Improving text retrieval precision and answer accuracy in question answering systems

Bilotti, Matthew W.; Nyberg, Eric

doi:10.3115/1641451.1641452

Cited by 10 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along with our relational representation this appears to be the key aspect for the high improvement over basic models. Finally, models for factoid questions using linguistic structures has been carried out in [2,3]. Again, the proposed methods rely on manual design of features whereas our approach is more general for passages and/or answer re-ranking.…”

Section: Related Workmentioning

confidence: 99%

Structural relationships for large-scale learning of answer re-ranking

Severyn

Moschitti

2012

Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Supervised learning applied to answer re-ranking can highly improve on the overall accuracy of question answering (QA) systems. The key aspect is that the relationships and properties of the question/answer pair composed of a question and the supporting passage of an answer candidate, can be efficiently compared with those captured by the learnt model. In this paper, we define novel supervised approaches that exploit structural relationships between a question and their candidate answer passages to learn a re-ranking model. We model structural representations of both questions and answers and their mutual relationships by just using an offthe-shelf shallow syntactic parser. We encode structures in Support Vector Machines (SVMs) by means of sequence and tree kernels, which can implicitly represent question and answer pairs in huge feature spaces. Such models together with the latest approach to fast kernel-based learning enabled the training of our rerankers on hundreds of thousands of instances, which previously rendered intractable for kernelized SVMs. The results on two different QA datasets, e.g., Answerbag and Jeopardy! data, show that our models deliver large improvement on passage re-ranking tasks, reducing the error in Recall of BM25 baseline by about 18%. One of the key findings of this work is that, despite its simplicity, shallow syntactic trees allow for learning complex relational structures, which exhibits a steep learning curve with the increase in the training size.

show abstract

Section: Related Workmentioning

confidence: 99%

Structural relationships for large-scale learning of answer re-ranking

Severyn

Moschitti

2012

Proceedings of the 35th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…In this context, Bilotti and Nyberg [8] emphasize that proponents of the modular architecture naturally view the question-answering task as decomposable, and to a certain extent, it is. The modules, however, can never be fully decoupled, because question analysis and answer extraction components, at least, depend on a common representation for answers and perhaps also a common set of text processing tools.…”

Section: Typical Architecture Of a Question-answering Systemmentioning

confidence: 99%

“…In our case, the expected answer type refers to the named entities returned by ArNER, only paragraphs that contain a Name Entity of the same type that the expected answer type are validated. Hence, the named-entity answer extraction method selects any candidate answer that is an instance of the expected answer type [8]. In fact, almost all the Arabic question-answering systems involve keywords extraction.…”

Section: Table 3: Mapping Question Type To Expected Answer Typementioning

confidence: 99%

A logical representation of Arabic questions toward automatic passage extraction from the Web

Bakari

Bellot

Néji³

2017

Int J Speech Technol

View full text Add to dashboard Cite

With the expanding growth of Arabic electronic data on the web, extracting information, which is actually one of the major challenges of the question-answering, is essentially used for building corpus of documents. In fact, building a corpus is a research topic that is currently referred to among some other major themes of conferences, in Natural Language Processing (NLP), such as, Information Retrieval (IR), Question-Answering (QA), Automatic Summary (AS), etc. Generally, a question-answering system provides various passages to answer the user questions. To make these passages truly informative, this system needs access to an underlying knowledge base; this requires the construction of a corpus. The aim of our research is to build an Arabic question-answering system. In addition, analyzing the question must be the first step. Next, it is essential to retrieve a passage from the web that can serve as an appropriate answer. In this paper, we propose a method to analysis the question and retrieve the passage answer in the Arabic language. For the question analysis, five factual question types are processed. Additionally, our purpose is to experiment with the generation of a logic representation from the declarative form of each question. Several studies, deal with the logic approaches in question-answering, are discussed in other languages than the Arabic language. This representation is very promising because it helps us later in the selection of a justifiable answer. The accuracy of questions that are correctly analyzed and translated into the logic form achieved 64%. And then, the results of passages of texts that are automatically generated achieved an 87% score for accuracy and a 98% score for c@1.

show abstract

“…There is also a very substantial body of work in scoring passages for relevance to a query, e.g., [22][23][24]. This task is not quite the same as scoring a specific candidate answer, but there is a considerable overlap in the kinds of techniques that are relevant to these tasks.…”

Section: Related Workmentioning

confidence: 99%

Textual evidence gathering and analysis

et al. 2012

View full text Add to dashboard Cite

One useful source of evidence for evaluating a candidate answer to a question is a passage that contains the candidate answer and is relevant to the question. In the DeepQA pipeline, we retrieve passages using a novel technique that we call Supporting Evidence Retrieval, in which we perform separate search queries for each candidate answer, in parallel, and include the candidate answer as part of the query. We then score these passages using an assortment of algorithms that use different aspects and relationships of the terms in the question and passage. We provide evidence that our mechanisms for obtaining and scoring passages have a substantial impact on the ability of our question-answering system to answer questions and judge the confidence of the answers. HypothesesWe evaluated the following two hypotheses.Hypothesis 1VAnalyzing passages using a variety of strategies, at different depths of analysis, is significantly more effective than a single scoring strategy. Specifically,

show abstract

Improving text retrieval precision and answer accuracy in question answering systems

Cited by 10 publications

References 9 publications

Structural relationships for large-scale learning of answer re-ranking

Structural relationships for large-scale learning of answer re-ranking

A logical representation of Arabic questions toward automatic passage extraction from the Web

Textual evidence gathering and analysis

Contact Info

Product

Resources

About