Don't understand a measure? Learn it: Structured Prediction for Coreference Resolution optimizing its measures
An interesting aspect of structured prediction is the evaluation of an output structure against the gold standard. Especially in the loss-augmented setting, the need of finding the max-violating constraint has severely limited the expressivity of effective loss functions. In this paper, we trade off exact computation for enabling the use and study of more complex loss functions for coreference resolution. Most interestingly, we show that such functions can be (i) automatically learned also from controversial but commonly accepted coreference measures, e.g., MELA, and (ii) successfully used in learning algorithms. The accurate model comparison on the standard CoNLL-2012 setting shows the benefit of more expressive loss functions.
Code (0)
등록된 구현이 없습니다.
Tasks
coreference-resolutionCoreference ResolutionStructured PredictionSimilar Papers 제목 키워드 기반
Autoregressive Structured Prediction with Language Models
Recent years have seen a paradigm shift in NLP towards using pretrained language models ({PLM}) for a wide range of tasks. However, there are many difficult design decisions to represent structures (e.g. tagged text, cor…
Coreference ResolutionNamed Entity RecognitionNamed Entity Recognition (NER)Prediction+2A Practical Perspective on Latent Structured Prediction for Coreference Resolution
Latent structured prediction theory proposes powerful methods such as Latent Structural SVM (LSSVM), which can potentially be very appealing for coreference resolution (CR). In contrast, only small work is available, mai…
coreference-resolutionCoreference Resolutionfeature selectionStructured Prediction+1The Validity of Coreference-based Evaluations of Natural Language Understanding
In this thesis, I refine our understanding as to what conclusions we can reach from coreference-based evaluations by expanding existing evaluation practices and considering the extent to which evaluation results are eith…
Natural Language UnderstandingType-aware Convolutional Neural Networks for Slot Filling
The slot filling task aims at extracting answers for queries about entities from text, such as "Who founded Apple". In this paper, we focus on the relation classification component of a slot filling system. We propose ty…
coreference-resolutionCoreference ResolutionGeneral ClassificationRelation+5Pairwise Representation Learning for Event Coreference
Natural Language Processing tasks such as resolving the coreference of events require understanding the relations between two text snippets. These tasks are typically formulated as (binary) classification problems over i…
Binary ClassificationCoreference ResolutionEvent Cross-Document Coreference ResolutionRepresentation Learning