paper-with-me

Papers

Reconsidering the Past: Optimizing Hidden States in Language Models

2021-12-16 · Findings (EMNLP) 2021 11 · Davis Yoshida, Kevin Gimpel

We present Hidden-State Optimization (HSO), a gradient-based method for improving the performance of transformer language models at inference time. Similar to dynamic evaluation (Krause et al., 2018), HSO computes the gradient of the log-probability the language model assigns to an evaluation text, but uses it to update the cached hidden states rather than the model parameters. We test HSO with pretrained Transformer-XL and GPT-2 language models, finding improvement on the WikiText103 and PG-19 datasets in terms of perplexity, especially when evaluating a model outside of its training distribution. We also demonstrate downstream applicability by showing gains in the recently developed prompt-based few-shot evaluation setting, again with no extra parameters or training data.

📄 PDF Abstract BibTeX arXiv:2112.08653

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Similar Papers 제목 키워드 기반

Parameter-Efficient Tuning by Manipulating Hidden States of Pretrained Language Models For Classification Tasks

2022-04-10 · Haoran Yang, Piji Li, Wai Lam

Parameter-efficient tuning aims to distill knowledge for downstream tasks by optimizing a few introduced parameters while freezing the pretrained language models (PLMs). Continuous prompt tuning which prepends a few trai…

Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning

2024-07-08 · Yadong Zhang, Shaoguang Mao, Wenshan Wu, Yan Xia 외

This paper introduces BI-Directional DEliberation Reasoning (BIDDER), a novel reasoning approach to enhance the decision rationality of language models. Traditional reasoning methods typically rely on historical informat…

Decision MakingLanguage ModelingLanguage Modelling

Multiplicative Models for Recurrent Language Modeling

2019-06-30 · Diego Maupomé, Marie-Jean Meurs

Recently, there has been interest in multiplicative recurrent neural networks for language modeling. Indeed, simple Recurrent Neural Networks (RNNs) encounter difficulties recovering from past mistakes when generating se…

Language ModelingLanguage Modelling

Multi-Prompting Decoder Helps Better Language Understanding

2024-06-10 · Zifeng Cheng, Zhaoling Chen, Zhiwei Jiang, Yafeng Yin 외

Recent Pre-trained Language Models (PLMs) usually only provide users with the inference APIs, namely the emerging Model-as-a-Service (MaaS) setting. To adapt MaaS PLMs to downstream tasks without accessing their paramete…

DecoderNatural Language Understanding

Autoregressive Affective Language Forecasting: A Self-Supervised Task

2020-12-01 · COLING 2020 8 · Matthew Matero, H. Andrew Schwartz

Human natural language is mentioned at a specific point in time while human emotions change over time. While much work has established a strong link between language use and emotional states, few have attempted to model …