The Document Set Expansion (DSE) task involves identifying relevant documents from large collections based on a limited set of example documents. Previous research has highlighted Positive and Unlabeled (PU) learning as a promising approach for this task. However, most PU methods rely on the unrealistic assumption of knowing the class prior for positive samples in the collection. To address this limitation, this paper introduces a novel PU learning framework that utilizes intractable density estimation models. Experiments conducted on PubMed and Covid datasets in a transductive setting showcase the effectiveness of the proposed method for DSE. Code is available from https://github.com/Beautifuldog01/Document-set-expansion-puDE.

Technology Assisted Review (TAR) stopping rules aim to reduce the cost of manually assessing documents for relevance by minimising the number of documents that need to be examined to ensure a desired level of recall. This paper extends an effective stopping rule using information derived from a text classifier that can be trained without the need for any additional annotation. Experiments on multiple data sets (CLEF e-Health, TREC Total Recall, TREC Legal and RCV1) showed that the proposed approach consistently improves performance and outperforms several alternative methods.

Knowledge Graph Embeddings (KGEs) have been intensively explored in recent years due to their promise for a wide range of applications. However, existing studies focus on improving the final model performance without acknowledging the computational cost of the proposed approaches, in terms of execution time and environmental impact. This paper proposes a simple yet effective KGE framework which can reduce the training time and carbon footprint by orders of magnitudes compared with state-of-the-art approaches, while producing competitive performance. We highlight three technical innovations: full batch learning via relational matrices, closed-form Orthogonal Procrustes Analysis for KGEs, and non-negative-sampling training. In addition, as the first KGE method whose entity embeddings also store full relation information, our trained models encode rich semantics and are highly interpretable. Comprehensive experiments and ablation studies involving 13 strong baselines and two standard datasets verify the effectiveness and efficiency of our algorithm.

Cross-Lingual Word Embeddings (CLWEs) encode words from two or more languages in a shared high-dimensional space in which vectors representing words with similar meaning (regardless of language) are closely located. Existing methods for building high-quality CLWEs learn mappings that minimise the ℓ2 norm loss function. However, this optimisation objective has been demonstrated to be sensitive to outliers. Based on the more robust Manhattan norm (aka. ℓ1 norm) goodness-of-fit criterion, this paper proposes a simple post-processing step to improve CLWEs. An advantage of this approach is that it is fully agnostic to the training process of the original CLWEs and can therefore be applied widely. Extensive experiments are performed involving ten diverse languages and embeddings trained on different corpora. Evaluation results based on bilingual lexicon induction and cross-lingual transfer for natural language inference tasks show that the ℓ1 refinement substantially outperforms four state-of-the-art baselines in both supervised and unsupervised settings. It is therefore recommended that this strategy be adopted as a standard for CLWE methods.

False information spread via the internet and social media influences public opinion and user activity, while generative models enable fake content to be generated faster and more cheaply than had previously been possible. In the not so distant future, identifying fake content generated by deep learning models will play a key role in protecting users from misinformation. To this end, a dataset containing human and computer-generated headlines was created and a user study indicated that humans were only able to identify the fake headlines in 47.8% of the cases. However, the most accurate automatic approach, transformers, achieved an overall accuracy of 85.7%, indicating that content generated from language models can be filtered out accurately.

It has been shown that word embeddings can exhibit gender bias, and various methods have been proposed to quantify this. However, the extent to which the methods are capturing social stereotypes inherited from the data has been debated. Bias is a complex concept and there exist multiple ways to define it. Previous work has leveraged gender word pairs to measure bias and extract biased analogies. We show that the reliance on these gendered pairs has strong limitations: bias measures based off of them are not robust and cannot identify common types of real-world bias, whilst analogies utilising them are unsuitable indicators of bias. In particular, the well-known analogy “man is to computer-programmer as woman is to homemaker” is due to word similarity rather than bias. This has important implications for work on measuring bias in embeddings and related work debiasing embeddings.

The Google Patents is one of the main important sources of patents information. A striking characteristic is that many of its abstracts are presented in more than one language, thus making it a potential source of parallel corpora. This article presents the development of a parallel corpus from the open access Google Patents dataset in 74 language pairs, comprising more than 68 million sentences and 800 million tokens. Sentences were automatically aligned using the Hunalign algorithm for the largest 22 language pairs, while the others were abstract (i.e. paragraph) aligned. We demonstrate the capabilities of our corpus by training Neural Machine Translation (NMT) models for the main 9 language pairs, with a total of 18 models. Our parallel corpus is freely available in TSV format and with a SQLite database, with complementary information regarding patent metadata.

