This paper describes the retrieval experiments for the main task and list task of the TREC-10 questionanswering track. The question answering system described automatically finds answers to questions in a large document collection. The system uses a two-stage retrieval approach to answer finding based on matching of named entities, linguistic patterns, and keywords. In answering a question, the...

In open domain Question Answering, answer candidates are ranked according to individual features such as matching the answer type expected by the question. We report on a technique based on the fusion of candidate answers and their context into answer neighbourhoods to provide better features for ranking and allow shallow reasoning.

This paper explores one particular limitation common to question answering systems which operate by using induced surface matching text patterns – namely the problems concerned with question specific words appearing within the induced answer extraction pattern. We suggest a solution to this problem by generalising the learned answer extraction patterns to include named entity classes.

According to the matching law, when an animal makes many repeated choices between alternatives, its preferences are in the ratio of the incomes derived from the alternatives. Because matching behavior does not maximize reward, it has been difficult to explain using optimal foraging theory or rational choice theory. Here I show that matching and maximizing can be regarded as two ends of a spec­ ...

In the question-and-answer (Q&A) communities of “China Agricultural Technology Extension Information Platform”, thousands rice-related Chinese questions are newly added every day. The rapid detection same semantic question is key to success a intelligent Q&A system. To allow fast and automatic questions, we propose new method based on Coattention-DenseGRU (Gated Recurrent Unit). Accordi...

This is our third participation in CLEF, this time in the Spanish monolingual Question Answering track. We have continued applying Natural Language Processing techniques for single word conflation. Our approach for Question Answering is based on complex pattern matching either over forms, part-of-speech tags or lemmas of the words involved.

The SQuAD dataset provides a reading comprehension task, with (question, answer, context) pairs. This paper attempts to develop a model to predict the answer for a given question, context pair. In a model inspired by ”Multi-Perspective Context Matching for Machine Comprehension” by Wang et al, this paper achieves 0.47 F1 score on a validation set.

We describe a system to address the MediaEval 2014 C@merata task of natural language queries on classical music scores. Our system first tokenizes the question to tag the musically relevant features in the question using pattern matching. In this stage suitable word replacements are made in the question based on a list of synonyms. Using the tokenized sentence we infer the question type using a...

We present a radically new indexing approach for approximate string matching. The scheme uses the metric properties of the edit distance and can be applied to any other metric between strings. We build a metric space where the sites are the nodes of the suux tree of the text, and the approximate query is seen as a proximity query on that metric space. This permits us nding the R occurrences of ...