Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees

• URL: http://arxiv.org/abs/2103.04350v1
• Date: Sun, 7 Mar 2021 13:11:31 GMT
• Title: Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees
• Abstract summary: We propose a novel framework named Syntax-BERT to incorporate the syntax trees effectively and efficiently into pre-trained Transformers. Experiments on various datasets of natural language understanding verify the effectiveness of syntax trees and achieve consistent improvement over multiple pre-trained models.
• Score: 15.245017922785403
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP applications. However, how to incorporate the syntax trees effectively and efficiently into pre-trained Transformers is still unsettled. In this paper, we address this problem by proposing a novel framework named Syntax-BERT. This framework works in a plug-and-play mode and is applicable to an arbitrary pre-trained checkpoint based on Transformer architecture. Experiments on various datasets of natural language understanding verify the effectiveness of syntax trees and achieve consistent improvement over multiple pre-trained models, including BERT, RoBERTa, and T5.

Related papers

• Exploiting Pre-trained Encoder-Decoder Transformers for Sequence-to-Sequence Constituent Parsing [1.332091725929965]
  A recent approach involves using sequence-to-sequence models to handle constituent parsing as a machine translation problem.<n>These models are typically with pre-trained encoder-only language models like BERT or RoBERTa.<n>We extend this framework by investigating nots built on pre-trained encoder-decoder architectures, including BART, mBART, and T5.
  arXiv  Detail & Related papers  (2026-05-13T11:28:56Z)
• On Eliciting Syntax from Language Models via Hashing [19.872554909401316]
  Unsupervised parsing aims to infer syntactic structure from raw text. In this paper, we explore the possibility of leveraging this capability to deduce parsing trees from raw text. We show that our method is effective and efficient enough to acquire high-quality parsing trees from pre-trained language models at a low cost.
  arXiv  Detail & Related papers  (2024-10-05T08:06:19Z)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)
• XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding [73.24847320536813]
  This study explores distilling visual information from pretrained multimodal transformers to pretrained language encoders. Our framework is inspired by cross-modal encoders' success in visual-language tasks while we alter the learning objective to cater to the language-heavy characteristics of NLU.
  arXiv  Detail & Related papers  (2022-04-15T03:44:00Z)
• NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction [14.912579358678212]
  Using prompts to perform various downstream tasks, also known as prompt-based learning or prompt-learning, has lately gained significant success in comparison to the pre-train and fine-tune paradigm. In this paper, we attempt to accomplish several NLP tasks in a zero-shot scenario using a BERT original pre-training task abandoned by RoBERTa and other models--Next Sentence Prediction (NSP) Unlike token-level techniques, our sentence-level prompt-based method NSP-BERT does not need to fix the length of the prompt or the position to be predicted, allowing it to handle tasks such as entity linking
  arXiv  Detail & Related papers  (2021-09-08T11:57:08Z)
• A Comprehensive Comparison of Pre-training Language Models [0.5139874302398955]
  We pre-train a list of transformer-based models with the same amount of text and the same training steps. The experimental results show that the most improvement upon the origin BERT is adding the RNN-layer to capture more contextual information for short text understanding.
  arXiv  Detail & Related papers  (2021-06-22T02:12:29Z)
• SML: a new Semantic Embedding Alignment Transformer for efficient cross-lingual Natural Language Inference [71.57324258813674]
  The ability of Transformers to perform with precision a variety of tasks such as question answering, Natural Language Inference (NLI) or summarising, have enable them to be ranked as one of the best paradigms to address this kind of tasks at present. NLI is one of the best scenarios to test these architectures, due to the knowledge required to understand complex sentences and established a relation between a hypothesis and a premise. In this paper, we propose a new architecture, siamese multilingual transformer, to efficiently align multilingual embeddings for Natural Language Inference.
  arXiv  Detail & Related papers  (2021-03-17T13:23:53Z)
• Teach me how to Label: Labeling Functions from Natural Language with Text-to-text Transformers [0.5330240017302619]
  This paper focuses on the task of turning natural language descriptions into Python labeling functions. We follow a novel approach to semantic parsing with pre-trained text-to-text Transformers. Our approach can be regarded as a stepping stone towards models that are taught how to label in natural language.
  arXiv  Detail & Related papers  (2021-01-18T16:04:15Z)
• Syntax-Enhanced Pre-trained Model [49.1659635460369]
  We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. We present a model that utilizes the syntax of text in both pre-training and fine-tuning stages.
  arXiv  Detail & Related papers  (2020-12-28T06:48:04Z)
• BURT: BERT-inspired Universal Representation from Twin Structure [89.82415322763475]
  BURT (BERT inspired Universal Representation from Twin Structure) is capable of generating universal, fixed-size representations for input sequences of any granularity. Our proposed BURT adopts the Siamese network, learning sentence-level representations from natural language inference dataset and word/phrase-level representations from paraphrasing dataset. We evaluate BURT across different granularities of text similarity tasks, including STS tasks, SemEval2013 Task 5(a) and some commonly used word similarity tasks.
  arXiv  Detail & Related papers  (2020-04-29T04:01:52Z)
• Tree-structured Attention with Hierarchical Accumulation [103.47584968330325]
  "Hierarchical Accumulation" encodes parse tree structures into self-attention at constant time complexity. Our approach outperforms SOTA methods in four IWSLT translation tasks and the WMT'14 English-German translation task.
  arXiv  Detail & Related papers  (2020-02-19T08:17:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.