information extraction, text mining, question answering, mobile translation tools, computer assisted language learning, dialogue system, medical information system
Human agents in technical customer support provide users with instructional answers to solve a ta... more Human agents in technical customer support provide users with instructional answers to solve a task that would otherwise require a lot of time, money, energy, physical costs. Developing a dialogue system in this domain is challenging due to the broad variety of user questions. Moreover, user questions are noisy (for example, spelling mistakes), redundant and have various natural language expressions. In this work, we introduce a conversational system, MOLI (the name of our dialogue system), to solve customer questions by providing instructional answers from a knowledge base. Our approach combines models for question type and intent category classification with slot filling and a back-end knowledge base for filtering and ranking answers, and uses a dialog framework to actively query the user for missing information. For answer-ranking we find that sequential matching networks and neural multi-perspective sentence similarity networks clearly outperform baseline models, achieving a 43%...
International Conference on Agents and Artificial Intelligence (ICAART), 2015
A new method is proposed and evaluated that improves distantly supervised learning of pattern rul... more A new method is proposed and evaluated that improves distantly supervised learning of pattern rules for n-ary relation extraction. The new method employs knowledge from a large lexical semantic repository to guide the discovery of patterns in parsed relation mentions. It extends the induced rules to semantically relevant material outside the minimal subtree containing the shortest paths connecting the relation entities and also discards rules without any explicit semantic content. It significantly raises both recall and precision with roughly 20% f-measure boost in comparison to the baseline system which does not consider the lexical semantic information.
International Conference on Computational Linguistics (COLING), Posters Volume, 2010
This paper presents a new approach to improving relation extraction based on minimally supervised... more This paper presents a new approach to improving relation extraction based on minimally supervised learning. By adding some limited closed-world knowledge for confidence estimation of learned rules to the usual seed data, the precision of relation extraction can be considerably improved. Starting from an existing base-line system we demonstrate that utilizing limited closed world knowledge can effectively eliminate " dangerous " or plainly wrong rules during the bootstrapping process. The new method improves the reliability of the confidence estimation and the precision value of the extracted instances. Although recall suffers to a certain degree depending on the domain and the selected settings, the overall performance measured by F-score considerably improves. Finally we validate the adaptability of the best ranking method to a new domain and obtain promising results.
Workshop on Natural Language Processing Techniques for Educational Applications at the Annual Meeting of the Association for Computational Linguistics (NLP-TEA @ ACL), 2015
We propose a strategy for the semi-automatic generation of learning material for reading-comprehe... more We propose a strategy for the semi-automatic generation of learning material for reading-comprehension tests, guided by semantic relations embedded in expos-itory texts. Our approach combines methods from the areas of information extraction and paraphrasing in order to present a language teacher with a set of candidate multiple-choice questions and answers that can be used for verifying a language learners reading capabilities. We implemented a web-based prototype showing the feasibility of our approach and carried out a pilot user evaluation that resulted in encouraging feedback but also pointed out aspects of the strategy and prototype implementation which need improvements.
International Conference on Language Resources and Evaluation (LREC), 2016
Recent research shows the importance of linking linguistic knowledge resources for the creation o... more Recent research shows the importance of linking linguistic knowledge resources for the creation of large-scale linguistic data. We describe our approach for combining two English resources, FrameNet and sar-graphs, and illustrate the benefits of the linked data in a relation extraction setting. While FrameNet consists of schematic representations of situations, linked to lexemes and their valency patterns, sar-graphs are knowledge resources that connect semantic relations from factual knowledge graphs to the linguistic phrases used to express instances of these relations. We analyze the conceptual similarities and differences of both resources and propose to link sar-graphs and FrameNet on the levels of relations/frames as well as phrases. The former alignment involves a manual ontology mapping step, which allows us to extend sar-graphs with new phrase patterns from FrameNet. The phrase-level linking, on the other hand, is fully automatic. We investigate the quality of the automatically constructed links and identify two main classes of errors.
We present an information system, which was developed within the project MIETTA (Multilingual Inf... more We present an information system, which was developed within the project MIETTA (Multilingual Information Extraction for Tourism and Travel Assistance), a project in the Language Engineering Sector of the Telematics Application Program of the European Commission. MIETTA facilitates multilingual information access in a number of languages (English, Finnish, French, German, Italian) to the tourist information (web documents and database information) provided by three different geographical regions: the German federal state of Saarland, the Finnish region around Turku and the Italian City of Rome.
