fine-tuning language models for text editing tasks. The benchmark will be open-sourced to support reproduction and facilitate future research at https://github.com/megagonlabs/xatu.
Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and concise information about a particular hotel or product, the information may be insufficient to help the user compare multiple different choices. Thus, the user may still struggle with the question “Which one should I pick?” In this paper, we propose the comparative opinion summarization task, which aims at generating two contrastive summaries and one common summary from two different candidate sets of reviews. We develop a comparative summarization framework CoCoSum, which consists of two base summarization models that jointly generate contrastive and common summaries. Experimental results on a newly created benchmark CoCoTrip show that CoCoSum can produce higher-quality contrastive and common summaries than state-of-the-art opinion summarization models. The dataset and code are available at https://github.com/megagonlabs/cocosum
Recent advances in text autoencoders have significantly improved the quality of the latent space, which enables models to generate grammatical and consistent text from aggregated latent vectors. As a successful application of this property, unsupervised opinion summarization models generate a summary by decoding the aggregated latent vectors of inputs. More specifically, they perform the aggregation via simple average. However, little is known about how the vector aggregation step affects the generation quality. In this study, we revisit the commonly used simple average approach by examining the latent space and generated summaries. We found that text autoencoders tend to generate overly generic summaries from simply averaged latent vectors due to an unexpected L2-norm shrinkage in the aggregated latent vectors, which we refer to as summary vector degeneration. To overcome this issue, we develop a framework Coop, which searches input combinations for the latent vector aggregation using input-output word overlap. Experimental results show that Coop successfully alleviates the summary vector degeneration issue and establishes new state-of-the-art performance on two opinion summarization benchmarks. Code is available at https://github.com/megagonlabs/coop.
Disease name recognition and normalization is a fundamental process in biomedical text mining. Recently, neural joint learning of both tasks has been proposed to utilize the mutual benefits. While this approach achieves high performance, disease concepts that do not appear in the training dataset cannot be accurately predicted. This study introduces a novel end-to-end approach that combines span representations with dictionary-matching features to address this problem. Our model handles unseen concepts by referring to a dictionary while maintaining the performance of neural network-based models. Experiments using two major datasaets demonstrate that our model achieved competitive results with strong baselines, especially for unseen concepts during training.
We propose a novel text editing task, referred to as fact-based text editing, in which the goal is to revise a given document to better describe the facts in a knowledge base (e.g., several triples). The task is important in practice because reflecting the truth is a common requirement in text editing. First, we propose a method for automatically generating a dataset for research on fact-based text editing, where each instance consists of a draft text, a revised text, and several facts represented in triples. We apply the method into two public table-to-text datasets, obtaining two new datasets consisting of 233k and 37k instances, respectively. Next, we propose a new neural network architecture for fact-based text editing, called FactEditor, which edits a draft text by referring to given facts using a buffer, a stream, and a memory. A straightforward approach to address the problem would be to employ an encoder-decoder model. Our experimental results on the two datasets show that FactEditor outperforms the encoder-decoder approach in terms of fidelity and fluency. The results also show that FactEditor conducts inference faster than the encoder-decoder approach.
We propose a data-to-text generation model with two modules, one for tracking and the other for text generation. Our tracking module selects and keeps track of salient information and memorizes which record has been mentioned. Our generation module generates a summary conditioned on the state of tracking module. Our proposed model is considered to simulate the human-like writing process that gradually selects the information by determining the intermediate variables while writing the summary. In addition, we also explore the effectiveness of the writer information for generations. Experimental results show that our proposed model outperforms existing models in all evaluation metrics even without writer information. Incorporating writer information further improves the performance, contributing to content planning and surface realization.
To date, various Twitter-based event detection systems have been proposed. Most of their targets, however, share common characteristics. They are seasonal or global events such as earthquakes and flu pandemics. In contrast, this study targets unseasonal and local disease events. Our system investigates the frequencies of disease-related words such as “nausea”,“chill”,and “diarrhea” and estimates the number of patients using regression of these word frequencies. Experiments conducted using Japanese 47 areas from January 2017 to April 2017 revealed that the detection of small and unseasonal event is extremely difficult (overall performance: 0.13). However, we found that the event scale and the detection performance show high correlation in the specified cases (in the phase of patient increasing or decreasing). The results also suggest that when 150 and more patients appear in a high population area, we can expect that our social sensors detect this outbreak. Based on these results, we can infer that social sensors can reliably detect unseasonal and local disease events under certain conditions, just as they can for seasonal or global events.
Because of the increasing popularity of social media, much information has been shared on the internet, enabling social media users to understand various real world events. Particularly, social media-based infectious disease surveillance has attracted increasing attention. In this work, we specifically examine influenza: a common topic of communication on social media. The fundamental theory of this work is that several words, such as symptom words (fever, headache, etc.), appear in advance of flu epidemic occurrence. Consequently, past word occurrence can contribute to estimation of the number of current patients. To employ such forecasting words, one can first estimate the optimal time lag for each word based on their cross correlation. Then one can build a linear model consisting of word frequencies at different time points for nowcasting and for forecasting influenza epidemics. Experimentally obtained results (using 7.7 million tweets of August 2012 – January 2016), the proposed model achieved the best nowcasting performance to date (correlation ratio 0.93) and practically sufficient forecasting performance (correlation ratio 0.91 in 1-week future prediction, and correlation ratio 0.77 in 3-weeks future prediction). This report is the first of the relevant literature to describe a model enabling prediction of future epidemics using Twitter.