David Milward

David Milward
Linguamatics an IQVIA company · R&D

PhD

About

78
Publications
10,218
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,437
Citations
Citations since 2017
1 Research Item
307 Citations
20172018201920202021202220230204060
20172018201920202021202220230204060
20172018201920202021202220230204060
20172018201920202021202220230204060

Publications

Publications (78)
Article
Comparative effectiveness research (CER) provides evidence for the relative effectiveness and risks of different treatment options and informs decisions made by healthcare providers, payers, and pharmaceutical companies. CER data come from retrospective analyses as well as prospective clinical trials. Here, we describe the development of a text-min...
Article
Full-text available
This paper describes the use of an agile text mining platform (Linguamatics' Interactive Information Extraction Platform, I2E) to extract document-level cardiac risk factors in patient records as defined in the i2b2/UTHealth 2014 Challenge. The approach uses a data-driven rule-based methodology with the addition of a simple supervised classifier. W...
Article
Full-text available
Background Synapses are fundamental components of brain circuits and are disrupted in over 100 neurological and psychiatric diseases. The synapse proteome is physically organized into multiprotein complexes and polygenic mutations converge on postsynaptic complexes in schizophrenia, autism and intellectual disability. Directly characterising human...
Conference Paper
Full-text available
Agile text mining is widely used for commercial text mining in the pharmaceutical industry. It can be applied without building an annotated training corpus, so is well-suited to novel or one-off extraction tasks. In this work we wanted to see how efficiently it could be adapted for healthcare extraction tasks such as medication extraction. The aim...
Conference Paper
The identification and normalisation of biomedical entities from the scientific literature has a long tradition and a number of challenges have contributed to the development of reliable solutions. Increasingly patient records are processed to align their content with other biomedical data resources, but this approach requires analysing documents i...
Conference Paper
Full-text available
Multilingual terminological resources can be drawn from par- allel corpora in the languages of interest, possibly exploiting machine translation solutions for term identi�cation. This main objective of the CLEF-ER challenge involves parallel corpora in English and other lan- guages. The challenge organisers have gathered and normalized documents fr...
Conference Paper
Full-text available
A number of gold standard corpora for named entity recognition are available to the public. However, the existing gold standard corpora are limited in size and semantic entity types. These usually lead to implementation of trained solutions (1) for a limited number of semantic entity types and (2) lacking in generalization capability. In order to o...
Article
Full-text available
sylvie.regnier@siege.aerospatiale.fr] 3 LRC, Dublin [reinhard.schaler@ucd.ie] 4 IBM Germany, Heidelberg [tibor.kiss@vnet.ibm.com] 5 ISSCO/ETI, Geneva [susan.armstrong|sabine.lehmann@issco.unige.ch] 6 SRI, Cambridge [david.milward@cam.sri.com] Abstract The project DiET is developing a comprehensive environment for the construction, annotation and ma...
Article
Full-text available
Background: Competitions in text mining have been used to measure the performance of automatic text processing solutions against a manually annotated gold standard corpus (GSC). The preparation of the GSC is time-consuming and costly and the final corpus consists at the most of a few thousand documents annotated with a limited set of semantic grou...
Article
Full-text available
Biological systems are inherently complex. Experimental results, especially if they cover multiple experimental modalities or diverse biological responses, are difficult to interpret out of context. This is a key area for the application of semantic technologies. Extensible semantic standards such as RDF, N3 and OWL are used to create coherent, dyn...
Conference Paper
Background / Purpose: The biomedical text mining community is using annotated corpora to improve their information extraction solutions. The lack of large-scale annotated corpora is one part of the problem and the lack of annotations for different semantic types in the same set of documents is another problem. CALBC is a support action project, w...
Article
Full-text available
The CALBC initiative aims to provide a large-scale biomedical text corpus that contains semantic annotations for named entities of different kinds. The generation of this corpus requires that the annotations from different automatic annotation systems be harmonized. In the first phase, the annotation systems from five participants (EMBL-EBI, EMC Ro...
Conference Paper
Full-text available
This paper describes recent approaches using text-mining to automat- ically profile and extract arguments from legal cases. We outline some of the background context and motivations. We then turn to consider issues related to the construction and composition of a corpora of legal cases. We show how a Context-Free Grammar can be used to extract argu...
Article
In a typical task oriented dialogue system, the interpretation task consists of mapping from the acoustic input to a series of moves. In the simplest cases each move is just a pairing of slots and values e.g. "destination = paris". In this paper we will describe a system for language interpretation which is designed to work with lattice based outpu...
Article
Natural language processing (NLP) technology can be used to rapidly extract protein–protein interactions from large collections of published literature. In this chapter we will work through a case study using MEDLINE® biomedical abstracts (1) to find how a specific set of 50 genes interact with each other. We will show what steps are required to ac...
Conference Paper
Interactive Information Extraction brings together search and information extraction to provide fast, interactive text mining over large volumes of text such as Medline abstracts, full text scientific articles, patents etc. As well as covering the two ends of the spectrum: keyword search over documents, and detailed linguistic patterns within sente...