After several years of development, the vision of the Semantic Web is gradually becoming reality.... more After several years of development, the vision of the Semantic Web is gradually becoming reality. Large data repositories have been created and offer semantic information in a machine-processable form for various domains. Semantic Web data can be published on the Web, gathered automatically, and reasoned about. All these developments open interesting perspectives for building a new class of domain-specific, broad-coverage information systems that overcome a long-standing bottleneck of AI systems, the notoriously incomplete knowledge base. We present a system that shows how the wealth of information in the Semantic Web can be interfaced with humans once again, using natural language for querying and answering rather than technical formalisms. Whereas current Question Answering systems typically select snippets from Web documents retrieved by a search engine, we utilize Semantic Web data, which allows us to provide natural-language answers that are tailored to the current dialog context. Furthermore, we show how to use natural language processing technologies to acquire new data and enrich existing data in a Semantic Web framework. Our system has acquired a rich biographic data resource by combining existing Semantic Web resources, which are discovered from semi-structured textual data in Web pages, with information extracted from free natural language texts.
This paper presents a novel information system integrating advanced information extraction techno... more This paper presents a novel information system integrating advanced information extraction technology and automatic hyper-linking. Extracted entities are mapped into a domain ontology that relates concepts to a selection of hyperlinks. For information extraction, we use SProUT, a generic platform for the development and use of multilingual text processing components. By combining finite-state and unification-based formalisms, the grammar formalism used in SProUT offers both processing efficiency and a high degree of decalrativeness. The ExtraLink demo system showcases the extraction of relevant concepts from German texts in the tourism domain, offering the direct connection to associated web documents on demand.
In this paper we present our current state-of-the art in the development of a hybrid QA architect... more In this paper we present our current state-of-the art in the development of a hybrid QA architecture. In particular we present a strategy for open-domain web-based QA, and a strategy for open domain cross-language QA. In both cases the focus is on processing fact-based questions and exact answer strategies using the Web as primarily document source. Both strategies are realized using the same core technology, and have been implemented for German and English queries and documents, and tested for German Web pages.
The Compass2008 project is a sino-german cooperation, aiming at integrating advanced information ... more The Compass2008 project is a sino-german cooperation, aiming at integrating advanced information technologies to create a high-tech information system that helps visitors to access location-sensitive information services during the 2008 Olympic Games in their preferred language, offering a variety of service-adaptive modalities available on the mobile devices. In this paper, we demonstrate one of the COMPASS2008 services, the Smart Dining Service, to showcase the new interaction concepts between multimodality, multilingual and location-sensitive information search.
This paper presents the extension of an existing mimimally supervised rule acquisition method for... more This paper presents the extension of an existing mimimally supervised rule acquisition method for relation extraction by coreference resolution (CR). To this end, a novel approach to CR was designed and tested. In comparison to state-of-the-art methods for CR, our strategy is driven by the target semantic relation and utilizes domain-specific ontological and lexical knowledge in addition to the learned relation extraction rules. An empirical investigation reveals that newswire texts in our selected domains contain more coreferring noun phrases than prononimal coreferences. This means that existing methods for CR would not suffice and a semantic approach is needed. Our experiments show that the utilization of domain knowledge can boost CR. In our approach, the tasks of relation extraction and CR support each other. On the one hand, reference resolution is needed for the detection of arguments of the target relation. On the other hand, domain modelling for the IE task is used for semantic classification of the referring nouns. Moreover, the application of the learned relation extraction rules often narrows down the number of candidates for CR.
We present an implemented approach for domainrestricted question answering from structured knowle... more We present an implemented approach for domainrestricted question answering from structured knowledge sources, based on robust semantic analysis in a hybrid NLP system architecture. We build on a lexicalsemantic conceptual structure for question interpretation, which is interfaced with domain-specific concepts and properties in a structured knowledge base. Question interpretation involves a limited amount of domain-specific inferences and accounts for quantificational questions. We extract so-called proto queries from the linguistic representation, which provide partial constraints for answer extraction from the underlying knowledge sources. The search queries we construct from proto queries effectively constitute minimum spanning trees that restrict the possible answer candidates. Our approach naturally extends to multilingual question answering and has been developed as a prototype system for two application domains: the domain of Nobel prize winners and the domain of Language Technology, on the basis of the large ontology underlying the information portal LT World.
