Challenge: Pre-training methods like BERT mask individual words or subword units, but many tasks involve reasoning about relationships between two or more spans of text.
Approach: They propose a pre-training method that masks contiguous random spans instead of random tokens to train the span boundary representations to predict the entire content of the masked span.
Outcome: The proposed method outperforms BERT and its better-tuned baselines on span selection tasks and on coreference resolution tasks.

Similar Papers

PairSpanBERT: An Enhanced Language Model for Bridging Resolution (2023.acl-long)

Copied to clipboard

Challenge: bridging resolution is crucial for machine comprehension of discourse entities for various downstream applications.
Approach: They propose a SpanBERT-based pre-trained model specialized for bridging resolution.
Outcome: The proposed model achieves the best results on three evaluation datasets for bridging resolution despite the noise inherent in the automatically generated data .
Span Selection Pre-training for Question Answering (2020.acl-main)

Copied to clipboard

Challenge: Pre-trained BERTs provide large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA).
Approach: They propose a new pre-training task inspired by reading comprehension to better align the pre- training from memorization to understanding.
Outcome: The proposed model outperforms BERT-BASE and BERT LARGE on a new dataset and improves answer prediction F1 by 4 points and supporting fact prediction F1.
Coreference Resolution without Span Representations (2021.acl-short)

Copied to clipboard

Challenge: Pretraining has reduced many complex task-specific NLP models to simple lightweight layers.
Approach: They propose a lightweight end-to-end coreference model that removes the dependency on span representations, handcrafted features, pruning heuristics, and more.
Outcome: The proposed model performs competitively with the current standard model, while being simpler and more efficient.
LinkBERT: Pretraining Language Models with Document Links (2022.acl-long)

Copied to clipboard

Challenge: Existing language model pretraining methods do not capture dependencies or knowledge that span across documents.
Approach: They propose a language model pretraining method that leverages links between documents . they use masked language modeling and document relation prediction to model LMs .
Outcome: The proposed method outperforms existing methods on downstream tasks across two domains.
Improving Span Representation by Efficient Span-Level Attention (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for generating high-quality span representations are limited by subset of tokens . span-span interactions should play an important role in span encoding, authors argue .
Approach: They propose to introduce span-span interactions and more comprehensive span-token interactions to improve span representations.
Outcome: The proposed model outperforms baseline models on span-related tasks and shows superior performance.
Span Fine-tuning for Pre-trained Language Models (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to fine-tune pre-trained language models are time-consuming and lack flexibility.
Approach: They propose a span fine-tuning method which allows for a more efficient and efficient way of incorporating span-level information into pre-training.
Outcome: Experiments on GLUE benchmark show that the proposed method significantly enhances the PrLM and offers more flexibility in an efficient way.
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning (2022.findings-naacl)

Copied to clipboard

Challenge: Existing pre-trained MLMs produce an anisotropic distribution of token representations . this is not ideal for tasks that require discriminative semantic meanings of distinct tokens - a problem that exists in pre-training models .
Approach: They propose a continual pre-training approach that encourages BERT to learn an isotropic distribution of token representations.
Outcome: The proposed approach improves on a wide range of English and Chinese benchmarks.
A Span Selection Model for Semantic Role Labeling (D18-1)

Copied to clipboard

Challenge: Existing models for semantic role labeling use BIO tags to predict argument spans . but performance of these approaches is weak .
Approach: They propose a span-based model that takes into account all possible argument spans and scores them for each label.
Outcome: The proposed model achieves state-of-the-art results on the CoNLL-2005 and 2012 datasets.
LuxemBERT: Simple and Practical Data Augmentation in Language Model Pre-Training for Luxembourgish (2022.lrec-1)

Copied to clipboard

Challenge: Pre-trained Language Models such as BERT are ubiquitous in NLP but are scarce for low-resource languages such as Luxembourgish.
Approach: They propose a BERT model for Luxembourgish language that they use to augment pre-training datasets by partially translating text data from a closely related language.
Outcome: The proposed model outperforms the baseline model and the mBERT model in Luxembourgish.
NarrowBERT: Accelerating Masked Language Model Pretraining and Inference (2023.acl-short)

Copied to clipboard

Challenge: Large-scale language model pretraining is expensive as the models and pretraining corpora have become larger over time.
Approach: They propose a modified transformer encoder that increases throughput for masked language model pretraining by more than 2x.
Outcome: The proposed model increases throughput on IMDB and Amazon reviews classification and CoNLL NER tasks by 3.5x with minimal performance degradation.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations