An evaluation of corpus-driven measures of medical concept similarity for information retrieval

Measures of semantic similarity between medical concepts are central to a number of techniques in medical informatics, including query expansion in medical information retrieval. Previous work has mainly considered thesaurus-based path measures of semantic similarity and has not compared different corpus-driven approaches in depth. We evaluate the effectiveness of eight common corpus-driven measures in capturing semantic relatedness and compare these against human judged concept pairs assessed by medical professionals. Our results show that certain corpus-driven measures correlate strongly (approx 0.8) with human judgements. An important finding is that performance was significantly affected by the choice of corpus used in priming the measure, i.e., used as evidence from which corpus-driven similarities are drawn. This paper provides guidelines for the implementation of semantic similarity measures for medical informatics and concludes with implications for medical information retrieval.

University of Glasgow at ImageCLEFPhoto 2009 : optimising similarity and diversity in image retrieval

In this paper we describe the approaches adopted to generate the runs submitted to ImageCLEFPhoto 2009 with an aim to promote document diversity in the rankings. Four of our runs are text based approaches that employ textual statistics extracted from the captions of images, i.e. MMR [1] as a state of the art method for result diversification, two approaches that combine relevance information and clustering techniques, and an instantiation of Quantum Probability Ranking Principle. The fifth run exploits visual features of the provided images to re-rank the initial results by means of Factor Analysis. The results reveal that our methods based on only text captions consistently improve the performance of the respective baselines, while the approach that combines visual features with textual statistics shows lower levels of improvements.

Similarity-based birdcall retrieval from environmental audio

Automated digital recordings are useful for large-scale temporal and spatial environmental monitoring. An important research effort has been the automated classification of calling bird species. In this paper we examine a related task, retrieval of birdcalls from a database of audio recordings, similar to a user supplied query call. Such a retrieval task can sometimes be more useful than an automated classifier. We compare three approaches to similarity-based birdcall retrieval using spectral ridge features and two kinds of gradient features, structure tensor and the histogram of oriented gradients. The retrieval accuracy of our spectral ridge method is 94% compared to 82% for the structure tensor method and 90% for the histogram of gradients method. Additionally, this approach potentially offers a more compact representation and is more computationally efficient.

Similarity metrics within a point of view

In vector space based approaches to natural language processing, similarity is commonly measured by taking the angle between two vectors representing words or documents in a semantic space. This is natural from a mathematical point of view, as the angle between unit vectors is, up to constant scaling, the only unitarily invariant metric on the unit sphere. However, similarity judgement tasks reveal that human subjects fail to produce data which satisfies the symmetry and triangle inequality requirements for a metric space. A possible conclusion, reached in particular by Tversky et al., is that some of the most basic assumptions of geometric models are unwarranted in the case of psychological similarity, a result which would impose strong limits on the validity and applicability vector space based (and hence also quantum inspired) approaches to the modelling of cognitive processes. This paper proposes a resolution to this fundamental criticism of of the applicability of vector space models of cognition. We argue that pairs of words imply a context which in turn induces a point of view, allowing a subject to estimate semantic similarity. Context is here introduced as a point of view vector (POVV) and the expected similarity is derived as a measure over the POVV's. Different pairs of words will invoke different contexts and different POVV's. Hence the triangle inequality ceases to be a valid constraint on the angles. We test the proposal on a few triples of words and outline further research.

Pairwise similarity of TopSig document signatures

This paper analyses the pairwise distances of signatures produced by the TopSig retrieval model on two document collections. The distribution of the distances are compared to purely random signatures. It explains why TopSig is only competitive with state of the art retrieval models at early precision. Only the local neighbourhood of the signatures is interpretable. We suggest this is a common property of vector space models.

Efficient top-k retrieval with signatures

This paper describes a new method of indexing and searching large binary signature collections to efficiently find similar signatures, addressing the scalability problem in signature search. Signatures offer efficient computation with acceptable measure of similarity in numerous applications. However, performing a complete search with a given search argument (a signature) requires a Hamming distance calculation against every signature in the collection. This quickly becomes excessive when dealing with large collections, presenting issues of scalability that limit their applicability. Our method efficiently finds similar signatures in very large collections, trading memory use and precision for greatly improved search speed. Experimental results demonstrate that our approach is capable of finding a set of nearest signatures to a given search argument with a high degree of speed and fidelity.

Compositional data analysis (CoDA) approaches to distance in information retrieval

Many techniques in information retrieval produce counts from a sample, and it is common to analyse these counts as proportions of the whole - term frequencies are a familiar example. Proportions carry only relative information and are not free to vary independently of one another: for the proportion of one term to increase, one or more others must decrease. These constraints are hallmarks of compositional data. While there has long been discussion in other fields of how such data should be analysed, to our knowledge, Compositional Data Analysis (CoDA) has not been considered in IR. In this work we explore compositional data in IR through the lens of distance measures, and demonstrate that common measures, naïve to compositions, have some undesirable properties which can be avoided with composition-aware measures. As a practical example, these measures are shown to improve clustering. Copyright 2014 ACM.

