Do Lexical and Contextual Coreference Resolution Systems Degrade Differently under Mention Noise? An Empirical Study on Scientific Software Mentions
We present our participation in the SOMD 2026 shared task on cross-document software mention coreference resolution, where our systems ranked second across all three subtasks. We compare two fine-tuning-free approaches: Fuzzy Matching (FM), a lexical string-similarity method, and Context Aware Representations (CAR), which combines mention-level and document-level embeddings. Both achieve competitive performance across all subtasks (CoNLL F1 of 0.94-0.96), with CAR consistently outperforming FM by 1 point on the official test set, consistent with the high surface regularity of software names, which reduces the need for complex semantic reasoning. A controlled noise-injection study reveals complementary failure modes: as boundary noise increases, CAR loses only 0.07 F1 points from clean to fully corrupted input, compared to 0.20 for FM, whereas under mention substitution, FM degrades more gracefully (0.52 vs. 0.63). Our inference-time analysis shows that FM scales superlinearly with corpus size, whereas CAR scales approximately linearly, making CAR the more efficient choice at large scale. These findings suggest that system selection should be informed by both the noise profile of the upstream mention detector and the scale of the target corpus. We release our code to support future work on this underexplored task.
Code (0)
등록된 구현이 없습니다.
Tasks
Coreference ResolutionSimilar Papers 제목 키워드 기반
What happens before and after: Multi-Event Commonsense in Event Coreference Resolution
Event coreference models cluster event mentions pertaining to the same real-world event. Recent models rely on contextualized representations to recognize coreference among lexically or contextually similar mentions. How…
coreference-resolutionCoreference ResolutionEvent Coreference ResolutionSentenceOntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres
SOTA coreference resolution produces increasingly impressive scores on the OntoNotes benchmark. However lack of comparable data following the same scheme for more genres makes it difficult to evaluate generalizability to…
coreference-resolutionCoreference ResolutionLexical Features in Coreference Resolution: To be Used With Caution
Lexical features are a major source of information in state-of-the-art coreference resolvers. Lexical features implicitly model some of the linguistic phenomena at a fine granularity level. They are especially useful for…
coreference-resolutionCoreference ResolutionCoreference Resolution System for Indonesian Text with Mention Pair Method and Singleton Exclusion using Convolutional Neural Network
Neural network has shown promising performance on coreference resolution systems that uses mention pair method. With deep neural network, it can learn hidden and deep relations between two mentions. However, there is no …
coreference-resolutionCoreference ResolutionWord EmbeddingsAn Exercise in Reuse of Resources: Adapting General Discourse Coreference Resolution for Detecting Lexical Chains in Patent Documentation
The Stanford Coreference Resolution System (StCR) is a multi-pass, rule-based system that scored best in the CoNLL 2011 shared task on general discourse coreference resolution. We describe how the StCR has been adapted t…
coreference-resolutionCoreference ResolutionDomain AdaptationNamed Entity Recognition (NER)