@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:2004, abstract = {Current question answering systems typically combine methods based in information retrieval and information extraction. Such methods leverage the speed of the resulting algorithms and the presence of information redundancy, but few systems use methods based on linguistic information beyond the word level. In this paper we present a study of the impact of the syntactic and semantic information in the selection process of the final candidate sentence. The selection process is based on measures of grammatical relation overlap and flat logical form overlap.}, added-at = {2008-01-29T08:25:08.000+0100}, author = {Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/2a138fccaf668e2ac25eb12206aecad63/diego_ma}, interhash = {5dc6917e0033588e21a5b5214f96d6b8}, intrahash = {a138fccaf668e2ac25eb12206aecad63}, journal = {Procesamiento del Lenguaje Natural}, keywords = {AnswerFinder molla_publication Spanish}, pages = {17-24}, timestamp = {2008-01-29T08:25:08.000+0100}, title = {Hacia el Uso de la Informaci{\'o}n Sint{\'a}ctica y Sem{\'a}ntica en los Sistemas de B{\'u}squeda de Respuestas}, url = {http://www.ics.mq.edu.au/~diego/publications/sepln04.pdf}, volume = 33, year = 2004 } @inproceedings{Molla:ANLP02, added-at = {2008-01-29T08:20:55.000+0100}, author = {Moll{\'a}, Diego and Hutchinson, Ben}, biburl = {http://www.bibsonomy.org/bibtex/251a7573fde0a098e561c31f0d776ad5c/diego_ma}, booktitle = {Proc. 2002 Australasian NLP Workshop}, interhash = {bc6690c5c8367272a97adf7cbf1ca3b7}, intrahash = {51a7573fde0a098e561c31f0d776ad5c}, keywords = {AnswerFinder dependencies molla_publication}, timestamp = {2008-01-29T08:20:55.000+0100}, title = {Dependency-based Semantic Interpretation for Answer Extraction}, year = 2002 } @inproceedings{Moll'a:2003b, abstract = {A wide range of parser and/or grammar evaluation methods have been reported in the literature. However, in most cases these evaluations take the parsers independently (intrinsic evaluations), and only in a few cases has the effect of different parsers in real applications been measured (extrinsic evaluations). This paper compares two evaluations of the Link Grammar parser and the Conexor Functional Dependency Grammar parser. The parsing systems, despite both being dependency-based, return different types of dependencies, making a direct comparison impossible. In the intrinsic evaluation, the accuracy of the parsers is compared independently by converting the dependencies into grammatical relations and using the methodology of \newcite{Carroll:1998} for parser comparison. In the extrinsic evaluation, the parsers' impact in a practical application is compared within the context of answer extraction. The differences in the results are significant.}, added-at = {2008-01-29T08:19:28.000+0100}, address = {Budapest}, author = {Moll{\'a}, Diego and Hutchinson, Ben}, biburl = {http://www.bibsonomy.org/bibtex/2a9ae1ef031141fe460eaa6deea6036d7/diego_ma}, booktitle = {Proc. European Association for Computational Linguistics (EACL), workshop on Evaluation Initiatives in Natural Language Processing}, interhash = {c39636076c0c039471b07265565ed060}, intrahash = {a9ae1ef031141fe460eaa6deea6036d7}, keywords = {parsers evaluation AnswerFinder gram_rels molla_publication}, month = {April}, organization = {Association for Computational Linguistics}, pages = {43-50}, publisher = {ACL}, timestamp = {2008-01-29T08:19:28.000+0100}, title = {Intrinsic versus Extrinsic Evaluations of Parsing Systems}, year = 2003 } @unpublished{Molla:anlp02:preparation, abstract = {A wide variety of parser and/or grammar evaluation methods have been reported in the literature. However, in most cases these evaluations take the parsers independently (\emph{in vitro} evaluations), and only in a few cases has the effect of different parsers in real applications been measured (\emph{in vivo} evaluations). This paper compares two evaluations of the Link Grammar parser and the Conexor Functional Dependency Grammar parser. The parsing systems, despite both being dependency-based, return different types of dependencies, making a direct comparison impossible. In the first evaluation, the accuracy of the parsers is compared \emph{in vitro} by converting the dependencies into grammatical relations and using the methodology of \newcite{Carroll:1998} for parser comparison. In the second evaluation, the parsers' impact in a practical application is compared \emph{in vivo} within the context of answer extraction. The differences in the results are significant and raise questions on the usefulness of purely \emph{in vitro} evaluations.