The Sumerian cuneiform script was invented more than 5,000 years ago and represents one of the oldest in history. We present the first attempt to translate Sumerian texts into English automatically. We publicly release high-quality corpora for standardized training and evaluation and report results on experiments with supervised, phrase-based, and transfer learning techniques for machine translation. Quantitative and qualitative evaluations indicate the usefulness of the translations. Our proposed methodology provides a broader audience of researchers with novel access to the data, accelerates the costly and time-consuming manual translation process, and helps them better explore the relationships between Sumerian cuneiform and Mesopotamian culture.
Memory-based acquisition of argument structures and its application to implicit role detection
(2015)
Linguistic Linked Open Data (LLOD) is a flourishing line of research in the language resource community, so far mostly adopted for selected aspects of linguistics, natural language processing and the semantic web, as well as for practical applications in localization and lexicography. Yet, computational philology seems to be somewhat decoupled from the recent progress in this area: even though LOD as a concept is gaining significant popularity in Digital Humanities, existing LLOD standards and vocabularies are not widely used in this community, and philological resources are underrepresented in the LLOD cloud diagram (http://linguistic-lod.org/llod-cloud). In this paper, we present an application of Linguistic Linked Open Data in Assyriology. We describe the LLOD edition of a linguistically annotated corpus of Sumerian, as well as its linking with lexical resources, repositories of annotation terminology, and the museum collections in which the artifacts bearing these texts are kept. The chosen corpus is the Electronic Text Corpus of Sumerian Royal Inscriptions, a well curated and linguistically annotated archive of Sumerian text, in preparation for the creating and linking of other corpora of cuneiform texts, such as the corpus of Ur III administrative and legal Sumerian texts, as part of the Machine Translation and Automated Analysis of Cuneiform Languages project (https://cdli-gh.github.io/mtaac/).
This paper describes work on the morphological and syntactic annotation of Sumerian cuneiform as a model for low resource languages in general. Cuneiform texts are invaluable sources for the study of history, languages, economy, and cultures of Ancient Mesopotamia and its surrounding regions. Assyriology, the discipline dedicated to their study, has vast research potential, but lacks the modern means for computational processing and analysis. Our project, Machine Translation and Automated Analysis of Cuneiform Languages, aims to fill this gap by bringing together corpus data, lexical data, linguistic annotations and object metadata. The project’s main goal is to build a pipeline for machine translation and annotation of Sumerian Ur III administrative texts. The rich and structured data is then to be made accessible in the form of (Linguistic) Linked Open Data (LLOD), which should open them to a larger research community. Our contribution is two-fold: in terms of language technology, our work represents the first attempt to develop an integrative infrastructure for the annotation of morphology and syntax on the basis of RDF technologies and LLOD resources. With respect to Assyriology, we work towards producing the first syntactically annotated corpus of Sumerian.
This paper describes our contribution to the Third Shared Task on Translation Inference across Dictionaries (TIAD-2020). We describe an approach on translation inference based on symbolic methods, the propagation of concepts over a graph of interconnected dictionaries: Given a mapping from source language words to lexical concepts (e.g., synsets) as a seed, we use bilingual dictionaries to extrapolate a mapping of pivot and target language words to these lexical concepts. Translation inference is then performed by looking up the lexical concept(s) of a source language word and returning the target language word(s) for which these lexical concepts have the respective highest score. We present two instantiations of this system: One using WordNet synsets as concepts, and one using lexical entries (translations) as concepts. With a threshold of 0, the latter configuration is the second among participant systems in terms of F1 score. We also describe additional evaluation experiments on Apertium data, a comparison with an earlier approach based on embedding projection, and an approach for constrained projection that outperforms the TIAD-2020 vanilla system by a large margin.
A recurrent neural model with attention for the recognition of Chinese implicit discourse relations
(2017)
We introduce an attention-based Bi-LSTM for Chinese implicit discourse relations and demonstrate that modeling argument pairs as a joint sequence can outperform word order-agnostic approaches. Our model benefits from a partial sampling scheme and is conceptually simple, yet achieves state-of-the-art performance on the Chinese Discourse Treebank. We also visualize its attention activity to illustrate the model’s ability to selectively focus on the relevant parts of an input sequence.
We present a resource-lean neural recognizer for modeling coherence in commonsense stories. Our lightweight system is inspired by successful attempts to modeling discourse relations and stands out due to its simplicity and easy optimization compared to prior approaches to narrative script learning. We evaluate our approach in the Story Cloze Test demonstrating an absolute improvement in accuracy of 4.7% over state-of-the-art implementations.
