Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
78
0
0.0
(
0
)
Added by
Hakan Inan
Publication date
2016
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Recurrent neural networks have been very successful at predicting sequences of words in tasks such as language modeling. However, all such models are based on the conventional classification framework, where the model is trained against one-hot targets, and each word is represented both as an input and as an output in isolation. This causes inefficiencies in learning both in terms of utilizing all of the information and in terms of the number of parameters needed to train. We introduce a novel theoretical framework that facilitates better learning in language modeling, and show that our framework leads to tying together the input embedding and the output projection matrices, greatly reducing the number of trainable variables. Our framework leads to state of the art performance on the Penn Treebank with a variety of network models.
rate research
Read More
In this paper, we focus on the problem of adapting word vector-based models to new textual data. Given a model pre-trained on large reference data, how can we adapt it to a smaller piece of data with a slightly different language distribution? We frame the adaptation problem as a monolingual word vector alignment problem, and simply average models after alignment. We align vectors using the RCSLS criterion. Our formulation results in a simple and efficient algorithm that allows adapting general-purpose models to changing word distributions. In our evaluation, we consider applications to word embedding and text classification models. We show that the proposed approach yields good performance in all setups and outperforms a baseline consisting in fine-tuning the model on new data.
Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood. In this paper, we start from an investigation of the gradient vanishing issue in the skipgram model without a proper negative sampler. By performing an insightful analysis from the stochastic gradient descent (SGD) learning perspective, we demonstrate that, both theoretically and intuitively, negative samples with larger inner product scores are more informative than those with lower scores for the SGD learner in terms of both convergence rate and accuracy. Understanding this, we propose an alternative sampling algorithm that dynamically selects informative negative samples during each SGD update. More importantly, the proposed sampler accounts for multi-dimensional self-embedded features during the sampling process, which essentially makes it more effective than the original popularity-based (one-dimensional) sampler. Empirical experiments further verify our observations, and show that our fine-grained samplers gain significant improvement over the existing ones without increasing computational complexity.
Word vectors require significant amounts of memory and storage, posing issues to resource limited devices like mobile phones and GPUs. We show that high quality quantized word vectors using 1-2 bits per parameter can be learned by introducing a quantization function into Word2Vec. We furthermore show that training with the quantization function acts as a regularizer. We train word vectors on English Wikipedia (2017) and evaluate them on standard word similarity and analogy tasks and on question answering (SQuAD). Our quantized word vectors not only take 8-16x less space than full precision (32 bit) word vectors but also outperform them on word similarity tasks and question answering.
Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance. A key ingredient to the successful application of these representations is to train them on very large corpora, and use these pre-trained models in downstream tasks. In this paper, we describe how we trained such high quality word representations for 157 languages. We used two sources of data to train these models: the free online encyclopedia Wikipedia and data from the common crawl project. We also introduce three new word analogy datasets to evaluate these word vectors, for French, Hindi and Polish. Finally, we evaluate our pre-trained word vectors on 10 languages for which evaluation datasets exists, showing very strong performance compared to previous models.
The word movers distance (WMD) is a fundamental technique for measuring the similarity of two documents. As the crux of WMD, it can take advantage of the underlying geometry of the word space by employing an optimal transport formulation. The original study on WMD reported that WMD outperforms classical baselines such as bag-of-words (BOW) and TF-IDF by significant margins in various datasets. In this paper, we point out that the evaluation in the original study could be misleading. We re-evaluate the performances of WMD and the classical baselines and find that the classical baselines are competitive with WMD if we employ an appropriate preprocessing, i.e., L1 normalization. However, this result is not intuitive. WMD should be superior to BOW because WMD can take the underlying geometry into account, whereas BOW cannot. Our analysis shows that this is due to the high-dimensional nature of the underlying metric. We find that WMD in high-dimensional spaces behaves more similarly to BOW than in low-dimensional spaces due to the curse of dimensionality.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