}, added-at = {2008-01-29T08:16:55.000+0100}, author = {Moll{\'a}, Diego and Hutchinson, Ben}, biburl = {http://www.bibsonomy.org/bibtex/2ddf167520fb423a651e0c5dcb062f1f2/diego_ma}, interhash = {bd10546650953340c50de023e6c7c51e}, intrahash = {ddf167520fb423a651e0c5dcb062f1f2}, keywords = {AnswerFinder parsers evaluation gram_rels molla_publication}, note = {In preparation}, timestamp = {2008-01-29T08:16:55.000+0100}, title = {In Vitro and In Vivo Evaluations of Parsing Systems Within the Context of Answer Extraction}, year = 2002 } @inproceedings{Moll'a:2004a, added-at = {2008-01-29T08:07:10.000+0100}, author = {Moll{\'a}, Diego and Gardiner, Mary}, biburl = {http://www.bibsonomy.org/bibtex/239fce546c0e3de46c67db564b0767efe/diego_ma}, crossref = {ZZZ-TREC13}, interhash = {913d00edbeb2f08919941b0f48f87921}, intrahash = {39fce546c0e3de46c67db564b0767efe}, keywords = {question_answering AnswerFinder molla_publication}, timestamp = {2008-01-29T08:07:10.000+0100}, title = {AnswerFinder at {TREC} 2004}, year = 2004 } @inproceedings{Molla:ALTW05, added-at = {2008-01-29T07:32:31.000+0100}, author = {Moll{\'a}, Diego and van Zaanen, Menno}, biburl = {http://www.bibsonomy.org/bibtex/28d953ca54eb2d90819cd88d9c01d54f9/diego_ma}, crossref = {ZZZ-ALTW05}, interhash = {5cebd4e67b58e6e4a0fbd8404edacb04}, intrahash = {8d953ca54eb2d90819cd88d9c01d54f9}, keywords = {AnswerFinder molla_publication}, timestamp = {2008-01-29T07:32:31.000+0100}, title = {Learning of Graph Rules for Question Answering}, year = 2005 } @inproceedings{Zaanen:2007, abstract = {This article describes the AnswerFinder question answering system and its participation in the TREC 2006 question answering competition. This year there have been several improvements in the AnswerFinder system, although most of them in the implementation sphere. The actual functionality used this year is almost exactly the same as last year, but many bugs are fixed and the efficiency of the system has improved much. This allows for more extensive parameter tuning. Here we will also present an error analysis of the current AnswerFinder system.}, added-at = {2008-01-29T07:24:12.000+0100}, author = {van Zaanen, Menno and Moll{\'a}, Diego and Pizzato, Luiz}, biburl = {http://www.bibsonomy.org/bibtex/2f6eb57c10e7b0ed026b6d3169c2abdfe/diego_ma}, booktitle = {Proceedings TREC 2006}, editor = {Voorhees, Ellen M. and Buckland, Lori P.}, interhash = {fd2f43a86b64edb6702aeb09b9afba43}, intrahash = {f6eb57c10e7b0ed026b6d3169c2abdfe}, keywords = {AnswerFinder molla_publication}, pages = {8 pages}, timestamp = {2008-01-29T07:24:12.000+0100}, title = {AnswerFinder at TREC 2006}, year = 2007 } @inproceedings{Pizzato:2007, abstract = {This paper proposes the use of a language representation that specifies the relationship between terms of a sentence using question words. The proposed representation is tailored to help the search for documents containing an answer for a natural language question. This study presents the construction of this language model, the framework where it is used, and its evaluation.