Linear Recency Bias During Training Improves Transformers' Fit to Reading Times

• URL: http://arxiv.org/abs/2409.11250v1
• Date: Tue, 17 Sep 2024 14:57:51 GMT
• Title: Linear Recency Bias During Training Improves Transformers' Fit to Reading Times
• Authors: Christian Clark, Byung-Doh Oh, William Schuler,
• Abstract summary: This paper evaluates a modification of the Transformer model that uses ALiBi, a recency bias added to attention scores. ALiBi's mixture of slopes -- which determine the rate of memory decay in each attention head -- may play a role in helping models with ALiBi to track different kinds of linguistic dependencies.
• Score: 16.55240473621401
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent psycholinguistic research has compared human reading times to surprisal estimates from language models to study the factors shaping human sentence processing difficulty. Previous studies have shown a strong fit between surprisal values from Transformers and reading times. However, standard Transformers work with a lossless representation of the entire previous linguistic context, unlike models of human language processing that include memory decay. To bridge this gap, this paper evaluates a modification of the Transformer model that uses ALiBi (Press et al., 2022), a recency bias added to attention scores. Surprisal estimates with ALiBi show an improved fit to human reading times compared to a standard Transformer baseline. A subsequent analysis of attention heads suggests that ALiBi's mixture of slopes -- which determine the rate of memory decay in each attention head -- may play a role in the improvement by helping models with ALiBi to track different kinds of linguistic dependencies.

Related papers

• Differential Transformer [99.5117269150629]
  Transformer tends to overallocate attention to irrelevant context. We introduce Diff Transformer, which amplifies attention to relevant context while canceling noise. It offers notable advantages in practical applications, such as long-context modeling, key information retrieval, hallucination mitigation, in-context learning, and reduction of activation outliers.
  arXiv  Detail & Related papers  (2024-10-07T17:57:38Z)
• Explaining Text Similarity in Transformer Models [52.571158418102584]
  Recent advances in explainable AI have made it possible to mitigate limitations by leveraging improved explanations for Transformers. We use BiLRP, an extension developed for computing second-order explanations in bilinear similarity models, to investigate which feature interactions drive similarity in NLP models. Our findings contribute to a deeper understanding of different semantic similarity tasks and models, highlighting how novel explainable AI methods enable in-depth analyses and corpus-level insights.
  arXiv  Detail & Related papers  (2024-05-10T17:11:31Z)
• Transformers for Low-Resource Languages:Is F\'eidir Linn! [2.648836772989769]
  In general, neural translation models often under perform on language pairs with insufficient training data. We demonstrate that choosing appropriate parameters leads to considerable performance improvements. A Transformer optimized model demonstrated a BLEU score improvement of 7.8 points when compared with a baseline RNN model.
  arXiv  Detail & Related papers  (2024-03-04T12:29:59Z)
• Transformer Language Models Handle Word Frequency in Prediction Head [31.145866381881625]
  This study investigates the inner workings of the prediction head, specifically focusing on bias parameters. Our experiments with BERT and GPT-2 models reveal that the biases in their word prediction heads play a significant role in the models' ability to reflect word frequency in a corpus.
  arXiv  Detail & Related papers  (2023-05-29T17:59:15Z)
• Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times? [9.909170013118775]
  The propensity of larger Transformer-based models to'memorize' sequences during training makes their surprisal estimates diverge from humanlike expectations. These results suggest that the propensity of larger Transformer-based models to'memorize' sequences during training makes their surprisal estimates diverge from humanlike expectations.
  arXiv  Detail & Related papers  (2022-12-23T03:57:54Z)
• A Length-Extrapolatable Transformer [98.54835576985664]
  We focus on length extrapolation, i.e., training on short texts while evaluating longer sequences. We introduce a relative position embedding to explicitly maximize attention resolution. We evaluate different Transformer variants with language modeling.
  arXiv  Detail & Related papers  (2022-12-20T18:56:20Z)
• On the Effect of Pre-training for Transformer in Different Modality on Offline Reinforcement Learning [0.0]
  We investigate how pre-training on data of different modalities, such as language and vision, affects fine-tuning of Transformer-based models to Mujoco offline reinforcement learning tasks.
  arXiv  Detail & Related papers  (2022-11-17T13:34:08Z)
• Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers [54.4919139401528]
  We show that it is possible to reduce interference by identifying and pruning language-specific parameters. We show that removing identified attention heads from a fixed model improves performance for a target language on both sentence classification and structural prediction.
  arXiv  Detail & Related papers  (2022-10-11T18:11:37Z)
• Incorporating Residual and Normalization Layers into Analysis of Masked Language Models [29.828669678974983]
  We extend the scope of the analysis of Transformers from solely the attention patterns to the whole attention block. Our analysis of Transformer-based masked language models shows that the token-to-token interaction performed via attention has less impact on the intermediate representations than previously assumed.
  arXiv  Detail & Related papers  (2021-09-15T08:32:20Z)
• Improving Cross-Lingual Reading Comprehension with Self-Training [62.73937175625953]
  Current state-of-the-art models even surpass human performance on several benchmarks. Previous works have revealed the abilities of pre-trained multilingual models for zero-shot cross-lingual reading comprehension. This paper further utilized unlabeled data to improve the performance.
  arXiv  Detail & Related papers  (2021-05-08T08:04:30Z)
• Bayesian Transformer Language Models for Speech Recognition [59.235405107295655]
  State-of-the-art neural language models (LMs) represented by Transformers are highly complex. This paper proposes a full Bayesian learning framework for Transformer LM estimation.
  arXiv  Detail & Related papers  (2021-02-09T10:55:27Z)

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.