paper-with-me

홈 › Papers

Coreference Resolution without Span Representations

2021-01-02 · ACL 2021 5 · Yuval Kirstain, Ori Ram, Omer Levy

The introduction of pretrained language models has reduced many complex task-specific NLP models to simple lightweight layers. An exception to this trend is coreference resolution, where a sophisticated task-specific model is appended to a pretrained transformer encoder. While highly effective, the model has a very large memory footprint -- primarily due to dynamically-constructed span and span-pair representations -- which hinders the processing of complete documents and the ability to train on multiple instances in a single batch. We introduce a lightweight end-to-end coreference model that removes the dependency on span representations, handcrafted features, and heuristics. Our model performs competitively with the current standard model, while being simpler and more efficient.

📄 PDF Abstract BibTeX arXiv:2101.00434

Code (1)

yuvalkirstain/s2e-coref 공식 구현 pytorch

Tasks

coreference-resolutionCoreference Resolution

Similar Papers 제목 키워드 기반

Word-Level Coreference Resolution

2021-09-09 · EMNLP 2021 11 · Vladimir Dobrovolskii

Recent coreference resolution models rely heavily on span representations to find coreference links between word spans. As the number of spans is $O(n^2)$ in the length of text and the number of potential links is $O(n^4…

coreference-resolutionCoreference Resolution

Exploring Span Representations in Neural Coreference Resolution

2020-11-01 · EMNLP (CODI) 2020 11 · Patrick Kahardipraja, Olena Vyshnevska, Sharid Loáiciga

In coreference resolution, span representations play a key role to predict coreference links accurately. We present a thorough examination of the span representation derived by applying BERT on coreference resolution (Jo…

coreference-resolutionCoreference Resolution

SpanBERT: Improving Pre-training by Representing and Predicting Spans

2019-07-24 · TACL 2020 1 · Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S. Weld 외

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the…

Coreference ResolutionLinguistic AcceptabilityNatural Language InferenceOpen-Domain Question Answering+6

End-to-end Neural Coreference Resolution

2017-07-21 · EMNLP 2017 9 · Kenton Lee, Luheng He, Mike Lewis, Luke Zettlemoyer

We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or hand-engineered mention detector. The key idea is to directl…

Coreference Resolution

Higher-order Coreference Resolution with Coarse-to-fine Inference

2018-04-15 · NAACL 2018 6 · Kenton Lee, Luheng He, Luke Zettlemoyer

We introduce a fully differentiable approximation to higher-order inference for coreference resolution. Our approach uses the antecedent distribution from a span-ranking architecture as an attention mechanism to iterativ…

Coreference Resolution