@inproceedings{Molla:2011, abstract = {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.}, added-at = {2011-11-16T08:49:50.000+0100}, author = {Moll{\'a}, Diego and Santiago-Mart{\'i}nez, Maria Elena}, biburl = {http://www.bibsonomy.org/bibtex/2b9f0fa9d3e81750dd3731220af28b784/diego_ma}, booktitle = {Proceedings ALTA 2011}, interhash = {792e5066d52bf4464616ec08bc5eacbe}, intrahash = {b9f0fa9d3e81750dd3731220af28b784}, keywords = {corpus biomedical molla_publication}, timestamp = {2011-11-16T08:49:50.000+0100}, title = {Development of a Corpus for Evidence Based Medicine Summarisation}, year = 2011 } @inproceedings{Molla:2010, abstract = {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.}, added-at = {2011-01-19T05:42:18.000+0100}, author = {Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/2f67220713d3a4fa275ded7792d1ff320/diego_ma}, booktitle = {Proceedings of the Australasian Language Technology Workshop}, interhash = {5d7febb52df09e9aaea0e00a02c93dc0}, intrahash = {f67220713d3a4fa275ded7792d1ff320}, keywords = {molla_medicalnlp corpora summarisation molla_publication}, library = {Webpage (Jan 2011)}, pages = {76-80}, timestamp = {2011-01-19T05:42:18.000+0100}, title = {A Corpus for Evidence Based Medicine Summarisation}, url = {http://www.alta.asn.au/events/alta2010/proceedings/index.html}, volume = 8, year = 2010 } @inproceedings{Sarker:2010, abstract = {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.}, added-at = {2011-01-19T05:38:34.000+0100}, author = {Sarker, Abeed and Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/239bf579716c089a6f88172585849394c/diego_ma}, booktitle = {Proceedings of the Fifteenth Australasian Document Computing Symposium}, interhash = {36cf0ae6f5e2226dbf086ab69aad802b}, intrahash = {39bf579716c089a6f88172585849394c}, keywords = {molla_medicalnlp text_categorisation biomedical molla_publication}, library = {Website (Jan 2011)}, timestamp = {2011-01-19T05:38:34.000+0100}, title = {A Rule-based Approach for Automatic Identification of Publication Types of Medical Papers}, url = {http://www.cs.rmit.edu.au/adcs2010/proceedings/}, year = 2010 } @inproceedings{Tutos:2010, abstract = {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.}, added-at = {2010-02-03T05:18:03.000+0100}, author = {Tutos, Andreea and Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/276e4958f59a96bfab2f1d14d5a735174/diego_ma}, booktitle = {Proceedings HIKM 2010}, interhash = {a2d36c4e380ca7fa0f579de76f9984d3}, intrahash = {76e4958f59a96bfab2f1d14d5a735174}, keywords = {molla_medicalnlp search inf-retr question_answering biomedical molla_publication}, optpages = {8 pages}, timestamp = {2010-02-03T05:18:03.000+0100}, title = {A Study on the Use of Search Engines for Answering Clinical Questions}, year = 2010 } @inproceedings{Molla:2006a, abstract = {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.}, added-at = {2008-10-10T05:18:00.000+0200}, author = {Moll{\'a}, Diego and van Zaanen, Menno and Smith, Daniel}, biburl = {http://www.bibsonomy.org/bibtex/264e2ff61c23df0f5f02914ea091dc158/diego_ma}, booktitle = {Proceedings ALTW 2006}, interhash = {6759916d3748647a40af77f818a52130}, intrahash = {64e2ff61c23df0f5f02914ea091dc158}, keywords = {named_entities AnswerFinder molla_publication}, pages = {51-58}, timestamp = {2008-10-10T05:18:00.000+0200}, title = {Named Entity Recognition for Question Answering}, year = 2006 } @inproceedings{Pizzato:2008, abstract = {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.