Semanlink - Arxiv Doc ; Representation learning AND Allen Institute for AI (AI2)

Arxiv Doc ; Representation learning AND Allen Institute for AI (AI2)

Descendants partagés

6 Documents

[2212.09741] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Tags:

2023-02-17 A propos

[1902.06006] Contextual Word Representations: A Contextual Introduction

Tags:

2022-07-08 A propos

[1909.04164] Knowledge Enhanced Contextual Word Representations

Tags:

2020-05-13 A propos

[1902.11269] Efficient Contextual Representation Learning Without Softmax Layer

Tags:

**how to accelerate contextual representation learning**.

> Contextual representation models are difficult to train due to the large parameter sizes and high computational complexity

> We find that the softmax layer (the output layer) causes significant inefficiency due to the large vocabulary size.
Therefore, we redesign the learning objectiv.
> Specifically, the proposed approach bypasses the softmax layer by performing language modeling with dimension reduction, and allows the models to leverage pre-trained word embeddings.
Our framework reduces the time spent on the output layer to a negligible level, eliminates almost all the trainable parameters of the softmax layer and performs language modeling without truncating the vocabulary.
When applied to ELMo, our method achieves a 4 times speedup and eliminates 80% trainable parameters while achieving competitive performance on downstream tasks.

**decouples learning contexts and words**

> Instead of using
a softmax layer to predict the distribution of the
missing word, we utilize and extend the SEMFIT
layer (Kumar and Tsvetkov, 2018) to **predict the
embedding of the missing word**.

2019-03-02 A propos

[1811.05370] Unsupervised Transfer Learning for Spoken Language Understanding in Intelligent Agents

Tags:

2018-11-20 A propos

[1806.06259] Evaluation of sentence embeddings in downstream and linguistic probing tasks

Tags:

2018-06-19 A propos