This paper describes a research aimed at unveiling the role of Semantic Models in Question Answering. In these systems questions and answers are often expressed in quite different languages, so our objective is to bridge this ”lexical chasm” adopting semantic representations. The aim of the research is to find out if Semantc Models are useful for this task and if they can improve the answer re-...

The Legislature required the Controller to contract with actuaries for California's first valuation of unfunded state retiree health liabilities. reported that the state's estimated unfunded liabilities total $48 billion. This report answers key questions concerning the valuation and identifies actions the Legislature could take to address the state's liabilities. Analyst's Office (LAO) is a no...

The field of Artificial Intelligence (AI) has undergone many transformations, most recently the emergence of data-driven approaches centred on machine learning technology. The present article examines that paradigm shift by using the conceptual tools developed by Thomas Kuhn, and by analysing the contents of the longest running conference series in the field. A paradigm shift occurs when a new ...

We propose to use question answering (QA) data from Web forums to train chatbots from scratch, i.e., without dialog training data. First, we extract pairs of question and answer sentences from the typically much longer texts of questions and answers in a forum. We then use these shorter texts to train seq2seq models in a more efficient way. We further improve the parameter optimization using a ...

Passage Retrieval is a crucial step in question answering systems, one that has been well researched in the past. Due to the vocabulary mismatch problem and independence assumption of bag-of-words retrieval models, correct passages are often ranked lower than other incorrect passages in the retrieved list. Whereas in previous work, passages are reranked only on the basis of syntactic structures...

In this paper we describe and evaluate a Question Answering system that goes beyond answering factoid questions. We focus on FAQlike questions and answers, and build our system around a noisy-channel architecture which exploits both a language model for answers and a transformation model for answer/question terms, trained on a corpus of 1 million question/answer pairs collected from the Web.

The interaction between intonational marking (focus) and domain restriction in adverbial quantiication has been a matter of debate for a number of years. Most theories assume some semantic representation of focus that innuences the interpretation of quantiiers. Views on this interdependence range from a direct mapping of descriptive content between the two representations to a more indirect int...

A two-player one-round binary game consists of two cooperative players who each one replies by one bit to a message that receives privately; they win the game if both questions and answers satisfy some predetermined property. A game is called entangled if the players are allowed to share a priori entanglement. It is well-known that the maximum winning probability (the value) of entangled XOR-ga...

Social question and answer (Q&A) sites receive tens of thousands of questions each day, producing a mix of archival information, asker satisfaction, and, sometimes, frustration. This paper builds upon several recent research efforts that have explored the nature and qualities of questions asked on these social Q&A sites by offering a focused examination of answers posted to three of the most po...

A question/answer discussion session was conducted at the conclusion of the workshop “Pest Management During Transition to Organic Farming Systems”. The following categories were used to summarize the discussion: 1) questions and answers related to cultural and biological practices and their effects under various climatic conditions, 2) recommendations for pest management, and 3) future researc...