Grounded text generation, encompassing tasks such as long-form question-answering and summarization, necessitates both content selection and content consolidation. Current end-to-end methods are difficult to control and interpret due to their opaqueness.Accordingly, recent works have proposed a modular approach, with separate components for each step. Specifically, we focus on the second subtask, of generating coherent text given pre-selected content in a multi-document setting. Concretely, we formalize Fusion-in-Context (FiC) as a standalone task, whose input consists of source texts with highlighted spans of targeted content. A model then needs to generate a coherent passage that includes all and only the target information.Our work includes the development of a curated dataset of 1000 instances in the reviews domain, alongside a novel evaluation framework for assessing the faithfulness and coverage of highlights, which strongly correlate to human judgment. Several baseline models exhibit promising outcomes and provide insightful analyses.This study lays the groundwork for further exploration of modular text generation in the multi-document setting, offering potential improvements in the quality and reliability of generated content. Our benchmark, FuseReviews, including the dataset, evaluation framework, and designated leaderboard, can be found at https://fusereviews.github.io/.
Multi-document summarization (MDS) is a challenging task, often decomposed to subtasks of salience and redundancy detection, followed by text generation.In this context, alignment of corresponding sentences between a reference summary and its source documents has been leveraged to generate training data for some of the component tasks. Yet, this enabling alignment step has usually been applied heuristically on the sentence level on a limited number of subtasks.In this paper, we propose extending the summary-source alignment framework by (1) applying it at the more fine-grained proposition span level, (2) annotating alignment manually in a multi-document setup, and (3) revealing the great potential of summary-source alignments to yield several datasets for at least six different tasks. Specifically, for each of the tasks, we release a manually annotated test set that was derived automatically from the alignment annotation. We also release development and train sets in the same way, but from automatically derived alignments.Using the datasets, each task is demonstrated with baseline models and corresponding evaluation metrics to spur future research on this broad challenge.
In the Multi-document summarization (MDS) task, a summary is produced for a given set of documents. A recent line of research introduced the concept of damaging documents, denoting documents that should not be exposed to readers due to various reasons. In the presence of damaging documents, a summarizer is ideally expected to exclude damaging content in its output. Existing metrics evaluate a summary based on aspects such as relevance and consistency with the source documents. We propose to additionally measure the ability of MDS systems to properly handle damaging documents in their input set. To that end, we offer two novel metrics based on lexical similarity and language model likelihood. A set of experiments demonstrates the effectiveness of our metrics in measuring the ability of MDS systems to summarize a set of documents while eliminating damaging content from their summaries.
The common practice for assessing automatic evaluation metrics is to measure the correlation between their induced system rankings and those obtained by reliable human evaluation, where a higher correlation indicates a better metric. Yet, an intricate setting arises when an NLP task is evaluated by multiple Quality Criteria (QCs), like for text summarization where prominent criteria including relevance, consistency, fluency and coherence. In this paper, we challenge the soundness of this methodology when multiple QCs are involved, concretely for the summarization case. First, we show that the allegedly best metrics for certain QCs actually do not perform well, failing to detect even drastic summary corruptions with respect to the considered QC. To explain this, we show that some of the high correlations obtained in the multi-QC setup are spurious. Finally, we propose a procedure that may help detecting this effect. Overall, our findings highlight the need for further investigating metric evaluation methodologies for the multiple-QC case.
The performance of automatic summarization models has improved dramatically in recent years. Yet, there is still a gap in meeting specific information needs of users in real-world scenarios, particularly when a targeted summary is sought, such as in the useful aspect-based summarization setting targeted in this paper. Previous datasets and studies for this setting have predominantly concentrated on a limited set of pre-defined aspects, focused solely on single document inputs, or relied on synthetic data. To advance research on more realistic scenarios, we introduce OpenAsp, a benchmark for multi-document open aspect-based summarization. This benchmark is created using a novel and cost-effective annotation protocol, by which an open aspect dataset is derived from existing generic multi-document summarization datasets. We analyze the properties of OpenAsp showcasing its high-quality content. Further, we show that the realistic open-aspect setting realized in OpenAsp poses a challenge for current state-of-the-art summarization models, as well as for large language models.
Current approaches for text summarization are predominantly automatic, with rather limited space for human intervention and control over the process. In this paper, we introduce SummHelper, and screencast demo at https://www.youtube.com/watch?v=nGcknJwGhxk a 2-phase summarization assistant designed to foster human-machine collaboration. The initial phase involves content selection, where the system recommends potential content, allowing users to accept, modify, or introduce additional selections. The subsequent phase, content consolidation, involves SummHelper generating a coherent summary from these selections, which users can then refine using visual mappings between the summary and the source text. Small-scale user studies reveal the effectiveness of our application, with participants being especially appreciative of the balance between automated guidance and opportunities for personal input.
