BibSonomy publications for /user/diego_ma/molla_publicationWed Nov 16 08:49:50 CET 2011Proceedings ALTA 2011Development of a Corpus for Evidence Based Medicine Summarisation2011corpus biomedical molla_publication In this paper we introduce some of the key NLP-related problems related to the practice of Evidence Based Medicine and propose the task of multi-document query-focused summarisation as a key approach to solve these problems. We have completed a corpus for the development of such multi-document query-focused summarisation task. The process to build the corpus combined the use of automated extraction of text, manual annotation, and crowdsourcing to find the reference IDs. We perform a statistical analysis of the corpus for the particular use of single-document summarisation and show that there is still a lot of room for improvement from the current baselines.Wed Jan 19 05:42:18 CET 2011Proceedings of the Australasian Language Technology Workshop76-80A Corpus for Evidence Based Medicine Summarisation82010molla_medicalnlp corpora summarisation molla_publication In this paper we motivate the need for a corpus for the development and testing of summarisation systems for evidence-based medicine. We describe the corpus which we are currently creating, and show its applicability by evaluating several simple query-based summarisation techniques using a small fragment of the corpus.Wed Jan 19 05:38:34 CET 2011Proceedings of the Fifteenth Australasian Document Computing SymposiumA Rule-based Approach for Automatic Identification of Publication Types of Medical Papers2010molla_medicalnlp text_categorisation biomedical molla_publication The medical domain has an abundance of textual resources of varying quality. The quality of medical articles depends largely on their publication types. However, identifying high-quality medical articles from search results is till date a manual and time-consuming process. We present a simple, rule-based, post-retrieval approach to automatically identify medical articles belonging to three high-quality publication types. Our approach simply uses title and abstract information of the articles to perform this. Our experiments show that such a rule-based approach has close to 100% precision and recall for the three publication types.Wed Feb 03 05:18:03 CET 2010Proceedings HIKM 2010A Study on the Use of Search Engines for Answering Clinical Questions2010molla_medicalnlp search inf-retr question_answering biomedical molla_publication This paper describes an evaluation of the answerability of a set of clinical questions posed by physicians. The clinical questions belong to two categories of the five-leaf high-level hierarchical Evidence Taxonomy created by Ely and his colleagues: Intervention and Non Intervention. The questions are passed to two search engines (PubMed, Google), two question-answering systems (MedQA, Answers.com's BrainBoost), and a dictionary (OneLook) for locating the answers to the question corpus. The output of the systems is judged by a human and scored according to the Mean Reciprocal Rank (MRR). The results show the need for question modification and analyse the impact of specific types of modifications. The results also show that No Intervention questions are easier to answer than Intervention questions. Further, generic search engines like Google obtain higher MRR than specialised systems and even higher than a version of Google based on specialised literature (PubMed) only. In addition, an analysis of the location of the answer in the returned documents is provided.Fri Oct 10 05:18:00 CEST 2008Proceedings ALTW 200651-58Named Entity Recognition for Question Answering2006named_entities AnswerFinder molla_publication Current text-based question answering (QA) systems usually contain a named entity recogniser (NER) as a core component. Named entity recognition as traditionally been developed as a component for information extraction systems, and current techniques are focused on this end use. However, no formal assessment has been done on the characteristics of a NER within the task of question answering. In this paper we present a NER that aims at higher recall by allowing multiple entity labels to strings. The NER is embedded in a question answering system and the overall QA system performance is compared to that of one with a traditional variation of the NER that only allows single entity labels. It is shown that the added noise produced introduced by the additional labels is offset by the higher recall gained, therefore enabling the QA system to have a better chance to find the answer.Tue Jul 01 10:45:03 CEST 2008Proc. COLING Workshop on Information Retrieval for Question Answering8 pagesIndexing on Semantic Roles for Question Answering2008question_answering molla_publication AnswerFinder inf_retrieval Semantic Role Labeling (SRL) has been used successfully in several stages of automated Question Answering (QA) systems but its inherent slow procedures make it difficult to use at the indexing stage of the document retrieval component. In this paper we confirm the intuition that SRL at indexing stage improves the performance of QA and propose a simplified technique named the Question Prediction Language Model (QPLM), which provides similar information with a much lower cost. The methods were tested on four different QA systems and the results suggest that QPLM can be used as a good compromise between speed and accuracy.Tue Mar 04 07:47:41 CET 2008Proceedings ALTW83-90Pseudo Relevance Feedback Using Named Entities for Question Answering42006AnswerFinder inf_retrieval molla_publication Relevance feedback has already proven its usefulness in probabilistic information retrieval (IR). In this research we explore whether a pseudo relevance feedback technique on IR can improve the Question Answering task (QA). The basis of our exploration is the use of relevant named entities from the top retrieved documents as clues of relevance. We discuss two interesting findings from these experiments: the reasons the results were not improved, and the fact that today's metrics of IR evalu ation on QA do not reflect the results obtained by a QA system.Tue Mar 04 07:46:51 CET 2008Sydney, AustraliaProc. ALTW 20049-16AnswerFinder - Question Answering by Combining Lexical, Syntactic and Semantic Information2004AnswerFinder molla_publication We present a question answering system that combines information at the lexical, syntactic, and semantic levels, in the process to find and rank the candidate answer sentences. The candidate exact answers are extracted from the candidate answer sentences by means