A Cognitive Regularizer for Language Modeling

• URL: http://arxiv.org/abs/2105.07144v1
• Date: Sat, 15 May 2021 05:37:42 GMT
• Title: A Cognitive Regularizer for Language Modeling
• Authors: Jason Wei, Clara Meister, and Ryan Cotterell
• Abstract summary: We augment the canonical MLE objective for training language models by encoding UID as regularization. We find that using UID regularization consistently improves perplexity in language models. We also find that UID-regularized language models are higher-entropy and produce text that is longer and more lexically diverse.
• Score: 36.256053903862956
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The uniform information density (UID) hypothesis, which posits that speakers prefer utterances that distribute information uniformly across the signal, has gained substantial traction in psycholinguistics as an explanation for certain syntactic, morphological, and prosodic choices. Could we operationalize uniform information density as an inductive bias for statistical language modeling? In this paper, we augment the canonical MLE objective for training language models by encoding UID as regularization. In experiments on ten languages spanning five language families, we find that using UID regularization consistently improves perplexity in language models, having a larger effect when training data is limited. Moreover, via analysis of generated sequences, we find that UID-regularized language models are higher-entropy and produce text that is longer and more lexically diverse. Our results not only suggest that UID is a reasonable inductive bias for language modeling, but also provide an alternative validation of the UID hypothesis using modern-day NLP tools.

Related papers

• Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation [2.9921619703037274]
  We propose a retrieval augmented generation (RAG) framework backed by a large language model (LLM) to correct the output of a smaller model for the linguistic task of morphological glossing. We leverage linguistic information to make up for the lack of data and trainable parameters, while allowing for inputs from written descriptive grammars interpreted and distilled through an LLM. We show that a compact, RAG-supported model is highly effective in data-scarce settings, achieving a new state-of-the-art for this task and our target languages.
  arXiv  Detail & Related papers  (2024-10-01T04:20:14Z)
• Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning [56.03057119008865]
  We show that scaling diffusion language models can effectively make them strong language learners. We build competent diffusion language models at scale by first acquiring knowledge from massive data. Experiments show that scaling diffusion language models consistently improves performance across downstream language tasks.
  arXiv  Detail & Related papers  (2023-08-23T16:01:12Z)
• Jamp: Controlled Japanese Temporal Inference Dataset for Evaluating Generalization Capacity of Language Models [18.874880342410876]
  We present Jamp, a Japanese benchmark focused on temporal inference. Our dataset includes a range of temporal inference patterns, which enables us to conduct fine-grained analysis. We evaluate the generalization capacities of monolingual/multilingual LMs by splitting our dataset based on tense fragments.
  arXiv  Detail & Related papers  (2023-06-19T07:00:14Z)
• Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models [11.439430077017635]
  We find that pre-trained speech models optimally encode language discriminatory information in lower layers. We demonstrate that the embeddings obtained from these layers are significantly robust to classify unseen languages. We open-source the model through the NVIDIA NeMo toolkit.
  arXiv  Detail & Related papers  (2022-11-09T18:53:59Z)
• Revisiting the Uniform Information Density Hypothesis [44.277066511088634]
  We investigate the uniform information density (UID) hypothesis using reading time and acceptability data. For acceptability judgments, we find clearer evidence that non-uniformity in information density is predictive of lower acceptability.
  arXiv  Detail & Related papers  (2021-09-23T20:41:47Z)
• Learning Universal Representations from Word to Sentence [89.82415322763475]
  This work introduces and explores the universal representation learning, i.e., embeddings of different levels of linguistic unit in a uniform vector space. We present our approach of constructing analogy datasets in terms of words, phrases and sentences. We empirically verify that well pre-trained Transformer models incorporated with appropriate training settings may effectively yield universal representation.
  arXiv  Detail & Related papers  (2020-09-10T03:53:18Z)
• Data Augmentation for Spoken Language Understanding via Pretrained Language Models [113.56329266325902]
  Training of spoken language understanding (SLU) models often faces the problem of data scarcity. We put forward a data augmentation method using pretrained language models to boost the variability and accuracy of generated utterances.
  arXiv  Detail & Related papers  (2020-04-29T04:07:12Z)
• Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition [58.105818353866354]
  We propose an improved recurrent neural network transducer (RNN-T) model with language bias to alleviate the problem. We use the language identities to bias the model to predict the CS points. This promotes the model to learn the language identity information directly from transcription, and no additional LID model is needed.
  arXiv  Detail & Related papers  (2020-02-19T12:01:33Z)
• Limits of Detecting Text Generated by Large-Scale Language Models [65.46403462928319]
  Some consider large-scale language models that can generate long and coherent pieces of text as dangerous, since they may be used in misinformation campaigns. Here we formulate large-scale language model output detection as a hypothesis testing problem to classify text as genuine or generated.
  arXiv  Detail & Related papers  (2020-02-09T19:53:23Z)

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.