Phrase similarity is a key component of many NLP applications. Current phrase similarity methods focus on embedding the phrase itself and use the phrase context only during training of the pretrained model. To better leverage the information in the context, we propose McPhraSy (Multi-context Phrase Similarity), a novel algorithm for estimating the similarity of phrases based on multiple contexts. At inference time, McPhraSy represents each phrase by considering multiple contexts in which it appears and computes the similarity of two phrases by aggregating the pairwise similarities between the contexts of the phrases. Incorporating context during inference enables McPhraSy to outperform current state-of-the-art models on two phrase similarity datasets by up to 13.3%. Finally, we also present a new downstream task that relies on phrase similarity – keyphrase clustering – and create a new benchmark for it in the product reviews domain. We show that McPhraSy surpasses all other baselines for this task.
Text clustering methods were traditionally incorporated into multi-document summarization (MDS) as a means for coping with considerable information repetition. Particularly, clusters were leveraged to indicate information saliency as well as to avoid redundancy. Such prior methods focused on clustering sentences, even though closely related sentences usually contain also non-aligned parts. In this work, we revisit the clustering approach, grouping together sub-sentential propositions, aiming at more precise information alignment. Specifically, our method detects salient propositions, clusters them into paraphrastic clusters, and generates a representative sentence for each cluster via text fusion. Our summarization method improves over the previous state-of-the-art MDS method in the DUC 2004 and TAC 2011 datasets, both in automatic ROUGE scores and human preference.
Interactive summarization is a task that facilitates user-guided exploration of information within a document set. While one would like to employ state of the art neural models to improve the quality of interactive summarization, many such technologies cannot ingest the full document set or cannot operate at sufficient speed for interactivity. To that end, we propose two novel deep reinforcement learning models for the task that address, respectively, the subtask of summarizing salient information that adheres to user queries, and the subtask of listing suggested queries to assist users throughout their exploration. In particular, our models allow encoding the interactive session state and history to refrain from redundancy. Together, these models compose a state of the art solution that addresses all of the task requirements. We compare our solution to a recent interactive summarization system, and show through an experimental study involving real users that our models are able to improve informativeness while preserving positive user experience.
We study the phenomenon of linguistic synchrony between clients and therapists in a psychotherapy process. Linguistic Synchrony (LS) can be viewed as any observed interdependence or association between more than one person?s linguistic behavior. Accordingly, we establish LS as a methodological task. We suggest a LS function that applies a linguistic similarity measure based on the Jensen-Shannon distance across the observed part-of-speech tag distributions (JSDuPos) of the speakers in different time frames. We perform a study over a unique corpus of 872 transcribed sessions, covering 68 clients and 59 therapists. After establishing the presence of client-therapist LS, we verify its association with therapeutic alliance and treatment outcome (measured using WAI and ORS), and additionally analyse the behavior of JSDuPos throughout treatment. Results indicate that (1) higher linguistic similarity at the session level associates with higher therapeutic alliance as reported by the client and therapist at the end of the session, (2) higher linguistic similarity at the session level associates with higher level of treatment outcome as reported by the client at the beginnings of the next sessions, (3) there is a significant linear increase in linguistic similarity throughout treatment, (4) surprisingly, higher LS associates with lower treatment outcome. Finally, we demonstrate how the LS function can be used to interpret and explore the mechanism for synchrony.
Allowing users to interact with multi-document summarizers is a promising direction towards improving and customizing summary results. Different ideas for interactive summarization have been proposed in previous work but these solutions are highly divergent and incomparable. In this paper, we develop an end-to-end evaluation framework for interactive summarization, focusing on expansion-based interaction, which considers the accumulating information along a user session. Our framework includes a procedure of collecting real user sessions, as well as evaluation measures relying on summarization standards, but adapted to reflect interaction. All of our solutions and resources are available publicly as a benchmark, allowing comparison of future developments in interactive summarization, and spurring progress in its methodological evaluation. We demonstrate the use of our framework by evaluating and comparing baseline implementations that we developed for this purpose, which will serve as part of our benchmark. Our extensive experimentation and analysis motivate the proposed evaluation framework design and support its viability.
