Speech interfaces using LVCSR system have promise for improving the utility of Open-domain Question Answering, in which natural language questions about diversified topics are used as inputs. In this paper, we propose a method to improve both speech recognition and question answering performance by incorporating the passage retrieval, which is a component common to many QA systems, with respect...

Clinicians have minimal time to search for and absorb the information needed while performing duties of their medical practice. Their time-pressured situations requires relevant in be retrieved presented a more succinct form, such as short passage, rather than whole page or document. In this context, clinical decision support (CDS) searches are beneficial when used retrieve critical passages th...

Conversational passage retrieval relies on question rewriting to modify the original so that it no longer depends conversation history. Several methods for have recently been proposed, but they were compared under different pipelines. We bridge this gap by thoroughly evaluating those TREC CAsT 2019 and 2020 datasets same pipeline. analyze effect of types performance show combining we can achiev...

Passage Retrieval (PR) is typically used as the first step in current Question Answering (QA) systems. Most methods are based on the vector space model allowing the finding of relevant passages for general user needs, but failing on selecting pertinent passages for specific user questions. This paper describes a simple PR method specially suited for the QA task. This method considers the struct...

Document or passage retrieval is typically used as the first step in current question answering systems. The accuracy of the answer that is extracted from the passages and the efficiency of the question answering process will depend to some extent on the quality of this initial ranking. We show how language model approaches can be used to improve answer passage ranking. In particular, we show h...

We report on the result of investigating which relationship is important among hypernym and hyponym relationships in retrieval keyword expansion. Moreover, we report the effect of the keyword expansion and the contents complement for spoken document retrieval for SCR lecture retrieval task and SCR passage retrieval task. Spoken Document Retrieval by contents complement and keyword expansion usi...

An analysis is provided for three major components of a simple Chinese Question-Answering system: passage retrieval, entity extraction and candidate selection. The order of least effective component is determined to be: answer selection, retrieval and extraction. In crosslingual QA, deficiencies in question translation not only lead to retrieval loss, but may also have adverse effects at answer...

TF*IDF-based methods, as they are easily to implement, are widely accepted in information retrieval industry. It is interesting to investigate a feasible and practical technique to improve the retrieval performance of these conventional IR methods. In this paper, we are going to introduce a good alternative approach that uses passage-based ranking as the second stage of the retrieval process in...

TF*IDF-based methods, as they are easily to implement, are widely accepted in information retrieval industry. It is interesting to investigate a feasible and practical technique to improve the retrieval performance of these conventional IR methods. In this paper, we are going to introduce a good alternative approach that uses passage-based ranking as the second stage of the retrieval process in...

UIUC participated in the HARD track in TREC 2004 and focused on the evaluation of a new method for identifying variable-length passages using HMMs. Most existing approaches to passage retrieval rely on pre-segmentation of documents, but the optimal boundaries of a relevant passage depends on both the query and the document. Our new method aims at determining or improving the boundaries of a rel...