In this paper we show an approach to the customization of GermaNet to the German HPSG grammar lex... more In this paper we show an approach to the customization of GermaNet to the German HPSG grammar lexicon developed in the Verbmobil project. GermaNet has a broad coverage of the German base vocabulary and fine-grained semantic classification; while the HPSG grammar lexicon is comparatively small und has a coarse-grained semantic classification. In our approach, we have developed a mapping algorithm to relate the synsets in GermaNet with the semantic sorts in HPSG. The evaluation result shows that this approach is useful for the lexical extension of our deep grammar development to cope with real-world text understanding.
Web Intelligence and Agent Systems: An International Journal, 2004
Abstract. We present a novel method for mining textual answers in Web pages using semi-structured... more Abstract. We present a novel method for mining textual answers in Web pages using semi-structured NL questions and Google for initial document retrieval. We exploit the redundancy on the Web by weighting all identified named entities (NEs) found in the relevant document set based ...
The short papers reproduced here describe implemented systems that were presented at the demo ses... more The short papers reproduced here describe implemented systems that were presented at the demo session of EACL-2009 in Athens, March 30 -April 3, 2009. Upon the call for demos, a total of 33 papers were submitted. Each submission was reviewed by at least two members of the programme committee. Based on these reviews, 17 submissions were accepted for presentation at the demo session and publication in the conference proceedings.
In this paper, we present a survey of challenges and solutions of multilingual and translingual i... more In this paper, we present a survey of challenges and solutions of multilingual and translingual information service systems. In contrast to the computational linguistics literature on such systems, we are approaching the theme here from an HCI perspective. We will argue for a strategy that reduces reliance on automatic free-text translation, language input and classical information retrieval while not giving up these less reliable technologies altogether. We will also opt for a close situation-driven integration of information and communication functionalities. The described solutions have been incorporated into a novel mobile combined information and communication system for foreign tourists that has been tested under realistic conditions by users from several countries. The system is developed by the German-Chinese cooperation project COMPASS2008, a research action within the Digital Olympics framework.
Human agents in technical customer support provide users with instructional answers to solve a ta... more Human agents in technical customer support provide users with instructional answers to solve a task that would otherwise require a lot of time, money, energy, physical costs. Developing a dialogue system in this domain is challenging due to the broad variety of user questions. Moreover, user questions are noisy (for example, spelling mistakes), redundant and have various natural language expressions. In this work, we introduce a conversational system, MOLI (the name of our dialogue system), to solve customer questions by providing instructional answers from a knowledge base. Our approach combines models for question type and intent category classification with slot filling and a back-end knowledge base for filtering and ranking answers, and uses a dialog framework to actively query the user for missing information. For answer-ranking we find that sequential matching networks and neural multi-perspective sentence similarity networks clearly outperform baseline models, achieving a 43%...
International Conference on Agents and Artificial Intelligence (ICAART), 2015
A new method is proposed and evaluated that improves distantly supervised learning of pattern rul... more A new method is proposed and evaluated that improves distantly supervised learning of pattern rules for n-ary relation extraction. The new method employs knowledge from a large lexical semantic repository to guide the discovery of patterns in parsed relation mentions. It extends the induced rules to semantically relevant material outside the minimal subtree containing the shortest paths connecting the relation entities and also discards rules without any explicit semantic content. It significantly raises both recall and precision with roughly 20% f-measure boost in comparison to the baseline system which does not consider the lexical semantic information.
International Conference on Computational Linguistics (COLING), Posters Volume, 2010
This paper presents a new approach to improving relation extraction based on minimally supervised... more This paper presents a new approach to improving relation extraction based on minimally supervised learning. By adding some limited closed-world knowledge for confidence estimation of learned rules to the usual seed data, the precision of relation extraction can be considerably improved. Starting from an existing base-line system we demonstrate that utilizing limited closed world knowledge can effectively eliminate " dangerous " or plainly wrong rules during the bootstrapping process. The new method improves the reliability of the confidence estimation and the precision value of the extracted instances. Although recall suffers to a certain degree depending on the domain and the selected settings, the overall performance measured by F-score considerably improves. Finally we validate the adaptability of the best ranking method to a new domain and obtain promising results.
