Regularized Training of Nearest Neighbor Language Models

• URL: http://arxiv.org/abs/2109.08249v1
• Date: Thu, 16 Sep 2021 23:20:24 GMT
• Title: Regularized Training of Nearest Neighbor Language Models
• Authors: Jean-Francois Ton, Walter Talbott, Shuangfei Zhai, Josh Susskind
• Abstract summary: We build upon $k$NN-LM citepkhandelwal20generalization, which uses a pre-trained language model together with an exhaustive $k$NN search through the training data (memory bank) to achieve state-of-the-art results. We find that the added L2 regularization seems to improve the performance for high-frequency words without deteriorating the performance for low frequency ones.
• Score: 10.994336081018043
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Including memory banks in a natural language processing architecture increases model capacity by equipping it with additional data at inference time. In this paper, we build upon $k$NN-LM \citep{khandelwal20generalization}, which uses a pre-trained language model together with an exhaustive $k$NN search through the training data (memory bank) to achieve state-of-the-art results. We investigate whether we can improve the $k$NN-LM performance by instead training a LM with the knowledge that we will be using a $k$NN post-hoc. We achieved significant improvement using our method on language modeling tasks on \texttt{WIKI-2} and \texttt{WIKI-103}. The main phenomenon that we encounter is that adding a simple L2 regularization on the activations (not weights) of the model, a transformer, improves the post-hoc $k$NN classification performance. We explore some possible reasons for this improvement. In particular, we find that the added L2 regularization seems to improve the performance for high-frequency words without deteriorating the performance for low frequency ones.

Related papers

• Great Memory, Shallow Reasoning: Limits of $k$NN-LMs [71.73611113995143]
  $k$NN-LMs, which integrate retrieval with next-word prediction, have demonstrated strong performance in language modeling. We ask whether this improved ability to recall information really translates into downstream abilities.
  arXiv  Detail & Related papers  (2024-08-21T17:59:05Z)
• In-Context Language Learning: Architectures and Algorithms [73.93205821154605]
  We study ICL through the lens of a new family of model problems we term in context language learning (ICLL) We evaluate a diverse set of neural sequence models on regular ICLL tasks.
  arXiv  Detail & Related papers  (2024-01-23T18:59:21Z)
• Generate to Understand for Representation [3.5325087487696463]
  GUR is a pretraining framework that combines language modeling and contrastive learning objectives in a single training step. GUR achieves impressive results without any labeled training data, outperforming all other pretrained baselines as a retriever at the recall benchmark in a zero-shot setting.
  arXiv  Detail & Related papers  (2023-06-14T06:00:18Z)
• SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks [21.616328837090396]
  Spiking Neural Networks (SNNs) leverage sparse and event-driven activations to reduce the computational overhead associated with model inference. We implement generative language model with binary, event-driven spiking activation units. SpikeGPT is the largest backpropagation-trained SNN model to date, rendering it suitable for both the generation and comprehension of natural language.
  arXiv  Detail & Related papers  (2023-02-27T16:43:04Z)
• You can't pick your neighbors, or can you? When and how to rely on retrieval in the $k$NN-LM [65.74934004876914]
  Retrieval-enhanced language models (LMs) condition their predictions on text retrieved from large external datastores. One such approach, the $k$NN-LM, interpolates any existing LM's predictions with the output of a $k$-nearest neighbors model. We empirically measure the effectiveness of our approach on two English language modeling datasets.
  arXiv  Detail & Related papers  (2022-10-28T02:57:40Z)
• E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation [95.49128988683191]
  Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. We propose an encoding-enhanced seq2seq pretraining strategy, namely E2S2. E2S2 improves the seq2seq models via integrating more efficient self-supervised information into the encoders.
  arXiv  Detail & Related papers  (2022-05-30T08:25:36Z)
• Better Language Model with Hypernym Class Prediction [101.8517004687825]
  Class-based language models (LMs) have been long devised to address context sparsity in $n$-gram LMs. In this study, we revisit this approach in the context of neural LMs.
  arXiv  Detail & Related papers  (2022-03-21T01:16:44Z)
• Universal Conditional Masked Language Pre-training for Neural Machine Translation [29.334361879066602]
  We propose CeMAT, a conditional masked language model pre-trained on large-scale bilingual and monolingual corpora. We conduct extensive experiments and show that our CeMAT can achieve significant performance improvement for all scenarios.
  arXiv  Detail & Related papers  (2022-03-17T10:00:33Z)
• Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine Translation [127.81351683335143]
  Cross-lingual pretraining requires models to align the lexical- and high-level representations of the two languages. Previous research has shown that this is because the representations are not sufficiently aligned. In this paper, we enhance the bilingual masked language model pretraining with lexical-level information by using type-level cross-lingual subword embeddings.
  arXiv  Detail & Related papers  (2021-03-18T21:17:58Z)

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.