Mixed-effects transformers for hierarchical adaptation

• URL: http://arxiv.org/abs/2205.01749v1
• Date: Tue, 3 May 2022 19:34:15 GMT
• Title: Mixed-effects transformers for hierarchical adaptation
• Authors: Julia White and Noah Goodman and Robert Hawkins
• Abstract summary: We introduce the mixed-effects transformer (MET), a novel approach for learning hierarchically-structured prefixes. We show how the popular class of mixed-effects models may be extended to transformer-based architectures.
• Score: 1.9105318290910576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language use differs dramatically from context to context. To some degree, modern language models like GPT-3 are able to account for such variance by conditioning on a string of previous input text, or prompt. Yet prompting is ineffective when contexts are sparse, out-of-sample, or extra-textual; for instance, accounting for when and where the text was produced or who produced it. In this paper, we introduce the mixed-effects transformer (MET), a novel approach for learning hierarchically-structured prefixes -- lightweight modules prepended to the input -- to account for structured variation. Specifically, we show how the popular class of mixed-effects models may be extended to transformer-based architectures using a regularized prefix-tuning procedure with dropout. We evaluate this approach on several domain-adaptation benchmarks, finding that it efficiently adapts to novel contexts with minimal data while still effectively generalizing to unseen contexts.

Related papers

• Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods [69.36397993451742]
  This work introduces Context-aware Prompt Tuning (CPT), a method inspired by ICL, PT, and adversarial attacks. We modify specific context tokens, considering the unique structure of input and output formats. Inspired by adversarial attacks, we adjust the input based on the labels present in the context, focusing on minimizing, rather than maximizing, the loss.
  arXiv  Detail & Related papers  (2024-10-22T17:45:47Z)
• Attention over pre-trained Sentence Embeddings for Long Document Classification [4.38566347001872]
  transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. We suggest to take advantage of pre-trained sentence transformers to start from semantically meaningful embeddings of the individual sentences. We report the results obtained by this simple architecture on three standard document classification datasets.
  arXiv  Detail & Related papers  (2023-07-18T09:06:35Z)
• Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation [11.960178399478718]
  Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Instead, we prepare PLMs for data- and parameter-efficient adaptation by learning to learn the difference between general and adapted PLMs.
  arXiv  Detail & Related papers  (2022-07-07T18:00:22Z)
• Paragraph-based Transformer Pre-training for Multi-Sentence Inference [99.59693674455582]
  We show that popular pre-trained transformers perform poorly when used for fine-tuning on multi-candidate inference tasks. We then propose a new pre-training objective that models the paragraph-level semantics across multiple input sentences.
  arXiv  Detail & Related papers  (2022-05-02T21:41:14Z)
• Text Revision by On-the-Fly Representation Optimization [76.11035270753757]
  Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems. We present an iterative in-place editing approach for text revision, which requires no parallel data. It achieves competitive and even better performance than state-of-the-art supervised methods on text simplification.
  arXiv  Detail & Related papers  (2022-04-15T07:38:08Z)
• Revisiting Transformer-based Models for Long Document Classification [31.60414185940218]
  In real-world applications, multi-page multi-paragraph documents are common and cannot be efficiently encoded by vanilla Transformer-based models. We compare different Transformer-based Long Document Classification (TrLDC) approaches that aim to mitigate the computational overhead of vanilla transformers. We observe a clear benefit from being able to process longer text, and, based on our results, we derive practical advice of applying Transformer-based models on long document classification tasks.
  arXiv  Detail & Related papers  (2022-04-14T00:44:36Z)
• HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization [57.798070356553936]
  HETFORMER is a Transformer-based pre-trained model with multi-granularity sparse attentions for extractive summarization. Experiments on both single- and multi-document summarization tasks show that HETFORMER achieves state-of-the-art performance in Rouge F1.
  arXiv  Detail & Related papers  (2021-10-12T22:42:31Z)
• Experiments with adversarial attacks on text genres [0.0]
  Neural models based on pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTA results in many NLP tasks. We show that embedding-based algorithms which can replace some of the most significant'' words with words similar to them, have the ability to influence model predictions in a significant proportion of cases.
  arXiv  Detail & Related papers  (2021-07-05T19:37:59Z)
• 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)
• ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations [97.27005783856285]
  This paper introduces ASSET, a new dataset for assessing sentence simplification in English. We show that simplifications in ASSET are better at capturing characteristics of simplicity when compared to other standard evaluation datasets for the task.
  arXiv  Detail & Related papers  (2020-05-01T16:44:54Z)

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.