}, added-at = {2008-07-01T10:45:03.000+0200}, author = {Pizzato, Luiz and Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/2cc132a9e1fda44b9f205512d8975952c/diego_ma}, booktitle = {Proc. COLING Workshop on Information Retrieval for Question Answering}, interhash = {12bafd7d5a0de7c44be5cc5dcb54f512}, intrahash = {cc132a9e1fda44b9f205512d8975952c}, keywords = {question_answering molla_publication AnswerFinder inf_retrieval}, pages = {8 pages}, timestamp = {2008-07-01T10:45:03.000+0200}, title = {Indexing on Semantic Roles for Question Answering}, year = 2008 } @inproceedings{Pizzato:2006, abstract = {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.}, added-at = {2008-03-04T07:47:41.000+0100}, author = {Pizzato, Luiz and Moll{\'a}, Diego and Paris, C{\'e}cile}, biburl = {http://www.bibsonomy.org/bibtex/25ddeca10bfa22885c0c1a6a429ae5ed9/diego_ma}, booktitle = {Proceedings ALTW}, interhash = {4bd2eac0d86884713f58b8e5fa93bb96}, intrahash = {5ddeca10bfa22885c0c1a6a429ae5ed9}, keywords = {AnswerFinder inf_retrieval molla_publication}, pages = {83-90}, timestamp = {2008-03-04T07:47:41.000+0100}, title = {Pseudo Relevance Feedback Using Named Entities for Question Answering}, url = {http://www.alta.asn.au/events/altw2006/alta-2006-online-proceedings.html}, volume = 4, year = 2006 } @inproceedings{Molla:2004b, abstract = {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.}, added-at = {2008-03-04T07:46:51.000+0100}, address = {Sydney, Australia}, author = {Moll{\'a}, Diego and Gardiner, Mary}, biburl = {http://www.bibsonomy.org/bibtex/2d2a43592b416f89978d82c5cd2e06ef7/diego_ma}, booktitle = {Proc. ALTW 2004}, editor = {Asudeh, Ash and Paris, C{\'e}cile and Wan, Stephen}, interhash = {6fc3e48731c53b98b86f6d9ab7421a21}, intrahash = {d2a43592b416f89978d82c5cd2e06ef7}, keywords = {AnswerFinder molla_publication}, organization = {Macquarie University}, pages = {9-16}, timestamp = {2008-03-04T07:46:51.000+0100}, title = {AnswerFinder - Question Answering by Combining Lexical, Syntactic and Semantic Information}, url = {http://www.alta.asn.au/events/altw2004/publication/paperindex.html}, year = 2004 } @inproceedings{Molla:2006, abstract = {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.}, added-at = {2008-02-27T03:34:35.000+0100}, author = {Moll{\'a}, Diego and Wan, Stephen}, biburl = {http://www.bibsonomy.org/bibtex/2d3e298514ecd89ffb3bd1b5cb939e540/diego_ma}, booktitle = {Proceedings DUC}, interhash = {f639e2c0c7d8124a0ec4f65e1dedec4b}, intrahash = {d3e298514ecd89ffb3bd1b5cb939e540}, keywords = {AnswerFinder summarisation question_answering molla_publication}, timestamp = {2008-02-27T03:34:35.000+0100}, title = {Macquarie University at DUC 2006: Question Answering for Summarisation}, url = {http://www.ics.mq.edu.au/~diego/publications/DUC2006.pdf}, year = 2006 } @inproceedings{Molla:2006b, abstract = {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.}, added-at = {2008-02-06T06:48:51.000+0100}, author = {Moll\'{a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/2d40066e489bb1545f2afc538c451b0b3/diego_ma}, booktitle = {Proc. HLT/NAACL 2006 Workshop on Graph Algorithms for Natural Language Processing}, interhash = {519694cc699f9f82a8a2cf0d56e6d0f4}, intrahash = {d40066e489bb1545f2afc538c451b0b3}, keywords = {graphs AnswerFinder molla_publication}, pages = {37-44}, timestamp = {2008-02-06T06:48:51.000+0100}, title = {Learning of Graph-based Question Answering Rules}, url = {http://www.ics.mq.edu.au/~diego/publications/NAACL06Graphs.pdf}, year = 2006 } @article{Molla:2007a, abstract = {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.