CAW-coref: Conjunction-Aware Word-level Coreference Resolution

State-of-the-art coreference resolutions systems depend on multiple LLM calls per document and are thus prohibitively expensive for many use cases (e.g., information extraction with large corpora). The leading word-level coreference system (WL-coref) attains 96.6% of these SOTA systems' performance while Figure 1: We identify two types of failure cases for being much more efficient. In this work, we WL-coref when processing conjoined mentions. Our identify a routine yet important failure case of simple solution, CAW-coref, addresses these errors. WL-coref: dealing with conjoined mentions such as Tom and Mary.