Lingotowns, a new gaming platform targeting language learners developed by the DALI team. Lingotowns provides a unified experience integrating games for multiple aspects of lexical and grammatical experience in a single virtual world, whilst simultaneously collecting judgements. Both Lingotowns and its constituent games are designed to provide more engagement to the players/ learners than normal GWAPs. The platform also incorporates knowledge tracing methods ensuring that the players' progress in terms of understanding of grammatical concepts is tracked both at the individual game level and overall.
Natural language expressions are supposed to be unambiguous in context. Yet more
and more examples of use of expressions that are ambiguous in context, yet felicitous and rhetorically
unmarked, are emerging. In previous work, we demonstrated that ambiguity in anaphoric reference is
ubiquitous, through the study of disagreements in annotation, that we pioneered in CL. Since then,
additional cases of ambiguous anaphoric reference have been found; and similar findings have been made
for other aspects of language interpretation, including wordsense disambiguation, and even
part-of-speech tagging. Using the Phrase Detectives Game-With-A-Purpose to collect massive amounts of
judgments online, we found that up to 30% of anaphoric expressions in our data are ambiguous. These
findings raise a serious challenge for computational linguistics (CL), as assumptions about the
existence of a single interpretation in context are built in the dominant methodology, that depends on a
reliably annotated gold standard.
The goal of DALI is to tackle this fundamental issue of disagreements in interpretation by using
computational methods for collecting and analysing such disagreements, some of which already exist but
have never before been applied in linguistics on a large scale, some we will develop from scratch. First
of all, we will develop more advanced games-with-a-purpose to collect massive amounts of data about
anaphora from people playing a game.
Secondly, we will use Bayesian models of annotation, widely used in epidemiology but not in linguistics,
to analyse such data and identify genuine ambiguities; doing this for anaphora will require novel
methods. Third, we will use these data to revisit current theories about anaphoric expressions that do
not seem to cause infelicitousness when ambiguous. Finally, we intend to develop the first supervised
approach to anaphora resolution that does not require a gold standard as a blueprint for other areas.
