Niklas Stoehr, Pengxiang Cheng, Jing Wang, Daniel Preotiuc-Pietro, Rajarshi Bhowmik. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Free-form, unstructured and semi-structured textual data has become increasingly more prevalent in the telecommunications industry, with service and equipment providers alike. Some typical examples include textual data from customer care tickets, machine logs, alarm and alerting systems, and diagnostics. There is a growing business need to rapidly and automatically understand the underlying key topics and categories of this bulk collection of text. With the present mode of operation of relying on domain experts to analyze textual data, there is a clear need to apply text analytics to automate the process. Difficulties arise due to the jargon-filled and fragmented, incomplete nature of textual data in this field. In this paper, we propose a domain-agnostic, unsupervised approach that deploys a multi-stage text processing pipeline for automatically discovering the key topics and categories from free-form text documents. Using anonymized datasets retrieved from actual customer care tickets and system logs, we show that our approach outperforms traditional text mining approaches, and performs comparably to manual categorization tasks that were undertaken by domain experts with full system knowledge.

Despite being vast repositories of factual information, cross-domain knowledge graphs, such as Wikidata and the Google Knowledge Graph, only sparsely provide short synoptic descriptions for entities. Such descriptions that briefly identify the most discernible features of an entity provide readers with a near-instantaneous understanding of what kind of entity they are being presented. They can also aid in tasks such as named entity disambiguation, ontological type determination, and answering entity queries. Given the rapidly increasing numbers of entities in knowledge graphs, a fully automated synthesis of succinct textual descriptions from underlying factual information is essential. To this end, we propose a novel fact-to-sequence encoder-decoder model with a suitable copy mechanism to generate concise and precise textual descriptions of entities. In an in-depth evaluation, we demonstrate that our method significantly outperforms state-of-the-art alternatives.

While large-scale knowledge graphs provide vast amounts of structured facts about entities, a short textual description can often be useful to succinctly characterize an entity and its type.Unfortunately, many knowledge graph entities lack such textual descriptions.In this paper, we introduce a dynamic memory-based network that generates a short open vocabulary description of an entity by jointly leveraging induced fact embeddings as well as the dynamic context of the generated sequence of words.We demonstrate the ability of our architecture to discern relevant information for more accurate generation of type description by pitting the system against several strong baselines.