Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT (2020.acl-main)
Copied to clipboard
| Challenge: | Recent pre-trained language models achieve state-of-the-art performance for downstream NLP tasks. |
| Approach: | They propose a parameter-free probing technique for analyzing pre-trained language models . their method does not require direct supervision from probing tasks . |
| Outcome: | The proposed method improves on linguistically-uninformed baselines on pre-trained language models. |
Similar Papers
What Does Parameter-free Probing Really Uncover? (2024.acl-short)
Copied to clipboard
| Challenge: | Probing large language models (LLMs) has been criticized for using pre-defined label-laden target labels. |
| Approach: | They extend a parameter-free probing technique called perturbed masking applied to BERT to examine the relationship between UD and BERT. |
| Outcome: | The proposed method is compared to the UD formalism for English and shows that it lacks correlations with linguistic theory. |
Probe-Less Probing of BERT’s Layer-Wise Linguistic Knowledge with Masked Word Prediction (2022.naacl-srw)
Copied to clipboard
| Challenge: | Among studies on localization of linguistic knowledge, it is unclear what information is encoded in each layer. |
| Approach: | They analyze BERT’s layer-wise masked word prediction on an English corpus and find syntactic and semantic information is encoded at different layers for words of different syntaktic categories. |
| Outcome: | The proposed model outperforms state-of-the-art models in many downstream tasks. |
From BERT‘s Point of View: Revealing the Prevailing Contextual Differences (2022.findings-acl)
Copied to clipboard
| Challenge: | BERTology is a new approach to understanding the inner workings of large pretraining language models. |
| Approach: | They propose to invert the probing design to analyze the prevailing differences and clusters in BERT’s high dimensional space by extracting coarse features from masked token representations and predicting them by probing models with access to only partial information. |
| Outcome: | The proposed method extracts coarse features from masked token representations and predicts them by probing models with access to only partial information. |
GiBERT: Enhancing BERT with Linguistic Information using a Lightweight Gated Injection Method (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent pre-trained language models such as BERT have led to noticeable improvements in semantic similarity detection. |
| Approach: | They propose to explicitly inject linguistic information in the form of word embeddings into any layer of a pre-trained BERT. |
| Outcome: | The proposed method improves on multiple semantic similarity datasets and shows that it is beneficial and currently missing from the original model. |
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on enhancing existing models with the primary objective of improving downstream performance on various NLP tasks. |
| Approach: | They propose to use BERT to encode meaningful knowledge in token representations to explain probing results. |
| Outcome: | The proposed model can detect syntactic and semantic abnormalities and distinguish between grammatical number and tense subspaces. |
What BERT Is Not: Lessons from a New Suite of Psycholinguistic Diagnostics for Language Models (2020.tacl-1)
Copied to clipboard
| Challenge: | Pretraining by language modeling has become popular but we have yet to understand what language models learn during that process. |
| Approach: | They propose diagnostics that ask questions about information used by language models for generating predictions in context. |
| Outcome: | The proposed diagnostics can be used to study the popular BERT model . they show that the model can distinguish good from bad completions, but struggles with inference and role-based event prediction. |
Rethinking the Construction of Effective Metrics for Understanding the Mechanisms of Pretrained Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained language models are expected to map input text to a set of vectors while preserving the inherent relationships within the text. |
| Approach: | They propose a new line to constructing metrics for understanding the mechanisms of pretrained language models. |
| Outcome: | The proposed model is referred to as the tree topological probe and is based on a tree topology probe. |
Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense Knowledge (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing evidence suggests that pre-trained Transformers encode commonsense knowledge . however, the extent to which this knowledge is acquired is unclear . |
| Approach: | They inject verbalized knowledge into pre-training minibatches and evaluate generalization . they find generalization does not improve over the course of pre- training from scratch . |
| Outcome: | The proposed model generalizes to supported inferences after pre-training on the injected knowledge. |
Fusing Label Embedding into BERT: An Efficient Improvement for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve text classification performance of pre-trained models have been used to improve their performance. |
| Approach: | They propose a method for improving BERT's performance by using a label embedding technique while keeping almost the same computational cost. |
| Outcome: | The proposed method improves BERT's performance on six text classification benchmark datasets while keeping almost the same computational cost. |
BERT Rediscovers the Classical NLP Pipeline (P19-1)
Copied to clipboard
| Challenge: | Pre-trained text encoders have advanced the state of the art on many NLP tasks . Qualitative analysis reveals that the model can and often does adjust this pipeline dynamically . |
| Approach: | They aim to quantify where linguistic information is captured within a network model . they aim to use pre-trained text encoders to displace static word embeddings . |
| Outcome: | The proposed model can adjust the pipeline dynamically, revealing lower-level decisions on the basis of disambiguation from higher-level representations. |