Text retrieval systems often return large sets of documents, particularly when applied to large collections. Stopping criteria can reduce the number of these documents that need to be manually evaluated for relevance by predicting when a suitable level of recall has been achieved. In this work, a novel method for determining a stopping criterion is proposed that models the rate at which relevant documents occur using a Poisson process. This method allows a user to specify both a minimum desired level of recall to achieve and a desired probability of having achieved it. We evaluate our method on a public dataset and compare it with previous techniques for determining stopping criteria.

Topics models, such as LDA, are widely used in Natural Language Processing. Making their output interpretable is an important area of research with applications to areas such as the enhancement of exploratory search interfaces and the development of interpretable machine learning models. Conventionally, topics are represented by their n most probable words, however, these representations are often difficult for humans to interpret. This paper explores the re-ranking of topic words to generate more interpretable topic representations. A range of approaches are compared and evaluated in two experiments. The first uses crowdworkers to associate topics represented by different word rankings with related documents. The second experiment is an automatic approach based on a document retrieval task applied on multiple domains. Results in both experiments demonstrate that re-ranking words improves topic interpretability and that the most effective re-ranking schemes were those which combine information about the importance of words both within topics and their relative frequency in the entire corpus. In addition, close correlation between the results of the two evaluation approaches suggests that the automatic method proposed here could be used to evaluate re-ranking methods without the need for human judgements.

Approaches to authorship attribution, the task of identifying the author of a document, are based on analysis of individuals’ writing style and/or preferred topics. Although the problem has been widely explored, no previous studies have analysed the relationship between dataset characteristics and effectiveness of different types of features. This study carries out an analysis of four widely used datasets to explore how different types of features affect authorship attribution accuracy under varying conditions. The results of the analysis are applied to authorship attribution models based on both discrete and continuous representations. We apply the conclusions from our analysis to an extension of an existing approach to authorship attribution and outperform the prior state-of-the-art on two out of the four datasets used.

As the quantity of publications increases daily, researchers are forced to narrow their attention to their own specialism and are therefore less likely to make new connections with other areas. Literature based discovery (LBD) supports the identification of such connections. A number of LBD tools are available, however, they often suffer from limitations such as constraining possible searches or not producing results in real-time. We introduce HiDE (Hidden Discovery Explorer), an online knowledge browsing tool which allows fast access to hidden knowledge generated from all abstracts in Medline. HiDE is fast enough to allow users to explore the full range of hidden connections generated by an LBD system. The tool employs a novel combination of two approaches to LBD: a graph-based approach which allows hidden knowledge to be generated on a large scale and an inference algorithm to identify the most promising (most likely to be non trivial) information. Available at https://skye.shef.ac.uk/kdisc

This paper presents work on using continuous representations for authorship attribution. In contrast to previous work, which uses discrete feature representations, our model learns continuous representations for n-gram features via a neural network jointly with the classification layer. Experimental results demonstrate that the proposed model outperforms the state-of-the-art on two datasets, while producing comparable results on the remaining two.

Lexical knowledge bases (LKBs), such as WordNet, have been shown to be useful for a range of language processing tasks. Extending these resources is an expensive and time-consuming process. This paper describes an approach to address this problem by automatically generating a mapping from WordNet synsets to Wikipedia articles. A sample of synsets has been manually annotated with article matches for evaluation purposes. The automatic methods are shown to create mappings with precision of 87.8% and recall of 46.9%. These mappings can then be used as a basis for enriching WordNet with new relations based on Wikipedia links. The manual and automatically created data is available online.

Digitised Cultural Heritage (CH) items usually have short descriptions and lack rich contextual information. Wikipedia articles, on the contrary, include in-depth descriptions and links to related articles, which motivate the enrichment of CH items with information from Wikipedia. In this paper we explore the feasibility of finding matching articles in Wikipedia for a given Cultural Heritage item. We manually annotated a random sample of items from Europeana, and performed a qualitative and quantitative study of the issues and problems that arise, showing that each kind of CH item is different and needs a nuanced definition of what ``matching article'' means. In addition, we test a well-known wikification (aka entity linking) algorithm on the task. Our results indicate that a substantial number of items can be effectively linked to their corresponding Wikipedia article.

In natural language relationships between entities can asserted within a single sentence or over many sentences in a document. Many information extraction systems are constrained to extracting binary relations that are asserted within a single sentence (single-sentence relations) and this limits the proportion of relations they can extract since those expressed across multiple sentences (inter-sentential relations) are not considered. The analysis in this paper focuses on finding the distribution of inter-sentential and single-sentence relations in two corpora used for the evaluation of Information Extraction systems: the MUC6 corpus and the ACE corpus from 2003. In order to carry out this analysis we had to manually mark up all the management succession relations described in the MUC6 corpus. It was found that inter-sentential relations constitute 28.5% and 9.4% of the total number of relations in MUC6 and ACE03 respectively. This places upper bounds on the recall of information extraction systems that do not consider relations that are asserted across multiple sentences (71.5% and 90.6% respectively).