The boardgame Diplomacy is a challenging setting for communicative and cooperative artificial intelligence. The most prominent communicative Diplomacy AI, Cicero, has excellent strategic abilities, exceeding human players. However, the best Diplomacy players master communication, not just tactics, which is why the game has received attention as an AI challenge. This work seeks to understand the degree to which Cicero succeeds at communication. First, we annotate in-game communication with abstract meaning representation to separate in-game tactics from general language. Second, we run two dozen games with humans and Cicero, totaling over 200 human-player hours of competition. While AI can consistently outplay human players, AI-Human communication is still limited because of AI’s difficulty with deception and persuasion. This shows that Cicero relies on strategy and has not yet reached the full promise of communicative and cooperative AI.

There are few corpora that endeavor to represent the semantic content of entire documents. We present a corpus that accomplishes one way of capturing document level semantics, by annotating coreference and similar phenomena (bridging and implicit roles) on top of gold Abstract Meaning Representations of sentence-level semantics. We present a new corpus of this annotation, with analysis of its quality, alongside a plausible baseline for comparison. It is hoped that this Multi-Sentence AMR corpus (MS-AMR) may become a feasible method for developing rich representations of document meaning, useful for tasks such as information extraction and question answering.

We present uroman, a tool for converting text in myriads of languages and scripts such as Chinese, Arabic and Cyrillic into a common Latin-script representation. The tool relies on Unicode data and other tables, and handles nearly all character sets, including some that are quite obscure such as Tibetan and Tifinagh. uroman converts digital numbers in various scripts to Western Arabic numerals. Romanization enables the application of string-similarity metrics to texts from different scripts without the need and complexity of an intermediate phonetic representation. The tool is freely and publicly available as a Perl script suitable for inclusion in data processing pipelines and as an interactive demo web page.

In a corruption of John Searle’s famous AI thought experiment, the Chinese Room (Searle, 1980), we twist its original intent by enabling humans to translate text, e.g. from Uyghur to English, even if they don’t have any prior knowledge of the source language. Our enabling tool, which we call the Chinese Room, is equipped with the same resources made available to a machine translation engine. We find that our superior language model and world knowledge allows us to create perfectly fluent and nearly adequate translations, with human expertise required only for the target language. The Chinese Room tool can be used to rapidly create small corpora of parallel data when bilingual translators are not readily available, in particular for low-resource languages.

Source languages with complex word-formation rules present a challenge for statistical machine translation (SMT). In this paper, we take on three facets of this challenge: (1) common stems are fragmented into many different forms in training data, (2) rare and unknown words are frequent in test data, and (3) spelling variation creates additional sparseness problems. We present a novel, lightweight technique for dealing with this fragmentation, based on bilingual data, and we also present a combination of linguistic and statistical techniques for dealing with rare and unknown words. Taking these techniques together, we demonstrate +1.3 and +1.6 BLEU increases on top of strong baselines for Arabic-English machine translation.