Chatterbox challenge as a test-bed for synthetic emotions

Chatterbox Challenge is an annual web-based contest for artificial conversational systems, ACE. The 2010 instantiation was the tenth consecutive contest held between March and June in the 60th year following the publication of Alan Turing’s influential disquisition ‘computing machinery and intelligence’. Loosely based on Turing’s viva voca interrogator-hidden witness imitation game, a thought experiment to ascertain a machine’s capacity to respond satisfactorily to unrestricted questions, the contest provides a platform for technology comparison and evaluation. This paper provides an insight into emotion content in the entries since the 2005 Chatterbox Challenge. The authors find that synthetic textual systems, none of which are backed by academic or industry funding, are, on the whole and more than half a century since Weizenbaum’s natural language understanding experiment, little further than Eliza in terms of expressing emotion in dialogue. This may be a failure on the part of the academic AI community for ignoring the Turing test as an engineering challenge.

Antoine de La Sale's 'La Sale': the cannonball and the prince's head

The elderly tutor La Sale's didactic treatise for his charges (dated 1451) includes an eye-witness account of the siege of Anjou-held Naples by the Aragonese in 1438. It narrates the accidental death (or miracle, depending on the perspective of the chroniclers) of the infante Pedro of Castille, brother of King Alfonso the Magnanimous of Aragon. This article explores how "La Sale", an adapted version of the Middle French translation of Valerius Maximus's 'Facta et dicta memorabilia', frames and skews the anecdote towards an exploration of the reliability and authority of the tutor-narrator.

Deception-detection and machine intelligence in practical Turing tests

Deception-detection is the crux of Turing’s experiment to examine machine thinking conveyed through a capacity to respond with sustained and satisfactory answers to unrestricted questions put by a human interrogator. However, in 60 years to the month since the publication of Computing Machinery and Intelligence little agreement exists for a canonical format for Turing’s textual game of imitation, deception and machine intelligence. This research raises from the trapped mine of philosophical claims, counter-claims and rebuttals Turing’s own distinct five minutes question-answer imitation game, which he envisioned practicalised in two different ways: a) A two-participant, interrogator-witness viva voce, b) A three-participant, comparison of a machine with a human both questioned simultaneously by a human interrogator. Using Loebner’s 18th Prize for Artificial Intelligence contest, and Colby et al.’s 1972 transcript analysis paradigm, this research practicalised Turing’s imitation game with over 400 human participants and 13 machines across three original experiments. Results show that, at the current state of technology, a deception rate of 8.33% was achieved by machines in 60 human-machine simultaneous comparison tests. Results also show more than 1 in 3 Reviewers succumbed to hidden interlocutor misidentification after reading transcripts from experiment 2. Deception-detection is essential to uncover the increasing number of malfeasant programmes, such as CyberLover, developed to steal identity and financially defraud users in chatrooms across the Internet. Practicalising Turing’s two tests can assist in understanding natural dialogue and mitigate the risk from cybercrime.

Gallic war songs (II): Marcus Cicero, Quintus Cicero, and Caesar’s invasion of Britain

This article assembles and examines the evidence for the poetic outputs of Marcus and Quintus Cicero related to Caesar’s invasion of Britain. Following the establishment of a relative chronology of the evidence for their work, it is argued that Quintus Cicero most likely produced a fabula praetexta (not an epic poem, as commonly assumed). His brother, in turn, wrote an epic, based on Quintus’ eye-witness reports. Careful analysis of the ancient discourse about this piece reveals insights in Cicero’s poetic workshop and the creation of ‘archival truth’ through narrativising historical events in epic poetry. Finally, a case is made for greater attention to financial affairs between Caesar and the Ciceros that happen to coincide with the drafting process of their respective literary works.

The Earls of Kildare and their books at the end of the Middle Ages

The two surviving inventories of the library of the Fitzgerald Earls of Kildare bear witness to a particularly large and diverse collection of books in the Earls' castle at Maynooth, Co. Kildare. Between them, the lists record well over one hundred separate items in four languages: Latin, French, English and Irish. This paper traces the history of the library and analyses the Fitzgeralds' particular interests as book collectors and as readers. It provides the first full published set of suggested identifications and bibliographical details for the books at Maynooth. It also includes a fresh transcription of the library lists and a discussion of the manuscript context in which they are preserved. Sources like the Kildare library lists provide valuable evidence for the potential circulation of a wide range of non-native manuscripts and prints in late-medieval Ireland.

Family, locality and nationality: vernacular adaptations of the Expugnatio Hibernica from late medieval Ireland

This paper examines two late medieval abridgements of Gerald of Wales’ Expugnatio Hibernica, one in Hiberno-English and one in Irish. The manuscripts in which these adaptations survive all date from the late fifteenth century and appear to bear witness to a sudden and pronounced interest in Gerald’s text. Drawing on evidence from the extant manuscripts, this paper explores the readerships of, and the nature of their interest in, these adaptations. A key conclusion is that the Expugnatio, which gives prominence to Gerald's own relatives, the Fitzgeralds, was valued as a family history by the Fitzgerald Earls of Kildare and their allies. The Earls were at the height of their power in the period in which these manuscripts were produced. Examination of this neglected evidence of the adaptation and readership of the Expugnatio in late medieval Ireland suggests that, for some medieval readers at least, the primary identities Gerald’s text expressed were familial and local rather than colonial or national.

A lost insular version of the romance of Octavian

This article is the first full examination of the Irish translation of the popular and influential medieval romance "Octavian". I argue that the source for this Irish translation was an insular version of the romance, probably in Middle English. I show how the Irish translator incorporated material from another romance, "Fierabras", in order to introduce the characters of Charlemagne and his vassals into the story. This is the only version of "Octavian" that gives the text a Carolingian setting. I also demonstrate that the version of the romance from which the Irish translation was produced differed in significant ways from any of the surviving versions in other languages. I suggest that the Irish translation provides our only witness to a lost variant version of "Octavian" and, as such, extends our knowledge of the corpus of insular romance in the Middle Ages.

The circulation of romances from England in late-medieval Ireland

The fifteenth century saw a striking upturn in the number of texts from foreign vernaculars that were translated into Irish. Indeed, one might go so far as to speak in terms of a ‘translation trend’ in Ireland during the mid to late fifteenth century. A notable feature of this trend is that a particularly high number of these Irish translations are of romances; contextual and textual evidence suggests that the original exemplars for many of these translated texts appear to have come from England, though not all of them were necessarily in English. Irish translations of eight romances have survived to the present day: Guy of Warwick; Bevis of Hampton; La Queste de Saint Graal; Fierabras; Caxton’s Recuyell of the Histories of Troie; William of Palerne; the Seven Sages of Rome; and Octavian. This paper addresses two aspects of these texts of particular relevance to romance scholars who do not work within the sphere of Celtic studies. Firstly, it argues that certain aspects of the dissemination and reception of romance in Ireland are quite distinctive. Manuscript and textual evidence suggests that the religious orders, particularly the Franciscans, seem to have played a role in the importation and translation of these narratives. Secondly, examination of the Irish versions of romance tends to bear out an observation made by Flower many years ago, but not pursued by subsequent scholars: ‘texts of an unusual kind were current in Ireland, and it may be that interesting discoveries are to be made here’. Certain narrative features of several of these Irish translations diverge from all the surviving versions of the relevant romance in other languages and may witness to a variant exemplar that has since been lost from its own linguistic corpus.