Workshop on Natural Language Processing Techniques for Educational Applications at the Annual Meeting of the Association for Computational Linguistics (NLP-TEA @ ACL), 2015
We propose a strategy for the semi-automatic generation of learning material for reading-comprehe... more We propose a strategy for the semi-automatic generation of learning material for reading-comprehension tests, guided by semantic relations embedded in expos-itory texts. Our approach combines methods from the areas of information extraction and paraphrasing in order to present a language teacher with a set of candidate multiple-choice questions and answers that can be used for verifying a language learners reading capabilities. We implemented a web-based prototype showing the feasibility of our approach and carried out a pilot user evaluation that resulted in encouraging feedback but also pointed out aspects of the strategy and prototype implementation which need improvements.
International Conference on Language Resources and Evaluation (LREC), 2016
Recent research shows the importance of linking linguistic knowledge resources for the creation o... more Recent research shows the importance of linking linguistic knowledge resources for the creation of large-scale linguistic data. We describe our approach for combining two English resources, FrameNet and sar-graphs, and illustrate the benefits of the linked data in a relation extraction setting. While FrameNet consists of schematic representations of situations, linked to lexemes and their valency patterns, sar-graphs are knowledge resources that connect semantic relations from factual knowledge graphs to the linguistic phrases used to express instances of these relations. We analyze the conceptual similarities and differences of both resources and propose to link sar-graphs and FrameNet on the levels of relations/frames as well as phrases. The former alignment involves a manual ontology mapping step, which allows us to extend sar-graphs with new phrase patterns from FrameNet. The phrase-level linking, on the other hand, is fully automatic. We investigate the quality of the automatically constructed links and identify two main classes of errors.
We present an information system, which was developed within the project MIETTA (Multilingual Inf... more We present an information system, which was developed within the project MIETTA (Multilingual Information Extraction for Tourism and Travel Assistance), a project in the Language Engineering Sector of the Telematics Application Program of the European Commission. MIETTA facilitates multilingual information access in a number of languages (English, Finnish, French, German, Italian) to the tourist information (web documents and database information) provided by three different geographical regions: the German federal state of Saarland, the Finnish region around Turku and the Italian City of Rome.
After several years of development, the vision of the Semantic Web is gradually becoming reality.... more After several years of development, the vision of the Semantic Web is gradually becoming reality. Large data repositories have been created and offer semantic information in a machine-processable form for various domains. Semantic Web data can be published on the Web, gathered automatically, and reasoned about. All these developments open interesting perspectives for building a new class of domain-specific, broad-coverage information systems that overcome a long-standing bottleneck of AI systems, the notoriously incomplete knowledge base. We present a system that shows how the wealth of information in the Semantic Web can be interfaced with humans once again, using natural language for querying and answering rather than technical formalisms. Whereas current Question Answering systems typically select snippets from Web documents retrieved by a search engine, we utilize Semantic Web data, which allows us to provide natural-language answers that are tailored to the current dialog context. Furthermore, we show how to use natural language processing technologies to acquire new data and enrich existing data in a Semantic Web framework. Our system has acquired a rich biographic data resource by combining existing Semantic Web resources, which are discovered from semi-structured textual data in Web pages, with information extracted from free natural language texts.
This paper presents a novel information system integrating advanced information extraction techno... more This paper presents a novel information system integrating advanced information extraction technology and automatic hyper-linking. Extracted entities are mapped into a domain ontology that relates concepts to a selection of hyperlinks. For information extraction, we use SProUT, a generic platform for the development and use of multilingual text processing components. By combining finite-state and unification-based formalisms, the grammar formalism used in SProUT offers both processing efficiency and a high degree of decalrativeness. The ExtraLink demo system showcases the extraction of relevant concepts from German texts in the tourism domain, offering the direct connection to associated web documents on demand.
In this paper we present our current state-of-the art in the development of a hybrid QA architect... more In this paper we present our current state-of-the art in the development of a hybrid QA architecture. In particular we present a strategy for open-domain web-based QA, and a strategy for open domain cross-language QA. In both cases the focus is on processing fact-based questions and exact answer strategies using the Web as primarily document source. Both strategies are realized using the same core technology, and have been implemented for German and English queries and documents, and tested for German Web pages.
