BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies? (2021.acl-long)
Copied to clipboard
| Challenge: | Analogies play a central role in human commonsense reasoning. |
| Approach: | They analyze the capabilities of transformer-based language models on an unsupervised task . they find off-the-shelf language models can identify analogies to a certain extent . |
| Outcome: | The proposed language models outperform word embedding models on an unsupervised task . the best results were obtained with GPT-2 and RoBERTa . |
Similar Papers
Scientific and Creative Analogies in Pretrained Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing analogy datasets focus on a limited set of analogical relations with a high similarity of the two domains between which the analogy holds. |
| Approach: | They propose a dataset that encodes analogy in pretrained language models . they use a system that maps attributes and relational structures across dissimilar domains . |
| Outcome: | The proposed dataset shows that state-of-the-art models achieve low performance on analogy tasks . |
Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance (2023.emnlp-main)
Copied to clipboard
| Challenge: | Analogical reasoning is a common way to evaluate word embeddings in NLP, but it is also of interest to investigate whether or not it is able to be learned. |
| Approach: | They propose to use proportional analogies to evaluate word embeddings in NLP . they also test whether analogical reasoning is a task in itself that can be learned . |
| Outcome: | The proposed models can learn analogical reasoning even with small amounts of data. |
A Primer in BERTology: What We Know About How BERT Works (2020.tacl-1)
Copied to clipboard
| Challenge: | a new study examines the current state of knowledge about the BERT model . the model is a stack of transformer encoder layers that are based on multiple self-attention ''heads'' |
| Approach: | They present a survey of over 150 studies of the popular Transformer-based model BERT . they discuss the current state of knowledge about how BERT works and how it is represented . |
| Outcome: | The proposed model is based on the Transformer-based model with state-of-the-art results . the proposed model has little cognitive motivation and is too small to perform ablation studies . |
Probing Relational Knowledge in Language Models via Word Analogies (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have focused on probing relational knowledge by filling the blanks in pre-defined prompts such as “The capital of France is —” but these are affected by the co-occurrence of target relation words and entities in the pre-training corpus. |
| Approach: | They extend probing methodologies by using analogical proportions as a proxy to probe relational knowledge in transformer-based PLMs without directly presenting the desired relation. |
| Outcome: | The proposed methods are extremely accurate at (1) and (2), but have room for improvement for (3). |
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. |
On the Sentence Embeddings from Pre-trained Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained contextual representations like BERT have been widely used for NLP tasks. |
| Approach: | They propose to transform anisotropic sentence embedding distribution to smooth and isotropic Gaussian distribution by normalizing flows that are learned with an unsupervised objective. |
| Outcome: | The proposed method achieves significant performance gains over state-of-the-art embeddings on a variety of semantic textual similarity tasks. |
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. |
Language Models and Semantic Relations: A Dual Relationship (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on language models for the extraction of semantic relations have focused on injecting semantic knowledge into these models to enhance them. |
| Approach: | They propose to extract lexical semantic relations from a BERT model and inject them into it using unsupervised methods based on semantic similarity at word and sentence levels. |
| Outcome: | The proposed method allows to enrich a BERT model without using any external semantic resource. |
Life after BERT: What do Other Muppets Understand about Language? (2022.acl-long)
Copied to clipboard
| Challenge: | Existing pre-trained transformer analysis studies focus on one or two model families at a time, overlooking the variability of the architecture and pre-training objectives. |
| Approach: | They utilize oLMpics bench- mark and psycholinguistic probing datasets for a diverse set of 29 models including T5, BART, and ALBERT. |
| Outcome: | The proposed model fails to resolve compositional questions in a zero-shot fashion, suggesting that pre-training objectives are not predictive of a model’s linguistic capabilities. |
Investigating the Performance of Transformer-Based NLI Models on Presuppositional Inferences (2022.coling-1)
Copied to clipboard
| Challenge: | Presuppositions are assumptions that are taken for granted by an utterance. |
| Approach: | They propose to use heuristics to create alternative "contrastive" test cases . they also analyze samples from ImpPres datasets to better understand their predictions . |
| Outcome: | The proposed model performs better on the ImpPres dataset than on the other datasets. |