This paper is concerned with the problem of question search. In question search, given a question as query, we are to return questions semantically equivalent or close to the queried question. In this paper, we propose to conduct question search by identifying question topic and question focus. More specifically, we first summarize questions in a data structure consisting of question topic and question focus. Then we model question topic and question focus in a language modeling framework for search. We also propose to use the MDLbased tree cut model for identifying question topic and question focus automatically. Experimental results indicate that our approach of identifying question topic and question focus for search significantly outperforms the baseline methods such as Vector Space Model (VSM) and Language Model for Information Retrieval (LMIR). 1

We describe our work in progress on natural language analysis in medical question-answering in the context of a broader medical text-retrieval project. We analyze the limitations in the medical domain of the technologies that have been developed for general question-answering systems, and describe an alternative approach whose organizing principle is the identification of semantic roles in both question and answer texts that correspond to the fields of PICO format.

One of the major challenges in TRECstyle question-answering (QA) is to overcome the mismatch in the lexical representations in the query space and document space. This is particularly severe in QA as exact answers, rather than docmnents, are required in response to questions. Most current approaches overcome the mismatch problem by employing either data redundancy strategy through the use of Web or linguistic resources.

This paper presents a novel approach to extracting phrase-level answers in a question answering system. This approach uses structural support provided by an integrated Natural Language Processing (NLP) and Information Extraction (IE) system. Both questions and the sentence-level candidate answer strings are parsed by this NLP/IE system into binary dependency structures. Phrase-level answer extraction is modelled by comparing the structural similarity involving the question-phrase and the candidate answerphrase. There are two types of structural support. The first type involves predefined, specific entity associations such as Affiliation, Position, Age for a person entity. If a question asks about one of these associations, the answer-phrase can be determined as long as the system decodes such pre-defined dependency links correctly, despite the syntactic difference used in expressions between the question and the candidate answer string. The second type involves generic grammatical relationships such as V-S (verb-subject), V-O (verbobject). Preliminary experimental results show an improvement in both precision and recall in extracting phrase-level answers, compared with a baseline system which only uses Named Entity constraints. The proposed methods are particularly effective in cases where the question-phrase does not correspond to a known named entity type and in cases where there are multiple candidate answer-phrases satisfying the named entity constraints.

This thesis describes a computational grammar that analyzes Swedish noun phrases, and maps them to semantic representations. The noun phrase grammar is a component of the Swedish version of the Phoenix natural language interface to databases system which maps natural language questions to corresponding SQL queries. The coverage of the grammar is determined by the noun phrase part of a grammar specification for Swedish questions. Beside grammatical literature, a Wizard of Oz dialogue corpus has been used to investigate the grammatical phenomena supported by the grammar specification. An evaluation corpus has been compiled by randomly selecting questions from Internet FAQ:s about cellular phones, Internet banking and broadband connection. From these questions, noun phrases were extracted and supplied to the grammar. After manually examining the resulting semantic representations, it was found that 83% of a total of 254 noun phrases were given all the intended semantic representations, and only the intended semantic representations.

Abstract. PedaBot is a new discussion scaffolding application designed to aid student knowledge acquisition, promote reflection about course topics and encourage student participation in discussions. It dynamically processes student discussions and presents related discussions from a knowledge base of past discussions. This paper describes the system and presents a comparative analysis of the information retrieval techniques used to respond to free-form student discussions, a combination of topic profiling, term frequency-inverse document frequency, and latent semantic analysis. Responses are presented as annotated links that students can follow and rate. We report a pilot study of PedaBot based on student viewings, student ratings, and a small survey. Initial results indicate that there is a high level of student interest in the feature and that its responses are moderately relevant to student discussions.

This document explains the overall research direction of my dissertation. Because this direction is different from most research today in mainstream NLP, I spend a

Question Answering (QA) is the task of searching a large text collection for specific answers to questions posed in natural language. Many QA systems rely heavily on Natural Language Processing (NLP) technology, such as syntactic and semantic parsing and named entity recognition, for question analysis and for answer generation. To access the text collection, QA systems often use off-the-shelf bag-of-words Information Retrieval (IR) solutions, which rank results by matching a set of keyterms extracted from the question. There is a fundamental disconnect between the capabilities of the bag-of-words retrieval model and the retrieval needs of the QA system. Bag-of-words IR retrieves documents matching a query, but the QA system really needs documents that contain answers. Through question analysis, the QA system has compiled a sophisticated information need representation for what constitutes an answer to the question. This representation is composed of a set of linguistic and semantic constraints

Question Answering systems are systems that enable the user to ask questions in natural language and to also receive an answer in natural language. Most existing systems, however, are constructed for the English language, and it is not clear in how far these approaches are also applicable to other languages. A richer morphology, greater syntactic variability, and smaller fraction of webpages available in the language are just some issues that complicate the construction of systems for German. In this paper, we present a modular Question Answering System for German which uses several morphological resources to increase recall. Nouns are converted into verbs, verbs into nouns, and the tenses of verbs are modified. We use a web search engine as a back end to allow for open-domain Question Answering. A POS-tagger is employed to identify answer candidates which are then filtered and tiled. The system is shown to achieve a higher recall than other systems for German. 1.

We describe how the British National Corpus (BNC), a one hundred million word balanced corpus of British English, was parsed into Lexical Functional Grammar (LFG) c-structures and f-structures, using a treebank-based parsing architecture. The parsing architecture uses a state-of-the-art statistical parser and reranker trained on the Penn Treebank to produce context-free phrase structure trees, and an annotation algorithm to automatically annotate these trees into LFG f-structures. We describe the pre-processing steps which were taken to accommodate the differences between the Penn Treebank and the BNC. Some of the issues encountered in applying the parsing architecture on such a large scale are discussed. The process of annotating a gold standard set of 1,000 parse trees is described. We present evaluation results obtained by evaluating the c-structures produced by the statistical parser against the c-structure gold standard. We also present the results obtained by evaluating the f-structures produced by the annotation algorithm against an automatically constructed f-structure gold standard. The c-structures achieve an f-score of 83.7 % and the f-structures an f-score of 91.2%. 1