| Challenge: | iBERT is an encoder that produces inherently interpretable and controllable embeddings without compromising performance. |
| Approach: | They propose an encoder that produces interpretable embeddings that modularize and expose discriminative cues present in language. |
| Outcome: | The proposed model outperforms baselines on style-focused tasks while maintaining competitive performance on authorship verification. |
Similar Papers
SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features (2022.aacl-main)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (S3BERT) embeddings are composed of explainable sub-embeddings that emphasize various sentence meaning features. |
| Approach: | They propose to induce Semantically Structured Sentence BERT embeddings (S3BERT) that emphasize various sentence meaning features. |
| Outcome: | The proposed model shows high correlation to human similarity ratings, but lacks interpretability. |
SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddings (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing word embedding models lack interpretability for words . |
| Approach: | They propose to add interpretability to word embeddings by using a POLAR framework that enables wordsense aware interpretations for pre-trained contextual word embeds. |
| Outcome: | The proposed framework achieves comparable performance to existing embeddings across GLUE and SQuAD benchmarks. |
Embeddings in Natural Language Processing (2020.coling-tutorials)
Copied to clipboard
| Challenge: | Embeddings have been a key topic of interest in NLP for the past decade . a quick warm-up introduction to NLP and why it is important to have a semantic comprehension of texts . |
| Approach: | This tutorial will provide a high-level synthesis of the main embedding techniques in NLP . it will start with word embedds and then move to other types of embeddable vectors . |
| Outcome: | This tutorial will provide a high-level synthesis of the main embedding techniques in NLP . it will start with word embedds and move to other types of embeddable representations . |
SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings (2020.coling-main)
Copied to clipboard
| Challenge: | Contextualised embeddings are a key component of human languages but their opaqueness makes it difficult to interpret their behaviour. |
| Approach: | They propose a weakly supervised method to learn interpretable embeddings from raw corpora and seed words. |
| Outcome: | The proposed model can represent both a word and its context as embeddings into the same compact space, whose dimensions correspond to interpretable supersenses. |
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. |
Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing sparse retrieval methods suffer from a lack of interpretability . we propose a new interpretability framework that decomposes dense embeddings into distinct, interpretable latent concepts. |
| Approach: | They propose a new interpretability framework that leveragesSparse Autoencoders to decompose uninterpretable dense embeddings fromDPR models into distinct, interpretable latent concepts. |
| Outcome: | The proposed interpretability framework achieves high index-space and computational efficiency while maintaining robust performance across vocabulary and semantic mismatches. |
Which Evaluations Uncover Sense Representations that Actually Make Sense? (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing sense representations fail for human-centric tasks like inspecting a language’s sense inventory. |
| Approach: | They propose a coherence evaluation for sense embeddings and a model optimized for finding interpretable sense representations that are more coherent than existing sense embeds. |
| Outcome: | The proposed model is more coherent than existing sense embeddings and offers comparable word similarities with multisense representations while learning more distinguishable, interpretable senses. |
E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to enhance BERT with factual knowledge about entities require no additional pretraining and no changes to the encoder itself. |
| Approach: | They propose a way to inject factual knowledge into the pretrained BERT model by aligning Wikipedia2Vec entity vectors with BERT's native wordpiece vector space and feeding the aligned entity vector into BERT as if they were wordpieces. |
| Outcome: | The proposed version outperforms baseline models on unsupervised question answering, supervised relation classification and entity linking tasks. |
BERT Has More to Offer: BERT Layers Combination Yields Better Sentence Embeddings (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Obtaining sentence representations from BERT-based models is valuable as it takes less time to pre-compute a one-time representation of the data and then use it for the downstream tasks. |
| Approach: | They propose to combine certain layers of a BERT-based model rested on the data set and model to achieve substantially better results. |
| Outcome: | The proposed method outperforms baseline models on seven semantic textual similarity datasets and on eight transfer data sets. |
Word2Sense: Sparse Interpretable Word Embeddings (P19-1)
Copied to clipboard
| Challenge: | Word2Sense embeddings are interpretable, but they are sparse and fast to compute . a unitary rotation can be applied to many of these embeddables retaining their utility for computational tasks while changing the values of individual coordinates. |
| Approach: | They propose an unsupervised method to generate Word2Sense word embeddings that are interpretable. |
| Outcome: | The proposed method compares well with other unsupervised word embeddings on NLP tasks. |