Of pearls and pigs : a conceptual-semantic Tiernet approach to formal representation of structure and variation of phraseological units

"Helmiä sioille", pärlor för svin, säger man på finska om någonting bra och fint som tas emot av en mottagare som inte vill eller har ingen förmåga att förstå, uppskatta eller utnyttja hela den potential som finns hos det mottagna föremålet, är ointresserad av den eller gillar den inte. För sådana relativt stabila flerordiga uttryck, som är lagrade i språkbrukarnas minnen och som demonstrerar olika slags oregelbundna drag i sin struktur använder man inom lingvistiken bl.a. termerna "idiom" eller "fraseologiska enheter". Som en oregelbundenhet kan man t.ex. beskriva det faktum att betydelsen hos uttrycket inte är densamma som man skulle komma till ifall man betraktade det som en vanlig regelbunden fras. En annan oregelbundenhet, som idiomforskare har observerat, ligger i den begränsade förmågan att varieras i form och betydelse, som många idiom har jämfört med regelbundna fraser. Därför talas det ofta om "grundform" och "grundbetydelse" hos idiom och variationen avses som avvikelse från dessa. Men när man tittar på ett stort antal förekomstexempel av idiom i språkbruk, märker man att många av dem tillåter variation, t.o.m. i sådan utsträckning att gränserna mellan en variant och en "grundform" suddas ut, och istället för ett idiom råkar vi plötsligt på en "familj" av flera besläktade uttryck. Allt detta väcker frågan om hur dessa uttryck egentligen ska vara representerade i språket. I avhandlingen utförs en kritisk granskning av olika tidigare tillvägagångssätt att beskriva fraseologiska enheter i syfte att klargöra vilka svårigheter deras struktur och variation erbjuder för den lingvistiska teorin. Samtidigt presenteras ett alternativt sätt att beskriva dessa uttryck. En systematisk och formell modell som utvecklas i denna avhandling integrerar en beskrivning av idiom på många olika språkliga nivåer och skildrar deras variation i form av ett nätverk och som ett resultat av samspel mellan idiomets struktur och kontexter där det förekommer, samt av interaktion med andra fasta uttryck. Modellen bygger på en fördjupande, språkbrukbaserad analys av det finska idiomet "X HEITTÄÄ HELMIÄ SIOILLE" (X kastar pärlor för svin).

A Dependency Parsing Approach to Biomedical Text Mining

Biomedical research is currently facing a new type of challenge: an excess of information, both in terms of raw data from experiments and in the number of scientific publications describing their results. Mirroring the focus on data mining techniques to address the issues of structured data, there has recently been great interest in the development and application of text mining techniques to make more effective use of the knowledge contained in biomedical scientific publications, accessible only in the form of natural human language. This thesis describes research done in the broader scope of projects aiming to develop methods, tools and techniques for text mining tasks in general and for the biomedical domain in particular. The work described here involves more specifically the goal of extracting information from statements concerning relations of biomedical entities, such as protein-protein interactions. The approach taken is one using full parsing—syntactic analysis of the entire structure of sentences—and machine learning, aiming to develop reliable methods that can further be generalized to apply also to other domains. The five papers at the core of this thesis describe research on a number of distinct but related topics in text mining. In the first of these studies, we assessed the applicability of two popular general English parsers to biomedical text mining and, finding their performance limited, identified several specific challenges to accurate parsing of domain text. In a follow-up study focusing on parsing issues related to specialized domain terminology, we evaluated three lexical adaptation methods. We found that the accurate resolution of unknown words can considerably improve parsing performance and introduced a domain-adapted parser that reduced the error rate of theoriginal by 10% while also roughly halving parsing time. To establish the relative merits of parsers that differ in the applied formalisms and the representation given to their syntactic analyses, we have also developed evaluation methodology, considering different approaches to establishing comparable dependency-based evaluation results. We introduced a methodology for creating highly accurate conversions between different parse representations, demonstrating the feasibility of unification of idiverse syntactic schemes under a shared, application-oriented representation. In addition to allowing formalism-neutral evaluation, we argue that such unification can also increase the value of parsers for domain text mining. As a further step in this direction, we analysed the characteristics of publicly available biomedical corpora annotated for protein-protein interactions and created tools for converting them into a shared form, thus contributing also to the unification of text mining resources. The introduced unified corpora allowed us to perform a task-oriented comparative evaluation of biomedical text mining corpora. This evaluation established clear limits on the comparability of results for text mining methods evaluated on different resources, prompting further efforts toward standardization. To support this and other research, we have also designed and annotated BioInfer, the first domain corpus of its size combining annotation of syntax and biomedical entities with a detailed annotation of their relationships. The corpus represents a major design and development effort of the research group, with manual annotation that identifies over 6000 entities, 2500 relationships and 28,000 syntactic dependencies in 1100 sentences. In addition to combining these key annotations for a single set of sentences, BioInfer was also the first domain resource to introduce a representation of entity relations that is supported by ontologies and able to capture complex, structured relationships. Part I of this thesis presents a summary of this research in the broader context of a text mining system, and Part II contains reprints of the five included publications.