of a combination of information-extraction techniques (named entity recognition) and patterns based on logical forms. The system participated in the question answering track of TREC 2004.Wed Feb 27 03:34:35 CET 2008Proceedings DUCMacquarie University at DUC 2006: Question Answering for Summarisation2006AnswerFinder summarisation question_answering molla_publication We present an approach to summarisation based on the use of a question answering system to select the most relevant sentences. We used AnswerFinder, a question answering system that is being developed at Macquarie University. The sentences returned by AnswerFinder are further re-ranked and collated to produce the final summary. This system will serve as a baseline upon which we intend to develop methods more specific to the task of question-driven summarisation.Wed Feb 06 06:48:51 CET 2008Proc. HLT/NAACL 2006 Workshop on Graph Algorithms for Natural Language Processing37-44Learning of Graph-based Question Answering Rules2006graphs AnswerFinder molla_publication In this paper we present a graph-based approach to question answering. The method assumes a graph representation of question sentences and text sentences. Question answering rules are automatically learnt from a training corpus of questions and answer sentences with the answer annotated. The method is independent from the graph representation formalism chosen. A particular example is presented that uses a specific graph representation of the logical contents of sentences.Thu Jan 31 07:55:13 CET 2008Computational Linguistics141-61Question Answering in Restricted Domains: An Overview332007question_answering molla_publication Automated question answering has been a topic of research and development since the earliest AI applications. Computing power has increased since the first such systems were developed, and the general methodology has changed from the use of hand-encoded knowledge bases about simple domains to the use of text collections as the main knowledge source over more complex domains. Still, many research issues remain. The focus of this article is on the use of restricted domains for automated question answering. The article contains a historical perspective on question answering over restricted domains and an overview of the current methods and applications used in restricted domains. A main characteristic of question answering in restricted domains is the integration of domain-specific information that is either developed for question answering or that has been developed for other purposes. We explore the main methods developed to leverage this domain-specific information.Tue Jan 29 09:04:48 CET 2008Batumi, GeorgiaProc. Third International Tbilisi Symposium on Language, Logic and Computation\myurl{http://www.ifi.unizh.ch/cl/}ExtrAns --- Answer Extraction from Technical Documents by Minimal Logical Forms and Selective Highlighting1999ExtrAns molla_publication Tue Jan 29 09:03:47 CET 2008ZZZ-Brill:200020-27Answer Extraction -- Towards Better Evaluations of {NLP} Systems2000answer_extraction evaluation molla_publication We argue that reading comprehension tests are not particularly suited for the evaluation of NLP systems. Reading comprehension tests are specifically designed to evaluate human reading skills, and these require vast amounts of world knowledge and common-sense reasoning capabilities. Experience has shown that this kind of full-fledged question answering (QA) over texts from a wide range of domains is so difficult for machines as to be far beyond the present state of the art of NLP. To advance the field we propose a much more modest evaluation set-up, viz. Answer Extraction (AE) over texts from highly restricted domains. AE aims at retrieving those sentences from documents that contain the explicit answer to a user query. AE is less ambitious than full-fledged QA but has a number of important advantages over QA. It relies mainly on linguistic knowledge and needs only a very limited amount of world knowledge and few inference rules. However, it requires the solution of a number of key linguistic problems. This makes AE a suitable task to advance NLP techniques in a measurable way. Finally, there is a real demand for working AE systems in technical domains. We outline how evaluation procedures for AE systems over real world domains might look like and discuss their feasibility.Tue Jan 29 09:03:11 CET 2008Germersheim, GermanyProc. 34. Linguistisches {K}olloquiumInkrementelle Minimale Logische {F}ormen f{\"u}r die {A}ntwortextraktion1999answer_extraction semantics ExtrAns molla_publication Tue Jan 29 09:01:47 CET 2008New Directions in Question AnsweringZ-NewDirections:200471-82Question Answering in Terminology-Rich Technical Domains2004ExtrAns molla_publication Tue Jan 29 08:59:46 CET 2008Sapporo, JapanProc. Workshop in Paraphrasing at ACL2003Exploiting Paraphrases in a Question Answering System2003question_answering molla_publication Tue Jan 29 08:59:29 CET 2008AmsterdamProc. ECAI2002 July 21-26 2002, Lyon, France460-464Towards Answer Extraction: An Application to Technical Domains2002ExtrAns molla_publication The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction (AE) systems satisfy that need. This paper presents one such system (ExtrAns) which works by transforming documents and queries into a semantic representation called Minimal Logical Form (MLF) and derives the answers by logical proof from the documents. MLFs use underspecification to overcome the problems associated with a complete semantic representation and offer the possibility of monotonic, non-destructive extension.Tue Jan 29 08:57:50 CET 2008Traitement Automatique des Langues2495-522Extrans, an Answer Extraction System412000ExtrAns answer_extraction molla_publication Tue Jan 29 08:56:36 CET 2008Traitement Automatique des Langues1127-156Answer Extraction Using a Dependency Grammar in {ExtrAns}412000DG ExtrAns molla_publication We report on the implementation of an answer extraction system, ExtrAns, that uses the output of a dependency-based parser and grammar. In order to increase speed, the parser and grammar used sacrifice functionalism (in the framework of dependency theory) in favour of projectivity. We have found that the resulting dependency structures, although cumbersome to handle, can be used by ExtrAns to find the syntactic and semantic dependencies needed in several of the linguistic processing stages. In particular, we focus on the minimal logical form generation.Tue Jan 29 08:55:24 CET 2008IEEE Intelligent Systems412-17ExtrAns: Extracting Answers from Technical Texts182003ExtrAns molla_publication