NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents (2024.acl-long)
Copied to clipboard
| Challenge: | (large) language models struggle to process long sequences due to the quadratic scaling of the underlying attention mechanism. |
| Approach: | They propose a Masked Language Model operating on higher-level semantic representations in the form of text embeddings to solve this problem. |
| Outcome: | The proposed model outperforms larger embedding models on three types of tasks. |
Similar Papers
CDLM: Cross-Document Language Modeling (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing language models (LMs) provide powerful representations for internal text structure, but there are important applications for multi-text tasks. |
| Approach: | They propose a pretraining approach that incorporates two key ideas into the masked language modeling objective. |
| Outcome: | The proposed model improves over existing models and sets of long-range transformers and can be easily applied to multiple multi-text tasks. |
What is the best recipe for character-level encoder-only modelling? (2023.acl-long)
Copied to clipboard
| Challenge: | aims to benchmark recent progress in language understanding models that output contextualised representations at the character level. |
| Approach: | They aim to find the best way to build and train character-level BERT-like models by comparing architectural innovations with pretraining objectives. |
| Outcome: | The proposed model outperforms a token-based model on a set of evaluation tasks with a fixed training procedure. |
QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale Retrieval (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for large-scale query-document retrieval are expensive and require sparse handcrafted features. |
| Approach: | They propose a quadrupletBERT model for effective and efficient retrieval using pre-trained language models like BERT. |
| Outcome: | The proposed model improves retrieval phase and leverages distances between simple negative and hard negative instances to obtain better embeddings. |
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. |
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings? (2023.findings-eacl)
Copied to clipboard
| Challenge: | obtaining document embeddings at document level is challenging due to computational requirements and lack of appropriate data. |
| Approach: | They compare methods to produce document-level representations from sentences based on LASER, LaBSE, and Sentence BERT pre-trained multilingual models. |
| Outcome: | The proposed methods produce document-level representations from sentences in 8 languages . the results show that a clever combination of sentence embeddings is usually better than encoding the full document as a single unit. |
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. |
SpanBERT: Improving Pre-training by Representing and Predicting Spans (2020.tacl-1)
Copied to clipboard
| 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. |
Pretrained Language Models for Sequential Sentence Classification (D19-1)
Copied to clipboard
| Challenge: | Recent successful models for document-level understanding have used hierarchical encoding and CRFs to capture dependencies between subsequent labels. |
| Approach: | They propose a pretrained language model that captures contextual dependencies without hierarchical encoding nor a CRF. |
| Outcome: | The proposed model captures contextual dependencies without hierarchical encoding nor a CRF on four datasets, including a new dataset of structured scientific abstracts. |
Give your Text Representation Models some Love: the Case for Basque (2020.lrec-1)
Copied to clipboard
Rodrigo Agerri, Iñaki San Vicente, Jon Ander Campos, Ander Barrena, Xabier Saralegi, Aitor Soroa, Eneko Agirre
| Challenge: | Word embeddings and pre-trained language models are expensive to train and are often used by small companies and research groups to build their own. |
| Approach: | They propose to use word embeddings and pre-trained language models to build rich representations of text and improve NLP tasks. |
| Outcome: | The proposed models perform better than publicly available versions in downstream NLP tasks for Basque. |
Combining Deep Generative Models and Multi-lingual Pretraining for Semi-supervised Document Classification (2021.eacl-main)
Copied to clipboard
| Challenge: | Semi-supervised learning and multilingual pretraining have been shown to be effective for task-specific labelled data shortages. |
| Approach: | They propose to combine semi-supervised deep generative models and multi-lingual pretraining to form a pipeline for document classification task. |
| Outcome: | The proposed method outperforms state-of-the-art models in low-resource settings across several languages and outperformed existing models in English. |