DeepAI AI Chat
Log In Sign Up

Lexical Features in Coreference Resolution: To be Used With Caution

by   Nafise Sadat Moosavi, et al.

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 representing the context of mentions. In this paper we investigate a drawback of using many lexical features in state-of-the-art coreference resolvers. We show that if coreference resolvers mainly rely on lexical features, they can hardly generalize to unseen domains. Furthermore, we show that the current coreference resolution evaluation is clearly flawed by only evaluating on a specific split of a specific dataset in which there is a notable overlap between the training, development and test sets.


page 1

page 2

page 3

page 4


Lexical Generalization Improves with Larger Models and Longer Training

While fine-tuned language models perform well on many tasks, they were a...

BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation

Although neural-based machine translation evaluation metrics, such as CO...

High-dimensional distributed semantic spaces for utterances

High-dimensional distributed semantic spaces have proven useful and effe...

A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification

Current lexical simplification approaches rely heavily on heuristics and...

A Wind of Change: Detecting and Evaluating Lexical Semantic Change across Times and Domains

We perform an interdisciplinary large-scale evaluation for detecting lex...

Revisiting Selectional Preferences for Coreference Resolution

Selectional preferences have long been claimed to be essential for coref...

Target Word Masking for Location Metonymy Resolution

Existing metonymy resolution approaches rely on features extracted from ...