Article
Full-text available
The two text mining strategies: finding co-occurrences of biological entities within documents, and finding relation- ships using Natural Language Processing, are often seen as competitors. Here we adopt a flexible approach where the tech- niques are adapted and combined to suit the nature of the document corpus, and the specific task. The approach...
Article
Full-text available
Over recent years, there has been a growing interest in extracting information automatically or semi-automatically from the scientific literature. This paper describes a novel ontology-based interactive information extraction (OBIIE) framework and a specific OBIIE system. We describe how this system enables life scientists to make ad hoc queries si...
Conference Paper
Full-text available
This paper investigates the use of abstract task specifications for dialogue man- agement in the medical domain. In most current dialogue systems, possible in- teractions with the system are hand-coded in the design. This is an expensive process, especially for complex dialogues. This paper motivates the use of a task description language for build...
Article
Full-text available
It therefore seems necessary to integrate technologies such as medical guidelines and advice systems directly with the dialogue system so that dialogues can be generated automatically to reflect user behaviour and changes in clinical context. 2 Solution Cancer Research UK (CR-UK) has developed a dialogue system (Beveridge and Milward, 2003a; Beveri...
Conference Paper
Full-text available
A major limiting factor in the acceptability of interactive guideline and decision support systems is the case of use of the system in the clinic. A way to reduce demands upon users and increase flexibility of the interface is to use natural language dialogues and speech based interfaces. This paper describes a voice-based data capture and decision...
Article
Task Specification As stated above, one of the aims of this work is to investigate use of an ATS to exploit existing knowledge representation schemas used in medicine, as a basis for generating a dialogue specification automatically. In order to support flexible dialogue, the ATS must provide information of two functional types: information on what...
Article
Full-text available
This paper describes an interactive graphical environment for computational semantics. The system provides a teaching tool, a stand alone extendible grapher, and a library of algorithms together with test suites. The teaching tool allows users to work step by step through derivations of semantic representations, and to compare the proper- ties of v...
Article
Full-text available
The paper describes two cquiwdeut grannnatical for. malisnq. The first is a lcxicalised version of dcpen dency grammar, and tills can be nsed to provide tree-structured analyses of sentences (thongh somewhat flatter thaa those usually provided hy phrase structure grammars). 'Fhc second is a new formal ism, 'Dynamic Dcpeudency Grammar', which ascs a...
Article
Why shonld computers interpret lauguagc incrementally ? In recent years psycholinguistic evidence for ineremental interpretation has bCCOlne more and more compelling, suggesting that hnmans perform semantic interpretation before constituent boundaries, possibly word by word. However, possible computational ap plications have received less attentiou...
Article
Full-text available
This paper describes a system which en-' ables users to create on-the-fly queries which involve not just keywords, but also sortal constraints and linguistic constralnts.
Article
A syntax tree or standard selnantic representation can be represented as a set of indexed constraints. This paper describes how this idea can be used in task oriented dialogue systelns to provide interpretation rules which incorporate structural and contextual constraints where avail- able, and degrade gracefully on ungralnlnatical input.
Article
Full-text available
ast of Munich and is just a short trip away from the famous Neuschwanstein castle. Originally built as a Benedictine cloister in the early 18 th centur y, the monastery complex, which also comp rises a wonderful baroque church and a brewery, is now run as a conference hotel, and p rovided the perfect setting for the ISCA Tutorial and Workshop on `M...
Article
Full-text available
The paper describes a parser for Categorial Grammar which provides fully word by word incremental interpretation. The parser does not require fragments of sen- tences to form constituents, and thereby avoids problems of spurious ambiguity. The paper includes a brief discussion of the relationship between basic Catego- rial Grammar and other formali...
Article
Full-text available
Previous work has demonstrated the success of statistical language models when enough training data is available [1], but despite that, grammar-based systems are proving the preferred choice in successful commercial systems such as HeyAnita [2], BeVocal [3] and Tellme [4], largely due to the difficulty involved in obtaining a corpus of training dat...
Article
A syntax tree or standard semantic representation can be represented as a set of indexed constraints. This paper describes how this idea can be used in task oriented dialogue systems to provide interpretation rules which incorporate structural and contextual constraints where available, and degrade gracefully on ungrammatical input. 1
Article
Full-text available
This paper motivates the use of Information Extraction (IE) for gathering data on protein interactions, describes the customisation of an existing IE system, SRI's Highlight, for this task and presents the results of an experimenton unseen Medline abstracts which show that customisation to a new domain can be fast, reliable and cost-effective. 1 In...
Article
Full-text available
A syntax tree or standard semantic representation can be represented as a set of indexed constraints. This paper describes how this idea can be used in task oriented dialogue systems to provide interpretation rules which incorporate structural and contextual constraints where available, and degrade gracefully on ungrammatical input. 1 Introduction...
Article
Full-text available
This paper discusses some of the implicit assumptions made by shallow and deep processing approaches, and advocates a new approach which keeps the robustness of shallow or keyword-based approaches, whilst retaining the generality and formal nature of a full semantics.
