A High-Quality Gold Standard for Citation-based Tasks (L18-1)

Copied to clipboard

Challenge: Citation recommendation tasks involve recommending citations within their specific contexts.
Approach: They propose to use arXiv.org's citation-dependent evaluation data set to evaluate citations . their data set is characterized by the fact that it exhibits almost zero noise in its extracted content .
Outcome: The proposed data set exhibits almost zero noise in extracted content and all citations are linked to their correct publications.

Similar Papers

Towards a Gold Standard Corpus for Variable Detection and Linking in Social Science Publications (L18-1)

Copied to clipboard

Challenge: a new corpus for detecting and linking survey variables is being developed . the corpus is multilingual and includes manually curated word and phrase alignments .
Approach: They propose to create a corpus for the evaluation of detecting and linking survey variables in social science publications.
Outcome: The proposed corpus is the first gold standard for the variable detection and linking task.
A Multi-level Annotated Corpus of Scientific Papers for Scientific Document Summarization and Cross-document Relation Discovery (2020.lrec-1)

Copied to clipboard

Challenge: Recent studies have proposed to take advantage of the scientific paper's citation network to approach literature summarization.
Approach: They propose to annotate related work sections, cite papers and sentences using machine readable data and an additional layer of papers citing the references.
Outcome: The proposed corpus expands the existing data-set of related work sections and cites the papers cited in the related work section.
CiteSum: Citation Text-guided Scientific Extreme Summarization and Domain Adaptation with Limited Supervision (2022.emnlp-main)

Copied to clipboard

Challenge: Scientific extreme summarization (TLDR) aims to form ultra-short summaries of scientific papers . previous attempts failed to scale up due to heavy human annotation and domain expertise .
Approach: They propose a method to automatically extract TLDR summaries from scientific papers . they propose 'citeSum' with no human annotation, which is 30 times larger than SciTLDR .
Outcome: The proposed approach outperforms most fully-supervised methods on SciTLDR without fine-tuning and achieves state-of-the-art results with only 128 examples.
TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics (2021.eacl-main)

Copied to clipboard

Challenge: Recent efforts to extract tasks, datasets and evaluation metrics from scientific literature focus on abstracts only.
Approach: They propose a corpus that contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities extracted from NLP papers.
Outcome: The proposed corpus contains domain expert annotations for Task (T), Dataset (D), Metric (M) entities extracted from NLP papers.
A Fair and In-Depth Evaluation of Existing End-to-End Entity Linking Systems (2023.emnlp-main)

Copied to clipboard

Challenge: Existing evaluations of entity linking systems often lack detailed error analysis or a closer look at the results.
Approach: They evaluate existing entity linking systems and propose two new benchmarks . they characterize their strengths and weaknesses and report on reproducibility aspects .
Outcome: The evaluations of existing system have strong biases and artifacts . they characterize their strengths and weaknesses and report on reproducibility aspects .
Boosting Entity Linking Performance by Leveraging Unlabeled Documents (P19-1)

Copied to clipboard

Challenge: a new approach to entity linking relies on unlabeled documents and Wikipedia . a supervised approach uses only natural information, such as unlabed documents .
Approach: They propose a method which exploits only naturally occurring information . they construct a high recall list of candidate entities for each mention in an unlabeled document .
Outcome: The proposed model outperforms fully-supervised state-of-the-art systems on standard test sets.
Scientific Statement Classification over arXiv.org (2020.lrec-1)

Copied to clipboard

Challenge: a dataset of 1.2 million documents converted from the original submissions is available for supervised learning.
Approach: They propose a new classification task for scientific statements and a large-scale dataset for supervised learning.
Outcome: The proposed task achieves a 0.91 F1 score and a lexeme serialization for mathematical formulas.
Dataset Construction for Scientific-Document Writing Support by Extracting Related Work Section and Citations from PDF Papers (2022.lrec-1)

Copied to clipboard

Challenge: To augment datasets used for scientific-document writing support research, we extract texts from “Related Work” sections and citation information in PDF-formatted papers published in English.
Approach: They propose to extract text from “Related Work” sections and citation information from PDF-formatted papers published in English.
Outcome: The proposed dataset is based on a previously constructed dataset using only Tex papers and is compared with the existing one.
The STEM-ECR Dataset: Grounding Scientific Entity References in STEM Scholarly Content to Authoritative Encyclopedic and Lexicographic Sources (2020.lrec-1)

Copied to clipboard

Challenge: a dataset for scientific entity extraction, classification, and resolution has been developed . a generic conceptual formalism for scientific entities is feasible, the authors say .
Approach: They propose a STEM-ECR dataset that provides a domain-independent benchmark for scientific entity extraction, classification, and resolution tasks.
Outcome: The proposed dataset provides a benchmark for evaluation of scientific entity extraction, classification, and resolution tasks in a domain-independent fashion.
CitationIE: Leveraging the Citation Graph for Scientific Information Extraction (2021.acl-long)

Copied to clipboard

Challenge: Existing work on scientific information extraction (SciIE) considers extraction solely based on the content of an individual paper, without considering the paper’s place in the broader literature.
Approach: They propose to automate the extraction of key information from scientific documents by leveraging a complementary source: the citation graph of referential links between citing and cited papers.
Outcome: The proposed model improves on a set of English-language scientific documents.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations