Abstract Automatic dialog systems have become a mainstream part of online customer service. Many such systems are built, maintained, and improved by customer service specialists, rather than dialog systems engineers and computer programmers. As conversations between people and machines become commonplace, it is critical to understand what is working, what is not, and what actions can be taken to reduce the frequency of inappropriate system responses. These analyses and recommendations need to be presented in terms that directly reflect the user experience rather than the internal dialog processing. This paper introduces and explains the use of Actionable Conversational Quality Indicators (ACQIs), which are used both to recognize parts of dialogs that can be improved and to recommend how to improve them. This combines benefits of previous approaches, some of which have focused on producing dialog quality scoring while others have sought to categorize the types of errors the dialog system is making. We demonstrate the effectiveness of using ACQIs on LivePerson internal dialog systems used in commercial customer service applications and on the publicly available LEGOv2 conversational dataset. We report on the annotation and analysis of conversational datasets showing which ACQIs are important to fix in various situations. The annotated datasets are then used to build a predictive model which uses a turn-based vector embedding of the message texts and achieves a 79% weighted average f1-measure at the task of finding the correct ACQI for a given conversation. We predict that if such a model worked perfectly, the range of potential improvement actions a bot-builder must consider at each turn could be reduced by an average of 81%.

This paper explores text classification on quantum computers. Previous results have achieved perfect accuracy on an artificial dataset of 100 short sentences, but at the unscalable cost of using a qubit for each word. This paper demonstrates that an amplitude encoded feature map combined with a quantum support vector machine can achieve 62% average accuracy predicting sentiment using a dataset of 50 actual movie reviews. This is still small, but considerably larger than previously-reported results in quantum NLP.

In the decade since 2010, successes in artificial intelligence have been at the forefront of computer science and technology, and vector space models have solidified a position at the forefront of artificial intelligence. At the same time, quantum computers have become much more powerful, and announcements of major advances are frequently in the news. The mathematical techniques underlying both these areas have more in common than is sometimes realized. Vector spaces took a position at the axiomatic heart of quantum mechanics in the 1930s, and this adoption was a key motivation for the derivation of logic and probability from the linear geometry of vector spaces. Quantum interactions between particles are modelled using the tensor product, which is also used to express objects and operations in artificial neural networks. This paper describes some of these common mathematical areas, including examples of how they are used in artificial intelligence (AI), particularly in automated reasoning and natural language processing (NLP). Techniques discussed include vector spaces, scalar products, subspaces and implication, orthogonal projection and negation, dual vectors, density matrices, positive operators, and tensor products. Application areas include information retrieval, categorization and implication, modelling word-senses and disambiguation, inference in knowledge bases, decision making, and and semantic composition. Some of these approaches can potentially be implemented on quantum hardware. Many of the practical steps in this implementation are in early stages, and some are already realized. Explaining some of the common mathematical tools can help researchers in both AI and quantum computing further exploit these overlaps, recognizing and exploring new directions along the way.This paper describes some of these common mathematical areas, including examples of how they are used in artificial intelligence (AI), particularly in automated reasoning and natural language processing (NLP). Techniques discussed include vector spaces, scalar products, subspaces and implication, orthogonal projection and negation, dual vectors, density matrices, positive operators, and tensor products. Application areas include information retrieval, categorization and implication, modelling word-senses and disambiguation, inference in knowledge bases, and semantic composition. Some of these approaches can potentially be implemented on quantum hardware. Many of the practical steps in this implementation are in early stages, and some are already realized. Explaining some of the common mathematical tools can help researchers in both AI and quantum computing further exploit these overlaps, recognizing and exploring new directions along the way.

Word order is clearly a vital part of human language, but it has been used comparatively lightly in distributional vector models.This paper presents a new method for incorporating word order information into word vector embedding models by combining the benefits of permutation-based order encoding with the more recent method of skip-gram with negative sampling.The new method introduced here is called Embeddings Augmented by Random Permutations (EARP).It operates by applying permutations to the coordinates of context vector representations during the process of training.Results show an 8% improvement in accuracy on the challenging Bigger Analogy Test Set, and smaller but consistent improvements on other analogy reference sets.These findings demonstrate the importance of order-based information in analogical retrieval tasks, and the utility of random permutations as a means to augment neural embeddings.

Ontologies are widely used in several areas with applications including knowledge Management, Web commerce and electronic business. An ontology provides a consensus of concept specifications for a specific domain shared by a group of people. In this paper we deal with Ontology Learning, specifically we aim to adapt the WordNet ontology, a general source of lexical knowledge, to the medical domain. We use for this task a combination of lexico– syntactic pattern, mainly conjunctions of the form “Noun_CJC_Noun”, where CJC can be {and, or, but}. Pairs of words extracted in this fashion are compared to find their similarity in the WordNet noun hierarchy, using a form of the Resnik similarity method. Large scale experiments were conducted by extracting many such pairs of nouns from the Ohsumed corpus and mapping them into WordNet. For a noun pattern like “A or B” we find the lowest common ancestor of A and B by using the hypernym and hyponym links. This enables us to keep the appropriate medical sense of the two words A and B.

Standard IR systems can process queries such as "web NOT internet", enabling users who are interested in arachnids to avoid documents about computing. The documents retrieved for such a query should be irrelevant to the negated query term. Most systems implement this by reprocessing results after retrieval to remove documents containing the unwanted string of letters.This paper describes and evaluates a theoretically motivated method for removing unwanted meanings directly from the original query in vector models, with the same vector negation operator as used in quantum logic. Irrelevance in vector spaces is modelled using orthogonality, so query vectors are made orthogonal to the negated term or terms.As well as removing unwanted terms, this form of vector negation reduces the occurrence of synonyms and neighbours of the negated terms by as much as 76% compared with standard Boolean methods. By altering the query vector itself, vector negation removes not only unwanted strings but unwanted meanings.