Model-based Answer Selection
نویسندگان
چکیده
Obtaining informative answer passages and ranking them appropriately has previously been error prone for complex, non-factoid questions related to action and event occurrences, causes, and spatiotemporal attributes. A fundamental problem that has hampered the efforts to date has been the inability to extract relations of interest that determine the search for relevant answer passages. We report on a model-based approach to answer selection based on the idea that relations relevant to a question are best captured by an expressive model of events. We outline the essential attributes of the model and report on its application to the AQUAINT focused data corpus for Question Answering.
منابع مشابه
The Role of Management Skills in the Selection of Management Model by Sports Managers
Background. Despite the research being accomplished so far, there is no clear answer to the question that "Do management skills have effect in the selection of management model by sports managers". Objective(s). The present study aims to investigate the effect of technical, human, perceptual, and political skills on the selection of managerial model by sports managers. Methods. This...
متن کاملUniversity of Hagen at CLEF 2007: Answer Validation Exercise
MAVE (Multinet-based Answer VErification) is an answer validation system based on deep linguistic processing and logical inference originally developed for AVE 2006. Robustness of the entailment check is obtained by embedding the theorem prover in a constraint relaxation loop. The system can also be used for answer selection, which is then guided by the joint evidence of all available text pass...
متن کاملLearning Unsupervised SVM Classifier for Answer Selection in Web Question Answering
Previous machine learning techniques for answer selection in question answering (QA) have required question-answer training pairs. It has been too expensive and labor-intensive, however, to collect these training pairs. This paper presents a novel unsupervised support vector machine (USVM) classifier for answer selection, which is independent of language and does not require hand-tagged trainin...
متن کاملRepresentation Learning for Answer Selection with LSTM-Based Importance Weighting
We present an approach to non-factoid answer selection with a separate component based on BiLSTM to determine the importance of segments in the input. In contrast to other recently proposed attention-based models within the same area, we determine the importance while assuming the independence of questions and candidate answers. Experimental results show the effectiveness of our approach, which...
متن کاملTo Calculate or Not to Calculate: A Source Activation Confusion Model of Problem Familiarity's Role in Strategy Selection
How do people decide whether to try to retrieve an answer to a problem or to compute the answer by some other means? The authors report 2 experiments showing that this decision is based on problem familiarity rather than on retrievability of some answer (correct or incorrect), even when problem familiarization occurred 24 hr earlier. These effects at the level of the individual problem solver a...
متن کامل