The Compass2008 project is a sino-german cooperation, aiming at integrating advanced information ... more The Compass2008 project is a sino-german cooperation, aiming at integrating advanced information technologies to create a high-tech information system that helps visitors to access location-sensitive information services during the 2008 Olympic Games in their preferred language, offering a variety of service-adaptive modalities available on the mobile devices. In this paper, we demonstrate one of the COMPASS2008 services, the Smart Dining Service, to showcase the new interaction concepts between multimodality, multilingual and location-sensitive information search.
This paper presents the extension of an existing mimimally supervised rule acquisition method for... more This paper presents the extension of an existing mimimally supervised rule acquisition method for relation extraction by coreference resolution (CR). To this end, a novel approach to CR was designed and tested. In comparison to state-of-the-art methods for CR, our strategy is driven by the target semantic relation and utilizes domain-specific ontological and lexical knowledge in addition to the learned relation extraction rules. An empirical investigation reveals that newswire texts in our selected domains contain more coreferring noun phrases than prononimal coreferences. This means that existing methods for CR would not suffice and a semantic approach is needed. Our experiments show that the utilization of domain knowledge can boost CR. In our approach, the tasks of relation extraction and CR support each other. On the one hand, reference resolution is needed for the detection of arguments of the target relation. On the other hand, domain modelling for the IE task is used for semantic classification of the referring nouns. Moreover, the application of the learned relation extraction rules often narrows down the number of candidates for CR.
We present an implemented approach for domainrestricted question answering from structured knowle... more We present an implemented approach for domainrestricted question answering from structured knowledge sources, based on robust semantic analysis in a hybrid NLP system architecture. We build on a lexicalsemantic conceptual structure for question interpretation, which is interfaced with domain-specific concepts and properties in a structured knowledge base. Question interpretation involves a limited amount of domain-specific inferences and accounts for quantificational questions. We extract so-called proto queries from the linguistic representation, which provide partial constraints for answer extraction from the underlying knowledge sources. The search queries we construct from proto queries effectively constitute minimum spanning trees that restrict the possible answer candidates. Our approach naturally extends to multilingual question answering and has been developed as a prototype system for two application domains: the domain of Nobel prize winners and the domain of Language Technology, on the basis of the large ontology underlying the information portal LT World.
In this paper we show an approach to the customization of GermaNet to the German HPSG grammar lex... more In this paper we show an approach to the customization of GermaNet to the German HPSG grammar lexicon developed in the Verbmobil project. GermaNet has a broad coverage of the German base vocabulary and fine-grained semantic classification; while the HPSG grammar lexicon is comparatively small und has a coarse-grained semantic classification. In our approach, we have developed a mapping algorithm to relate the synsets in GermaNet with the semantic sorts in HPSG. The evaluation result shows that this approach is useful for the lexical extension of our deep grammar development to cope with real-world text understanding.
Web Intelligence and Agent Systems: An International Journal, 2004
Abstract. We present a novel method for mining textual answers in Web pages using semi-structured... more Abstract. We present a novel method for mining textual answers in Web pages using semi-structured NL questions and Google for initial document retrieval. We exploit the redundancy on the Web by weighting all identified named entities (NEs) found in the relevant document set based ...
The short papers reproduced here describe implemented systems that were presented at the demo ses... more The short papers reproduced here describe implemented systems that were presented at the demo session of EACL-2009 in Athens, March 30 -April 3, 2009. Upon the call for demos, a total of 33 papers were submitted. Each submission was reviewed by at least two members of the programme committee. Based on these reviews, 17 submissions were accepted for presentation at the demo session and publication in the conference proceedings.
In this paper, we present a survey of challenges and solutions of multilingual and translingual i... more In this paper, we present a survey of challenges and solutions of multilingual and translingual information service systems. In contrast to the computational linguistics literature on such systems, we are approaching the theme here from an HCI perspective. We will argue for a strategy that reduces reliance on automatic free-text translation, language input and classical information retrieval while not giving up these less reliable technologies altogether. We will also opt for a close situation-driven integration of information and communication functionalities. The described solutions have been incorporated into a novel mobile combined information and communication system for foreign tourists that has been tested under realistic conditions by users from several countries. The system is developed by the German-Chinese cooperation project COMPASS2008, a research action within the Digital Olympics framework.
Uploads
Papers by Feiyu Xu