}, added-at = {2008-01-29T07:22:02.000+0100}, author = {Pizzato, Luiz and Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/23eb2ff36ad09d69729f2e7583357824f/diego_ma}, booktitle = {Proceedings ALTW}, interhash = {06a7151055c3f056819bee9cf3cfec2f}, intrahash = {3eb2ff36ad09d69729f2e7583357824f}, keywords = {AnswerFinder inf_retrieval molla_publication}, pages = {92-99}, timestamp = {2008-01-29T07:22:02.000+0100}, title = {Question Prediction Language Model}, url = {http://www.ics.mq.edu.au/~diego/answerfinder/}, volume = 5, year = 2007 } @inproceedings{Moll'a:2007, abstract = {Question answering on speech transcripts (QAst) is a pilot track of the CLEF competition. In this paper we present our contribution to QAst, which is centred on a study of Named Entity (NE) recognition on speech transcripts, and how it impacts on the accuracy of the final question answering system. We have ported AFNER, the NE recogniser of the AnswerFinder question-answering project, to the set of answer types expected in the QAst track. AFNER uses a combination of regular expressions, lists of names (gazetteers) and machine learning to find NeWS in the data. The machine learning component was trained on a development set of the AMI corpus. In the process we identified various problems with scalability of the system and the existence of errors of the extracted annotation, which lead to relatively poor performance in general. Performance was yet comparable with state of the art, and the system was second (out of three participants) in one of the QAst subtasks.}, added-at = {2008-01-29T07:21:37.000+0100}, author = {Moll{\'a}, Diego and van Zaanen, Menno and Cassidy, Steve}, biburl = {http://www.bibsonomy.org/bibtex/2202b97875a0ca06dba67da3f7febfc86/diego_ma}, booktitle = {Proc. ALTW 2007}, editor = {Colineau, Nathalie and Dras, Mark}, interhash = {2606e7117807640622c8c6ff801b2cf2}, intrahash = {202b97875a0ca06dba67da3f7febfc86}, keywords = {AnswerFinder named_entities speech molla_publication}, pages = {57-65}, timestamp = {2008-01-29T07:21:37.000+0100}, title = {Named Entity Recognition in Question Answering of Speech Data}, url = {http://www.alta.asn.au/events/altw2007/cdrom/index.html}, volume = 5, year = 2007 } @inproceedings{Molla:TREC05, abstract = {AnswerFinder has been completely redesigned for TREC 2005. The new architecture allows a fast development of question-answering systems for their deployment in the TREC tasks and other applications. The AnswerFinder modules use XML to express the services they provide, and they can be queried with XML for their services. The QA method now incorporates graph-based methods to compute the answerhood of a sentence and pin-point the answer. The system uses a set of graph-based rules that are learnt automatically. Unfortunately the system could not be completed and debugged before the TREC deadline and the runs did not fare well. Currently we are debugging and evaluating the system.}, added-at = {2008-01-29T07:21:22.000+0100}, author = {Moll{\'a}, Diego and van Zaanen, Menno}, biburl = {http://www.bibsonomy.org/bibtex/289ee81638dd47b1b73db44a450fcc9c6/diego_ma}, crossref = {ZZZ-TREC14}, interhash = {95e62b26b8f4dc7f3a048ec0157d40b8}, intrahash = {89ee81638dd47b1b73db44a450fcc9c6}, keywords = {AnswerFinder graphs molla_publication}, timestamp = {2008-01-29T07:21:22.000+0100}, title = {AnswerFinder at {TREC} 2005}, url = {http://trec.nist.gov/pubs/trec14/t14_proceedings.html}, year = 2006 } @inproceedings{Moll'a:2003a, added-at = {2008-01-29T07:13:18.000+0100}, address = {Melbourne}, author = {Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/26fbb4cafafc5651d244edd8fd16e435c/diego_ma}, booktitle = {Proc. ALTW03}, interhash = {6ed43b69e6aeb54fc179837ce9c98c05}, intrahash = {6fbb4cafafc5651d244edd8fd16e435c}, keywords = {AnswerFinder molla_publication}, pages = {130-137}, timestamp = {2008-01-29T07:13:18.000+0100}, title = {Towards Semantic-Based Overlap Measures for Question Answering}, year = 2003 } @inproceedings{Moll'a:2003, added-at = {2008-01-29T07:13:17.000+0100}, author = {Moll{\'a}, Diego}, biburl = {http://www.bibsonomy.org/bibtex/2fcafbf38f1cb4c5225ea22e699e426aa/diego_ma}, booktitle = {Proc. TREC 2003}, interhash = {32f6afefaa0acd17bc346cd7c362943b}, intrahash = {fcafbf38f1cb4c5225ea22e699e426aa}, keywords = {AnswerFinder molla_publication}, timestamp = {2008-01-29T07:13:17.000+0100}, title = {AnswerFinder in {TREC} 2003}, year = 2003 }