Computational Pun-derstanding

Creative language, such as humour and wordplay, is all around us: every day we are amused by clever advertising slogans; our televisions and cinemas play an endless string of eloquent comedies; and literary critics write volumes on the wit of contemporary and classic authors. The ubiquity of creative language, and the constant need for creative professionals to analyze and translate it, would seem to make it a prime candidate for automatic language processing techniques such as machine translation. However, computers have tremendous difficulties in processing the vagaries of creative language. This is because they view anomalies, incongruities, and ambiguities in the input as things that must be resolved in favour of a single correct interpretation, rather than preserved and interpreted in their own right. But if computers cannot translate creative language on their own, can they at least provide specialized support to creative professionals, such as human translators of humour and wordplay? The translation of wordplay is one of the most extensively researched problems in translation studies, but until now it has attracted little attention in the fields of artificial intelligence and language technology. In Computational Pun-derstanding, we will study how professional translators process wordplay, with particular attention to the tools, knowledge sources, and working processes they employ. We will then decompose these processes and look for parts that can be modelled computationally as part of an interactive, computer-assisted translation system. With this machine-in-the-loop paradigm, language technology will be applied only to those subtasks it can perform best, such as searching a large vocabulary space for translation candidates matching certain phonetic and semantic constraints. Subtasks that depend heavily on real-world background knowledgesuch as selecting the candidate that best fits the wider humorous contextwill be left to the human translator. To fulfill this ambitious vision, it will be necessary to develop innovative, interactive techniques for identifying instances of wordplay, interpreting and exploring their semantics, and generating target-language candidates that best preserve the ambiguity and humorousness of the original. The project`s scientific innovation lies in its connection of hitherto separate channels of research: linguistic theories of humour, computational representations and analyses of word meanings, manual translation of wordplay, and computer-assisted translation technologies. Besides providing new insights into the linguistic processes and translation strategies for wordplay, the research has the potential to significantly ease the burdens borne by professional translators in the processing of creative language, fostering creative solutions to unorthodox translation problems.

Humour and wordplay are ubiquitous in literature, television shows, movies, and advertising. The constant need for creative professionals to produce, analyze, and translate this material makes it a prime candidate for language technology such as machine translation. However, computers have tremendous difficulties in processing the vagaries of creative language. This is because they view anomalies, incongruities, and ambiguities in the source text as things that must be resolved in favour of a single "correct" interpretation, rather than preserved and interpreted in their own right. But if computers cannot translate creative language on their own, can they at least provide specialized support to creative professionals, such as human translators? The goal of our project was to study how human translators process wordplay, with particular attention to their tools, knowledge sources, and working processes, and then to model these processes computationally as part of an interactive, computer-assisted translation system. With this "machine-in-the-loop" paradigm, language technology is applied only to those subtasks it performs best, leaving the "essentially human" aspects of the translation to the user. The translation system we developed, PunCAT, automatically translates each sense of a play on words separately. It then allows the user to interactively explore the semantic neighbourhoods of these translations. This helps the translator produce wordplay in the target language that best preserves the meaning, or at least the overall intent, of the original text. We evaluated PunCAT in a pilot study in which human translators translated English puns into German, with and without computer assistance. Our triangulation of software logs, questionnaires, translators' notes, and target texts provided a robust basis to trace the users' interaction with the system. We found good evidence that PunCAT can effectively support the translation process in terms of facilitating brainstorming, stimulating creative thinking, and providing inspiration. PunCAT also broadened the translators' pool of solution candidates by opening up larger semantic fields than traditional dictionary searches. That said, the study also showed that working styles and processes differ considerably across individuals, and that PunCAT might be more suitable for some working styles than others. In bringing together natural language processing and cognitive approaches, we aimed to answer the clarion call that the development of computer aids for translators take better account of the users' actual working processes and practical needs. We consider the further integration of the two fields as a promising way forward to support translation in general and this rather exceptional class of translation problems in particular.