Lune

EMNLP Findings2020

Adapting Coreference Resolution to Twitter Conversations

Berfin Aktas, Veronika Solopova, Annalena Kohnert, Manfred Stede

Abstract

The performance of standard coreference resolution is known to drop significantly on Twitter texts. We improve the performance of the (Lee et al., 2018) system, which is originally trained on OntoNotes, by retraining on manually-annotated Twitter conversation data. Further experiments by combining different portions of OntoNotes with Twitter data show that selecting text genres for the training data can beat the mere maximization of training data amount. In addition, we inspect several phenomena such as the role of deictic pronouns in conversational data, and present additional results for variant settings. Our best configuration improves the performance of the "out of the box" system by 21.6%.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Moving on from OntoNotes: Coreference Resolution Model TransferPatrick Xia, Benjamin Van DurmeEMNLP 2021 · 23 citations
  2. Who are you referring to? Coreference resolution in image narrationsArushi Goel, Basura Fernando, Frank Keller, Hakan BilenICCV 2023 · 8 citations

Related papers

  1. Parallel Data Helps Neural Entity Coreference ResolutionGongbo Tang, Christian HardmeierACL Findings 2023 · 5 citations
  2. Interpretable Coreference Resolution Evaluation Using Explicit SemanticsBruno Gatti, Giuliano Martinelli, Roberto NavigliACL 2026
  3. Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social MediaXiang Dai, Sarvnaz Karimi, Ben Hachey, Cécile ParisEMNLP Findings 2020 · 44 citations
  4. Seq2seq is All You Need for Coreference ResolutionWenzheng Zhang, Sam Wiseman, Karl StratosEMNLP 2023 · 5 citations
  5. End-to-End Neural Discourse Deixis Resolution in DialogueShengjie Li, Vincent NgEMNLP 2022
Dusk over the sea between two cliffs drawn in fine vertical lines