Unsupervised Term Extraction for Highly Technical Domains
This work addresses the problem of expensive and scarce annotations for term extraction in technical fields like pharma and material science, offering a competitive baseline for unsupervised scenarios.
The paper tackles the challenge of generalizing term extraction across highly technical domains with scarce annotations by introducing a fully unsupervised annotator that combines morphological signals and similarity metrics, resulting in improved predictive performance and reduced inference latency on CPUs and GPUs.
Term extraction is an information extraction task at the root of knowledge discovery platforms. Developing term extractors that are able to generalize across very diverse and potentially highly technical domains is challenging, as annotations for domains requiring in-depth expertise are scarce and expensive to obtain. In this paper, we describe the term extraction subsystem of a commercial knowledge discovery platform that targets highly technical fields such as pharma, medical, and material science. To be able to generalize across domains, we introduce a fully unsupervised annotator (UA). It extracts terms by combining novel morphological signals from sub-word tokenization with term-to-topic and intra-term similarity metrics, computed using general-domain pre-trained sentence-encoders. The annotator is used to implement a weakly-supervised setup, where transformer-models are fine-tuned (or pre-trained) over the training data generated by running the UA over large unlabeled corpora. Our experiments demonstrate that our setup can improve the predictive performance while decreasing the inference latency on both CPUs and GPUs. Our annotators provide a very competitive baseline for all the cases where annotations are not available.