We introduce a large set of Hebrew lexicons pertaining to psychological aspects. These lexicons are useful for various psychology applications such as detecting emotional state, well being, relationship quality in conversation, identifying topics (e.g., family, work) and many more. We discuss the challenges in creating and validating lexicons in a new language, and highlight our methodological considerations in the data-driven lexicon construction process. Most of the lexicons are publicly available, which will facilitate further research on Hebrew clinical psychology text analysis. The lexicons were developed through data driven means, and verified by domain experts, clinical psychologists and psychology students, in a process of reconciliation with three judges. Development and verification relied on a dataset of a total of 872 psychotherapy session transcripts. We describe the construction process of each collection, the final resource and initial results of research studies employing this resource.
Aligning sentences in a reference summary with their counterparts in source documents was shown as a useful auxiliary summarization task, notably for generating training data for salience detection. Despite its assessed utility, the alignment step was mostly approached with heuristic unsupervised methods, typically ROUGE-based, and was never independently optimized or evaluated. In this paper, we propose establishing summary-source alignment as an explicit task, while introducing two major novelties: (1) applying it at the more accurate proposition span level, and (2) approaching it as a supervised classification task. To that end, we created a novel training dataset for proposition-level alignment, derived automatically from available summarization evaluation data. In addition, we crowdsourced dev and test datasets, enabling model development and proper evaluation. Utilizing these data, we present a supervised proposition alignment baseline model, showing improved alignment-quality over the unsupervised approach.
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, entities and statements surfacing in the source texts. We analyze the effectiveness of our application through small-scale user studies that suggest the usefulness of our tool.
Conducting a manual evaluation is considered an essential part of summary evaluation methodology. Traditionally, the Pyramid protocol, which exhaustively compares system summaries to references, has been perceived as very reliable, providing objective scores. Yet, due to the high cost of the Pyramid method and the required expertise, researchers resorted to cheaper and less thorough manual evaluation methods, such as Responsiveness and pairwise comparison, attainable via crowdsourcing. We revisit the Pyramid approach, proposing a lightweight sampling-based version that is crowdsourcable. We analyze the performance of our method in comparison to original expert-based Pyramid evaluations, showing higher correlation relative to the common Responsiveness method. We release our crowdsourced Summary-Content-Units, along with all crowdsourcing scripts, for future evaluations.
Reinforcement Learning (RL)based document summarisation systems yield state-of-the-art performance in terms of ROUGE scores, because they directly use ROUGE as the rewards during training. However, summaries with high ROUGE scores often receive low human judgement. To find a better reward function that can guide RL to generate human-appealing summaries, we learn a reward function from human ratings on 2,500 summaries. Our reward function only takes the document and system summary as input. Hence, once trained, it can be used to train RL based summarisation systems without using any reference summaries. We show that our learned rewards have significantly higher correlation with human ratings than previous approaches. Human evaluation experiments show that, compared to the state-of-the-art supervised-learning systems and ROUGE-as-rewards RL summarisation systems, the RL systems using our learned rewards during training generate summaries with higher human ratings. The learned reward function and our source code are available at https://github.com/yg211/summary-reward-no-reference.
We show that plain ROUGE F1 scores are not ideal for comparing current neural systems which on average produce different lengths. This is due to a non-linear pattern between ROUGE F1 and summary length. To alleviate the effect of length during evaluation, we have proposed a new method which normalizes the ROUGE F1 scores of a system by that of a random system with same average output length. A pilot human evaluation has shown that humans prefer short summaries in terms of the verbosity of a summary but overall consider longer summaries to be of higher quality. While human evaluations are more expensive in time and resources, it is clear that normalization, such as the one we proposed for automatic evaluation, will make human evaluations more meaningful.
Practical summarization systems are expected to produce summaries of varying lengths, per user needs. While a couple of early summarization benchmarks tested systems across multiple summary lengths, this practice was mostly abandoned due to the assumed cost of producing reference summaries of multiple lengths. In this paper, we raise the research question of whether reference summaries of a single length can be used to reliably evaluate system summaries of multiple lengths. For that, we have analyzed a couple of datasets as a case study, using several variants of the ROUGE metric that are standard in summarization evaluation. Our findings indicate that the evaluation protocol in question is indeed competitive. This result paves the way to practically evaluating varying-length summaries with simple, possibly existing, summarization benchmarks.
We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an open text-based manner. We do so by consolidating OIE extractions using entity and predicate coreference, while modeling information containment between coreferring elements via lexical entailment. We suggest that generating OKR structures can be a useful step in the NLP pipeline, to give semantic applications an easy handle on consolidated information across multiple texts.
We present a novel interactive summarization system that is based on abstractive summarization, derived from a recent consolidated knowledge representation for multiple texts. We incorporate a couple of interaction mechanisms, providing a bullet-style summary while allowing to attain the most important information first and interactively drill down to more specific details. A usability study of our implementation, for event news tweets, suggests the utility of our approach for text exploration.