Medical semantic similarity with a neural language model

Advances in neural network language models have demonstrated that these models can effectively learn representations of words meaning. In this paper, we explore a variation of neural language models that can learn on concepts taken from structured ontologies and extracted from free-text, rather than directly from terms in free-text. This model is employed for the task of measuring semantic similarity between medical concepts, a task that is central to a number of techniques in medical informatics and information retrieval. The model is built with two medical corpora (journal abstracts and patient records) and empirically validated on two ground-truth datasets of human-judged concept pairs assessed by medical professionals. Empirically, our approach correlates closely with expert human assessors ($\approx$ 0.9) and outperforms a number of state-of-the-art benchmarks for medical semantic similarity. The demonstrated superiority of this model for providing an effective semantic similarity measure is promising in that this may translate into effectiveness gains for techniques in medical information retrieval and medical informatics (e.g., query expansion and literature-based discovery).

Exploiting inference from semantic annotations for information retrieval

The increasing amount of information that is annotated against standardised semantic resources offers opportunities to incorporate sophisticated levels of reasoning, or inference, into the retrieval process. In this position paper, we reflect on the need to incorporate semantic inference into retrieval (in particular for medical information retrieval) as well as previous attempts that have been made so far with mixed success. Medical information retrieval is a fertile ground for testing inference mechanisms to augment retrieval. The medical domain offers a plethora of carefully curated, structured, semantic resources, along with well established entity extraction and linking tools, and search topics that intuitively require a number of different inferential processes (e.g., conceptual similarity, conceptual implication, etc.). We argue that integrating semantic inference in information retrieval has the potential to uncover a large amount of information that otherwise would be inaccessible; but inference is also risky and, if not used cautiously, can harm retrieval.

Generalised features for bird vocalisation retrieval in acoustic recordings

Bioacoustic monitoring has become a significant research topic for species diversity conservation. Due to the development of sensing techniques, acoustic sensors are widely deployed in the field to record animal sounds over a large spatial and temporal scale. With large volumes of collected audio data, it is essential to develop semi-automatic or automatic techniques to analyse the data. This can help ecologists make decisions on how to protect and promote the species diversity. This paper presents generic features to characterize a range of bird species for vocalisation retrieval. In the implementation, audio recordings are first converted to spectrograms using short-time Fourier transform, then a ridge detection method is applied to the spectrogram for detecting points of interest. Based on the detected points, a new region representation are explored for describing various bird vocalisations and a local descriptor including temporal entropy, frequency bin entropy and histogram of counts of four ridge directions is calculated for each sub-region. To speed up the retrieval process, indexing is carried out and the retrieved results are ranked according to similarity scores. The experiment results show that our proposed feature set can achieve 0.71 in term of retrieval success rate which outperforms spectral ridge features alone (0.55) and Mel frequency cepstral coefficients (0.36).

Birdcall retrieval from environmental acoustic recordings using image processing

Acoustic recordings of the environment provide an effective means to monitor bird species diversity. To facilitate exploration of acoustic recordings, we describe a content-based birdcall retrieval algorithm. A query birdcall is a region of spectrogram bounded by frequency and time. Retrieval depends on a similarity measure derived from the orientation and distribution of spectral ridges. The spectral ridge detection method caters for a broad range of birdcall structures. In this paper, we extend previous work by incorporating a spectrogram scaling step in order to improve the detection of spectral ridges. Compared to an existing approach based on MFCC features, our feature representation achieves better retrieval performance for multiple bird species in noisy recordings.

Scalable document hashing and retrieval

This thesis studies document signatures, which are small representations of documents and other objects that can be stored compactly and compared for similarity. This research finds that document signatures can be effectively and efficiently used to both search and understand relationships between documents in large collections, scalable enough to search a billion documents in a fraction of a second. Deliverables arising from the research include an investigation of the representational capacity of document signatures, the publication of an open-source signature search platform and an approach for scaling signature retrieval to operate efficiently on collections containing hundreds of millions of documents.

Compact features for birdcall retrieval from environmental acoustic recordings

Bioacoustic data can be used for monitoring animal species diversity. The deployment of acoustic sensors enables acoustic monitoring at large temporal and spatial scales. We describe a content-based birdcall retrieval algorithm for the exploration of large data bases of acoustic recordings. In the algorithm, an event-based searching scheme and compact features are developed. In detail, ridge events are detected from audio files using event detection on spectral ridges. Then event alignment is used to search through audio files to locate candidate instances. A similarity measure is then applied to dimension-reduced spectral ridge feature vectors. The event-based searching method processes a smaller list of instances for faster retrieval. The experimental results demonstrate that our features achieve better success rate than existing methods and the feature dimension is greatly reduced.

Integrating and evaluating neural word embeddings in information retrieval

Recent advances in neural language models have contributed new methods for learning distributed vector representations of words (also called word embeddings). Two such methods are the continuous bag-of-words model and the skipgram model. These methods have been shown to produce embeddings that capture higher order relationships between words that are highly effective in natural language processing tasks involving the use of word similarity and word analogy. Despite these promising results, there has been little analysis of the use of these word embeddings for retrieval. Motivated by these observations, in this paper, we set out to determine how these word embeddings can be used within a retrieval model and what the benefit might be. To this aim, we use neural word embeddings within the well known translation language model for information retrieval. This language model captures implicit semantic relations between the words in queries and those in relevant documents, thus producing more accurate estimations of document relevance. The word embeddings used to estimate neural language models produce translations that differ from previous translation language model approaches; differences that deliver improvements in retrieval effectiveness. The models are robust to choices made in building word embeddings and, even more so, our results show that embeddings do not even need to be produced from the same corpus being used for retrieval.