Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproving Low Compute Language Modeling with In-Domain Embedding Initialisation
71
0
0.0
(
0
)
Added by
Jonathan K Kummerfeld
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most language modeling research considers either a small dataset with a closed vocabulary (like the standard 1 million token Penn Treebank), or the whole web with byte-pair encoding. We show that for our target setting in English, initialising and freezing input embeddings using in-domain data can improve language model performance by providing a useful representation of rare words, and this pattern holds across several different domains. In the process, we show that the standard convention of tying input and output embeddings does not improve perplexity when initializing with embeddings trained on in-domain data.
rate research
Read More
In this work we explore Unsupervised Domain Adaptation (UDA) of pretrained language models for downstream tasks. We introduce UDALM, a fine-tuning procedure, using a mixed classification and Masked Language Model loss, that can adapt to the target domain distribution in a robust and sample efficient manner. Our experiments show that performance of models trained with the mixed loss scales with the amount of available target data and the mixed loss can be effectively used as a stopping criterion during UDA training. Furthermore, we discuss the relationship between A-distance and the target error and explore some limitations of the Domain Adversarial Training approach. Our method is evaluated on twelve domain pairs of the Amazon Reviews Sentiment dataset, yielding $91.74%$ accuracy, which is an $1.11%$ absolute improvement over the state-of-the-art.
The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the compression of these models to improve their inference time and memory footprint. This paper presents a novel loss objective to compress token embeddings in the Transformer-based models by leveraging an AutoEncoder architecture. More specifically, we emphasize the importance of the direction of compressed embeddings with respect to original uncompressed embeddings. The proposed method is task-agnostic and does not require further language modeling pre-training. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity. Moreover, we evaluate our proposed approach over SQuAD v1.1 dataset and several downstream tasks from the GLUE benchmark, where we also outperform the baseline in most scenarios. Our code is public.
A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models. Though recent years have finally seen Giza++ performance bested, the new methods primarily rely on large machine translation models, massively multilingual language models, or supervision from Giza++ alignments itself. We introduce Embedding-Enhanced Giza++, and outperform Giza++ without any of the aforementioned factors. Taking advantage of monolingual embedding space geometry of the source and target language only, we exceed Giza++s performance in every tested scenario for three languages. In the lowest-resource scenario of only 500 lines of bitext, we improve performance over Giza++ by 10.9 AER. Our method scales monotonically outperforming Giza++ for all tested scenarios between 500 and 1.9 million lines of bitext. Our code will be made publicly available.
Large pre-trained sentence encoders like BERT start a new chapter in natural language processing. A common practice to apply pre-trained BERT to sequence classification tasks (e.g., classification of sentences or sentence pairs) is by feeding the embedding of [CLS] token (in the last layer) to a task-specific classification layer, and then fine tune the model parameters of BERT and classifier jointly. In this paper, we conduct systematic analysis over several sequence classification datasets to examine the embedding values of [CLS] token before the fine tuning phase, and present the biased embedding distribution issue---i.e., embedding values of [CLS] concentrate on a few dimensions and are non-zero centered. Such biased embedding brings challenge to the optimization process during fine-tuning as gradients of [CLS] embedding may explode and result in degraded model performance. We further propose several simple yet effective normalization methods to modify the [CLS] embedding during the fine-tuning. Compared with the previous practice, neural classification model with the normalized embedding shows improvements on several text classification tasks, demonstrates the effectiveness of our method.
End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the performance on rare content words often lags behind hybrid ASR systems. To address this problem, second-pass rescoring is often applied leveraging upon language modeling. In this paper, we propose a second-pass system with multi-task learning, utilizing semantic targets (such as intent and slot prediction) to improve speech recognition performance. We show that our rescoring model trained with these additional tasks outperforms the baseline rescoring model, trained with only the language modeling task, by 1.4% on a general test and by 2.6% on a rare word test set in terms of word-error-rate relative (WERR). Our best ASR system with multi-task LM shows 4.6% WERR deduction compared with RNN Transducer only ASR baseline for rare words recognition.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