}, added-at = {2008-01-31T07:55:13.000+0100}, author = {Moll{\'a}, Diego and Vicedo, Jos\'{e} Luis}, biburl = {http://www.bibsonomy.org/bibtex/230cd548849b8c0528e7dcd83d00ff331/diego_ma}, interhash = {2b4f432cc644deb7e1f92b3fe9f6d109}, intrahash = {30cd548849b8c0528e7dcd83d00ff331}, journal = {Computational Linguistics}, keywords = {question_answering molla_publication}, number = 1, pages = {41-61}, timestamp = {2008-01-31T07:55:13.000+0100}, title = {Question Answering in Restricted Domains: An Overview}, url = {http://www.ics.mq.edu.au/~diego/answerfinder/rdqa/index.html}, volume = 33, year = 2007 } @inproceedings{Schwitter:1999, added-at = {2008-01-29T09:04:48.000+0100}, address = {Batumi, Georgia}, author = {Schwitter, Rolf and Moll{\'a}, Diego and Hess, Michael}, biburl = {http://www.bibsonomy.org/bibtex/2bcf00da4b48bb36d5a40373ee3f77703/diego_ma}, booktitle = {Proc. Third International Tbilisi Symposium on Language, Logic and Computation}, interhash = {6e228b9cfc284a6e5789dffb16a62863}, intrahash = {bcf00da4b48bb36d5a40373ee3f77703}, keywords = {ExtrAns molla_publication}, note = {\myurl{http://www.ifi.unizh.ch/cl/}}, timestamp = {2008-01-29T09:04:48.000+0100}, title = {ExtrAns --- Answer Extraction from Technical Documents by Minimal Logical Forms and Selective Highlighting}, url = {http://www.ifi.unizh.ch/cl/}, year = 1999 } @inproceedings{Schwitter:2000, abstract = {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.}, added-at = {2008-01-29T09:03:47.000+0100}, author = {Schwitter, Rolf and Moll{\'a}, Diego and Fournier, Rachel and Hess, Michael}, biburl = {http://www.bibsonomy.org/bibtex/2449b4548c23384e9a02234898bdc9715/diego_ma}, crossref = {ZZZ-Brill:2000}, interhash = {d1873a08ccf2b428f2a6090d1c54d27e}, intrahash = {449b4548c23384e9a02234898bdc9715}, keywords = {answer_extraction evaluation molla_publication}, pages = {20-27}, timestamp = {2008-01-29T09:03:47.000+0100}, title = {Answer Extraction -- Towards Better Evaluations of {NLP} Systems}, year = 2000 } @inproceedings{Schneider:1999, added-at = {2008-01-29T09:03:11.000+0100}, address = {Germersheim, Germany}, author = {Schneider, Gerold and Moll{\'a}, Diego and Hess, Michael}, biburl = {http://www.bibsonomy.org/bibtex/297e9a688c93398aaedca1cc8430e5604/diego_ma}, booktitle = {Proc. 34. Linguistisches {K}olloquium}, interhash = {1b8400b01be0f110bd6918782d7cfeba}, intrahash = {97e9a688c93398aaedca1cc8430e5604}, keywords = {answer_extraction semantics ExtrAns molla_publication}, timestamp = {2008-01-29T09:03:11.000+0100}, title = {Inkrementelle Minimale Logische {F}ormen f{\"u}r die {A}ntwortextraktion}, year = 1999 } @incollection{Rinaldi:2004:2, added-at = {2008-01-29T09:01:47.000+0100}, author = {Rinaldi, Fabio and Hess, Michael and Dowdall, James and Moll{\'a}, Diego and Schwitter, Rolf}, biburl = {http://www.bibsonomy.org/bibtex/257984336f70601891082f056b18508c0/diego_ma}, booktitle = {New Directions in Question Answering}, crossref = {Z-NewDirections:2004}, editor = {Maybury, Mark T.