Question Answering (QA) is a growing area of research, often used to facilitate the extraction of information from within documents. State-of-the-art QA models are usually pre-trained on domain-general corpora like Wikipedia and thus tend to struggle on out-of-domain documents without fine-tuning. We demonstrate that synthetic domain-specific datasets can be generated easily using domain-general models, while still providing significant improvements to QA performance. We present two new tools for this task: A flexible pipeline for validating the synthetic QA data and training down stream models on it, and an online interface to facilitate human annotation of this generated data. Using this interface, crowdworkers labelled 1117 synthetic QA pairs, which we then used to fine-tune downstream models and improve domain-specific QA performance by 8.75 F1.

Cross-document co-reference resolution (CDCR) is the task of identifying and linking mentions to entities and concepts across many text documents. Current state-of-the-art models for this task assume that all documents are of the same type (e.g. news articles) or fall under the same theme. However, it is also desirable to perform CDCR across different domains (type or theme). A particular use case we focus on in this paper is the resolution of entities mentioned across scientific work and newspaper articles that discuss them. Identifying the same entities and corresponding concepts in both scientific articles and news can help scientists understand how their work is represented in mainstream media. We propose a new task and English language dataset for cross-document cross-domain co-reference resolution (CDˆ2CR). The task aims to identify links between entities across heterogeneous document types. We show that in this cross-domain, cross-document setting, existing CDCR models do not perform well and we provide a baseline model that outperforms current state-of-the-art CDCR models on CDˆ2CR. Our data set, annotation tool and guidelines as well as our model for cross-document cross-domain co-reference are all supplied as open access open source resources.

Being able to reliably link scientific works to the newspaper articles that discuss them could provide a breakthrough in the way we rationalise and measure the impact of science on our society. Linking these articles is challenging because the language used in the two domains is very different, and the gathering of online resources to align the two is a substantial information retrieval endeavour. We present HarriGT, a semi-automated tool for building corpora of news articles linked to the scientific papers that they discuss. Our aim is to facilitate future development of information-retrieval tools for newspaper/scientific work citation linking. HarriGT retrieves newspaper articles from an archive containing 17 years of UK web content. It also integrates with 3 large external citation networks, leveraging named entity extraction, and document classification to surface relevant examples of scientific literature to the user. We also provide a tuned candidate ranking algorithm to highlight potential links between scientific papers and newspaper articles to the user, in order of likelihood. HarriGT is provided as an open source tool (http://harrigt.xyz).

The task of recommending relevant scientific literature for a draft academic paper has recently received significant interest. In our effort to ease the discovery of scientific literature and augment scientific writing, we aim to improve the relevance of results based on a shallow semantic analysis of the source document and the potential documents to recommend. We investigate the utility of automatic argumentative and rhetorical annotation of documents for this purpose. Specifically, we integrate automatic Core Scientific Concepts (CoreSC) classification into a prototype context-based citation recommendation system and investigate its usefulness to the task. We frame citation recommendation as an information retrieval task and we use the categories of the annotation schemes to apply different weights to the similarity formula. Our results show interesting and consistent correlations between the type of citation and the type of sentence containing the relevant information.

With the constant growth of the scientific literature, automated processes to enable access to its contents are increasingly in demand. Several functional discourse annotation schemes have been proposed to facilitate information extraction and summarisation from scientific articles, the most well known being argumentative zoning. Core Scientific concepts (CoreSC) is a three layered fine-grained annotation scheme providing content-based annotations at the sentence level and has been used to index, extract and summarise scientific publications in the biomedical literature. A previously developed CoreSC corpus on which existing automated tools have been trained contains a single annotation for each sentence. However, it is the case that more than one CoreSC concept can appear in the same sentence. Here, we present the Multi-CoreSC CRA corpus, a text corpus specific to the domain of cancer risk assessment (CRA), consisting of 50 full text papers, each of which contains sentences annotated with one or more CoreSCs. The full text papers have been annotated by three biology experts. We present several inter-annotator agreement measures appropriate for multi-label annotation assessment. Employing several inter-annotator agreement measures, we were able to identify the most reliable annotator and we built a harmonised consensus (gold standard) from the three different annotators, while also taking concept priority (as specified in the guidelines) into account. We also show that the new Multi-CoreSC CRA corpus allows us to improve performance in the recognition of CoreSCs. The updated guidelines, the multi-label CoreSC CRA corpus and other relevant, related materials are available at the time of publication at http://www.sapientaproject.com/.