Bevan Koopman

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.

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 (≈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).

Towards semantic search and inference in electronic medical records: An approach using concept-­based information retrieval

BACKGROUND This paper presents a novel approach to searching electronic medical records that is based on concept matching rather than keyword matching. AIM The concept-based approach is intended to overcome specific challenges we identified in searching medical records. METHOD Queries and documents were transformed from their term-based originals into medical concepts as defined by the SNOMED-CT ontology. RESULTS Evaluation on a real-world collection of medical records showed our concept-based approach outperformed a keyword baseline by 25% in Mean Average Precision. CONCLUSION The concept-based approach provides a framework for further development of inference based search systems for dealing with medical data.

Automatic ICD-10 classification of cancers from free-text death certificates.

OBJECTIVE Death certificates provide an invaluable source for cancer mortality statistics; however, this value can only be realised if accurate, quantitative data can be extracted from certificates--an aim hampered by both the volume and variable nature of certificates written in natural language. This paper proposes an automatic classification system for identifying cancer related causes of death from death certificates. METHODS Detailed features, including terms, n-grams and SNOMED CT concepts were extracted from a collection of 447,336 death certificates. These features were used to train Support Vector Machine classifiers (one classifier for each cancer type). The classifiers were deployed in a cascaded architecture: the first level identified the presence of cancer (i.e., binary cancer/nocancer) and the second level identified the type of cancer (according to the ICD-10 classification system). A held-out test set was used to evaluate the effectiveness of the classifiers according to precision, recall and F-measure. In addition, detailed feature analysis was performed to reveal the characteristics of a successful cancer classification model. RESULTS The system was highly effective at identifying cancer as the underlying cause of death (F-measure 0.94). The system was also effective at determining the type of cancer for common cancers (F-measure 0.7). Rare cancers, for which there was little training data, were difficult to classify accurately (F-measure 0.12). Factors influencing performance were the amount of training data and certain ambiguous cancers (e.g., those in the stomach region). The feature analysis revealed a combination of features were important for cancer type classification, with SNOMED CT concept and oncology specific morphology features proving the most valuable. CONCLUSION The system proposed in this study provides automatic identification and characterisation of cancers from large collections of free-text death certificates. This allows organisations such as Cancer Registries to monitor and report on cancer mortality in a timely and accurate manner. In addition, the methods and findings are generally applicable beyond cancer classification and to other sources of medical text besides death certificates.

Information retrieval as semantic inference: a Graph Inference model applied to medical search

This paper presents a Graph Inference retrieval model that integrates structured knowledge resources, statistical information retrieval methods and inference in a unified framework. Key components of the model are a graph-based representation of the corpus and retrieval driven by an inference mechanism achieved as a traversal over the graph. The model is proposed to tackle the semantic gap problem—the mismatch between the raw data and the way a human being interprets it. We break down the semantic gap problem into five core issues, each requiring a specific type of inference in order to be overcome. Our model and evaluation is applied to the medical domain because search within this domain is particularly challenging and, as we show, often requires inference. In addition, this domain features both structured knowledge resources as well as unstructured text. Our evaluation shows that inference can be effective, retrieving many new relevant documents that are not retrieved by state-of-the-art information retrieval models. We show that many retrieved documents were not pooled by keyword-based search methods, prompting us to perform additional relevance assessment on these new documents. A third of the newly retrieved documents judged were found to be relevant. Our analysis provides a thorough understanding of when and how to apply inference for retrieval, including a categorisation of queries according to the effect of inference. The inference mechanism promoted recall by retrieving new relevant documents not found by previous keyword-based approaches. In addition, it promoted precision by an effective reranking of documents. When inference is used, performance gains can generally be expected on hard queries. However, inference should not be applied universally: for easy, unambiguous queries and queries with few relevant documents, inference did adversely affect effectiveness. These conclusions reflect the fact that for retrieval as inference to be effective, a careful balancing act is involved. Finally, although the Graph Inference model is developed and applied to medical search, it is a general retrieval model applicable to other areas such as web search, where an emerging research trend is to utilise structured knowledge resources for more effective semantic search.

Relevation!: An open source system for information retrieval relevance assessment

Relevation! is a system for performing relevance judgements for information retrieval evaluation. Relevation! is web-based, fully configurable and expandable; it allows researchers to effectively collect assessments and additional qualitative data. The system is easily deployed allowing assessors to smoothly perform their relevance judging tasks, even remotely. Relevation! is available as an open source project at: http://ielab.github.io/relevation.

Graph-based concept weighting for medical information retrieval

This paper presents a graph-based method to weight medical concepts in documents for the purposes of information retrieval. Medical concepts are extracted from free-text documents using a state-of-the-art technique that maps n-grams to concepts from the SNOMED CT medical ontology. In our graph-based concept representation, concepts are vertices in a graph built from a document, edges represent associations between concepts. This representation naturally captures dependencies between concepts, an important requirement for interpreting medical text, and a feature lacking in bag-of-words representations. We apply existing graph-based term weighting methods to weight medical concepts. Using concepts rather than terms addresses vocabulary mismatch as well as encapsulates terms belonging to a single medical entity into a single concept. In addition, we further extend previous graph-based approaches by injecting domain knowledge that estimates the importance of a concept within the global medical domain. Retrieval experiments on the TREC Medical Records collection show our method outperforms both term and concept baselines. More generally, this work provides a means of integrating background knowledge contained in medical ontologies into data-driven information retrieval approaches.

Evaluating medical information retrieval

This paper presents a framework for evaluating information retrieval of medical records. We use the BLULab corpus, a large collection of real-world de-identified medical records. The collection has been hand coded by clinical terminologists using the ICD-9 medical classification system. The ICD codes are used to devise queries and relevance judgements for this collection. Results of initial test runs using a baseline IR system show that there is room for improvement in medical information retrieval. Queries and relevance judgements are made available at http://aehrc.com/med_eval

Diagnose This If You Can

An increasing amount of people seek health advice on the web using search engines; this poses challenging problems for current search technologies. In this paper we report an initial study of the effectiveness of current search engines in retrieving relevant information for diagnostic medical circumlocutory queries, i.e., queries that are issued by people seeking information about their health condition using a description of the symptoms they observes (e.g. hives all over body) rather than the medical term (e.g. urticaria). This type of queries frequently happens when people are unfamiliar with a domain or language and they are common among health information seekers attempting to self-diagnose or self-treat themselves. Our analysis reveals that current search engines are not equipped to effectively satisfy such information needs; this can have potential harmful outcomes on people’s health. Our results advocate for more research in developing information retrieval methods to support such complex information needs.

The Impact of Fixed-Cost Pooling Strategies on Test Collection Bias

In Information Retrieval, test collections are usually built using the pooling method. Many pooling strategies have been developed for the pooling method. Herein, we address the question of identifying the best pooling strategy when evaluating systems using precision-oriented measures in presence of budget constraints on the number of documents to be evaluated. As a quality measurement we use the bias introduced by the pooling strategy, measured both in terms of Mean Absolute Error of the scores and in terms of ranking errors. Based on experiments on 15 test collections, we conclude that, for precision-oriented measures, the best strategies are based on Rank-Biased Precision (RBP). These results can inform collection builders because they suggest that, under fixed assessment budget constraints, RBP-based sampling produces less biased pools than other alternatives.