}, interhash = {86a358af3ecbe27e825ae3a161a8f67b}, intrahash = {57984336f70601891082f056b18508c0}, keywords = {ExtrAns molla_publication}, pages = {71-82}, publisher = {AAAI Press/MIT Press}, timestamp = {2008-01-29T09:01:47.000+0100}, title = {Question Answering in Terminology-Rich Technical Domains}, year = 2004 } @inproceedings{Rinaldi:2003, added-at = {2008-01-29T08:59:46.000+0100}, address = {Sapporo, Japan}, author = {Rinaldi, Fabio and Dowdall, James and Kaljurand, Kaarel and Hess, Michael and Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/227d481e497e3d5186ae87afc0aa51a42/diego_ma}, booktitle = {Proc. Workshop in Paraphrasing at ACL2003}, interhash = {f98a3643d44d8f44c0becb0d795fdc4c}, intrahash = {27d481e497e3d5186ae87afc0aa51a42}, keywords = {question_answering molla_publication}, timestamp = {2008-01-29T08:59:46.000+0100}, title = {Exploiting Paraphrases in a Question Answering System}, year = 2003 } @inproceedings{Rinaldi:2002, abstract = {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.}, added-at = {2008-01-29T08:59:29.000+0100}, address = {Amsterdam}, author = {Rinaldi, Fabio and Dowdall, James and Hess, Michael and Moll{\'a}, Diego and Schwitter, Rolf}, biburl = {http://www.bibsonomy.org/bibtex/2a9862cf4812a9496453656806f9f2a16/diego_ma}, booktitle = {Proc. ECAI2002 July 21-26 2002, Lyon, France}, editor = {van Harmelen, Frank}, interhash = {24563ca9f22cb07b18cbd0003fd4255c}, intrahash = {a9862cf4812a9496453656806f9f2a16}, keywords = {ExtrAns molla_publication}, pages = {460-464}, publisher = {IOS Press}, timestamp = {2008-01-29T08:59:29.000+0100}, title = {Towards Answer Extraction: An Application to Technical Domains}, url = {http://www.ifi.unizh.ch/staff/rinaldi/}, year = 2002 } @article{Molla:TAL2, added-at = {2008-01-29T08:57:50.000+0100}, author = {Moll{\'a}, Diego and Schwitter, Rolf and Hess, Michael and Fournier, Rachel}, biburl = {http://www.bibsonomy.org/bibtex/28c68dc2b9b93d0fb3dc28858c35a0a42/diego_ma}, interhash = {ea41560f6e524b98bbfd8eeaa25cab5c}, intrahash = {8c68dc2b9b93d0fb3dc28858c35a0a42}, journal = {Traitement Automatique des Langues}, keywords = {ExtrAns answer_extraction molla_publication}, number = 2, pages = {495-522}, timestamp = {2008-01-29T08:57:50.000+0100}, title = {Extrans, an Answer Extraction System}, volume = 41, year = 2000 } @article{Molla:DGPaper, abstract = {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.}, added-at = {2008-01-29T08:56:36.000+0100}, author = {Moll{\'a}, Diego and Schneider, Gerold and Schwitter, Rolf and Hess, Michael}, biburl = {http://www.bibsonomy.org/bibtex/20165dbba25a1cd2fa846f3dd26a383a4/diego_ma}, interhash = {496501ed9bff90b28b2df7d7ace1924d}, intrahash = {0165dbba25a1cd2fa846f3dd26a383a4}, journal = {Traitement Automatique des Langues}, keywords = {DG ExtrAns molla_publication}, number = 1, pages = {127-156}, timestamp = {2008-01-29T08:56:36.000+0100}, title = {Answer Extraction Using a Dependency Grammar in {ExtrAns}}, volume = 41, year = 2000 } @article{Molla:IEEE, added-at = {2008-01-29T08:55:24.000+0100}, author = {Moll{\'a}, Diego and Rinaldi, Fabio and Schwitter, Rolf and Dowdall, James and Hess, Michael}, biburl = {http://www.bibsonomy.org/bibtex/2e97a26af27691a1817f4be105440eab6/diego_ma}, interhash = {f4dd3a2cc8c8d732934ea15933495303}, intrahash = {e97a26af27691a1817f4be105440eab6}, journal = {IEEE Intelligent Systems}, keywords = {ExtrAns molla_publication}, number = 4, pages = {12-17}, timestamp = {2008-01-29T08:55:24.000+0100}, title = {ExtrAns: Extracting Answers from Technical Texts}, volume = 18, year = 2003 }