Article
Full-text available
This paper describes the implementation of an interface which allows runtime queries from a PATR-II grammar to a precompiled DATR lexicon during the parse of a sentence. The lexical information requested by the PATR system is then unified to the PATR parse tree. Alternatively, there is the option to create all the possible dictionary entries from a...
Article
This paper motivates the use of Information Extraction (IE) for gathering data on protein interactions, describes the customization of an existing IE system, SRI's Highlight, for this task and presents the results of an experiment on unseen Medline abstracts which show that customization to a new domain can be fast, reliable and cost-effective.
Article
Full-text available
1 This paper provides an account of definite and pronominal anaphora which draws together insights from dynamic semantics and situation semantics. The result is a dynamic semantics in which contexts consist of the parts of a scenario which have been brought to a hearer's attention. The contexts are structured by meta-level disjunction, correspondin...
Article
This paper describes an interactive graphical environment for computational semantics. The system provides a teaching tool, a stand alone extendible grapher, and a library of algorithms together with test suites. The teaching tool allows users to work step by step through derivations of semantic representations, and to compare the properties of var...
Article
Full-text available
Why should computers interpret language incrementally ? In recent years psycholinguistic evidence for incremental interpretation has become more and more compelling, suggesting that humans perform semantic interpretation before constituent boundaries, possibly word by word. However, possible computational applications have received less attention....
Article
Full-text available
Despite the large amount of theoretical work done on non-constituent coordination during the last two decades, many computational systems still treat coordination using adapted parsing strategies, in a similar fashion to the SYSCONJ system developed for ATNs. This paper reviews the theoretical literature, and shows why many of the theoretical accou...
Article
Full-text available
The CLEARS (Computational Linguistics Education and Research for Semantics) tool provides a graphical interface allowing interactive construction of semantic representations in a variety of different formalisms, and using several construction methods. CLEARS was developed as part of the FraCaS project which was designed to encourage convergence bet...
Article
Full-text available
Experimental evidence demonstrates that understanding begins before the end of a sentence. This presumably means that some proposition based on what is heard is integrated with contextually relevant propositions drawn from general knowledge. However, formal treatments of the semantics of natural language do not typically give fragments a propositio...
Article
Full-text available
There are two major levels of processing that are significant in the use of a computational semantic framework: semantic composition for the construction of meanings; and inference either for the exploitation of those meanings, or to assist in determining contextually sensitive aspects of meaning. The first chapter of this deliverable outlines the...
Article
In this document we discuss and evaluate some relevant recent research which aims at providing strategies for a general framework for computational semantics. The approaches considered can be broadly classified into three groups: operators, formal specification and semantic metatheory. Chapter 1 Operators 1.1 Introduction Briefly and informally the...
Article
Full-text available
In this document we outline what is meant by a framework for computational semantics and describe three possible approaches: a logical approach, a conceptual approach and a toolbox approach. Various examples of the approaches are given. For the logical approach we describe a way towards providing a unification of various dynamic semantics. For the...
Conference Paper
This paper describes an interactive graphical environment for computational semantics. The system provides a teaching tool, a stand alone extendible grapher, and a library of algorithms together with test suites. The teaching tool allows users to work step by step through derivations of semantic representations, and to compare the properties of var...
Article
Full-text available
The paper describes two equivalent grammatical formalisms. The first is a lexicalised version of dependency grammar, and this can be used to provide tree-structured analyses of sentences (though somewhat flatter than those usually provided by phrase structure grammars). The second is a new formalism, `Dynamic Dependency Grammar', which uses axioms...
Article
1. INTRODUCTION Dynamics is the formal study of systems involving states and transitions between states. A natural application of dynamics is to the study of language processing, where words or morphemes can be thought of as actions which perform transitions between states of the language processor. The paper concentrates on sentence as opposed to...
Conference Paper
Full-text available
For some time there has been interest in the idea of parsing as deduction. Here we present a grammatical formalism, 'Axiomatic Grammar', which is based upon a small number of linguistically motivated axioms and deduction rules. Each axion or rule combines a 'category' with a string of words to form a further category. This contrasts with the usual...
Article
Full-text available
In this paper we will consider relatively simple dialogues, but in domains which involve multiple tasks and services, and concepts of different granularity. We re-examine the notion of focus of attention, and show how ontological information combined with information states can shed new light on the distinctions be-tween linguistic and intentional...
Article
Full-text available
This paper examines how far it is possible to replace hand crafted dialogue design with a combination of generic dialogue system components and ontological domain knowledge. Two case studies are presented, one for dialogue-based breast cancer referrals, the other for control of networked home appliances.

Network

Cited By