Aspect-based Document Similarity for Research Papers

Ostendorff, Malte; Ruas, Terry; Blume, Till; Gipp, Béla; Rehm, Georg

doi:10.18653/v1/2020.coling-main.545

Cited by 21 publications

(42 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Section titles exist in particular in long documents like scientific papers. They usually imply the section content and describe the common topic for its sub-sentences (Ostendorff et al, 2020). In our work, we propose to utilize the corresponding section title as an additional HiStruct information when encoding its sub-sentences.…”

Section: Hierarchical Structure Informationmentioning

confidence: 99%

HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information

Ruan¹,

Ostendorff²,

Rehm³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Transformer-based language models usually treat texts as linear sequences. However, most texts also have an inherent hierarchical structure, i. e., parts of a text can be identified using their position in this hierarchy. In addition, section titles usually indicate the common topic of their respective sentences. We propose a novel approach to formulate, extract, encode and inject hierarchical structure information explicitly into an extractive summarization model based on a pre-trained, encoder-only Transformer language model (HiStruct+ model), which improves SOTA ROUGEs for extractive summarization on PubMed and arXiv substantially. Using various experimental settings on three datasets (i. e., CNN/DailyMail, PubMed and arXiv), our HiStruct+ model outperforms a strong baseline collectively, which differs from our model only in that the hierarchical structure information is not injected. It is also observed that the more conspicuous hierarchical structure the dataset has, the larger improvements our method gains. The ablation study demonstrates that the hierarchical position information is the main contributor to our model's SOTA performance.

show abstract

Section: Hierarchical Structure Informationmentioning

confidence: 99%

HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information

Ruan¹,

Ostendorff²,

Rehm³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite this wide applicability of the problem, and a range of proposed approaches, evaluation of these retrieval/similarity methods remains a problem. A broad set of approaches evaluate systems against citations or combine citation information with other incidental information such as section headers as a means to determine citation intents [36]. Incidental sources of information such as section headers tend to represent approximate signals of citation intent [19,Sec 4], which may be useful for building systems.…”

Section: Query Titlementioning

confidence: 99%

CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example

Mysore¹,

O'Gorman²,

McCallum³

et al. 2021

Preprint

View full text Add to dashboard Cite

Query by Example is a well-known information retrieval task in which a document is chosen by the user as the search query and the goal is to retrieve relevant documents from a large collection. However, a document often covers multiple aspects of a topic. To address this scenario we introduce the task of faceted Query by Example in which users can also specify a finer grained aspect in addition to the input query document. We focus on the application of this task in scientific literature search. We envision models which are able to retrieve scientific papers analogous to a query scientific paper along specifically chosen rhetorical structure elements as one solution to this problem. In this work, the rhetorical structure elements, which we refer to as facets, indicate "background", "method", or "result" aspects of a scientific paper. We introduce and describe an expert annotated test collection to evaluate models trained to perform this task. Our test collection consists of a diverse set of 50 query documents, drawn from computational linguistics and machine learning venues. We carefully followed the annotation guideline used by TREC for depth-k pooling (k = 100 or 250) and the resulting data collection consists of graded relevance scores with high annotation agreement. The data is freely available for research purposes.

show abstract

“…Domain-specific models build on top of Transformers typically outperform their baselines for related tasks [12]. For example, SciBERT [2] was pre-trained on scientific documents and typically outperforms BERT for scientific NLP tasks, such as determining document similarity [22].…”

Section: Related Workmentioning

confidence: 99%

“…Intermediate Pre-Trained. SciBERT [2] optimizes the MLM for 1.14M randomly selected papers from Semantic Scholar 22 . BioClinicalBERT [1] specializes on 2M notes in the MIMIC-III database [13], a collection of disidentified clinical data.…”

Section: A2 Model Detailsmentioning

confidence: 99%

Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection

Wahle,

Ashok,

Ruas

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for flagging online misinformation related to COVID-19. However, these methods predominantly target specific content types (e.g., news) or platforms (e.g., Twitter). The methods' capabilities to generalize were largely unclear so far. We evaluate fifteen Transformer-based models on five COVID-19 misinformation datasets that include social media posts, news articles, and scientific papers to fill this gap. We show tokenizers and models tailored to COVID-19 data do not provide a significant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems.

show abstract

Aspect-based Document Similarity for Research Papers

Cited by 21 publications

References 33 publications

HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information

HiStruct+: Improving Extractive Text Summarization with Hierarchical Structure Information

CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example

Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection

Contact Info

Product

Resources

About