Masked Audio Text Encoders are Effective Multi-Modal Rescorers (2023.findings-acl)
Copied to clipboard
| Challenge: | Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition systems. |
| Approach: | They propose a multi-modal masked language model rescorer which integrates acoustic representations into the input space of MLM. |
| Outcome: | The proposed model reduces word error rate (WER) by 4%-16% on in-domain and 3%-7% on out-of-domain datasets over the text-only baseline. |
Similar Papers
Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for incorporating a masked language model into an EncDec model have potential drawbacks when applied to GEC. |
| Approach: | They propose to incorporate a pre-trained masked language model (MLM) into an encoder-decoder model for grammatical error correction. |
| Outcome: | The proposed method achieves state-of-the-art on BEA-2019 and CoNLL-2014 benchmarks. |
Masked Language Model Scoring (2020.acl-main)
Copied to clipboard
| Challenge: | Pretrained masked language models require finetuning for most tasks. |
| Approach: | They evaluate pretrained masked language models out of the box via their pseudo-log-likelihood scores (PLLs) they attribute this success to PLL’s unsupervised expression of linguistic acceptability without a left-to-right bias, greatly improving on scores from GPT-2 . |
| Outcome: | The proposed model outperforms autoregressive language models in a variety of tasks. |
Joint Audio/Text Training for Transformer Rescorer of Streaming Speech Recognition (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that streaming end-to-end speech recognition models suffer from higher word error rates (WER) compared to non-streaming models, streaming endto-ended ASR models are limited to short audio context or not use future context to satisfy low latency constraints. |
| Approach: | They propose a 2nd-pass rescoring model on top of the 1st-pass streaming model to improve recognition accuracy while keeping latency low. |
| Outcome: | The proposed method improves word error rate significantly compared to the existing model without adding any additional parameters or latency. |
Data Efficient Masked Language Modeling for Vision and Language (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. |
| Approach: | They propose a masking strategy that masks tokens with a 15% probability for text-only data. |
| Outcome: | The proposed masking strategy outperforms the baseline model on a prompt-based probing task designed to elicit image objects. |
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that pretrained Masked Language Models are not effective as universal lexical and sentence encoders off-the-shelf, i.e., without further task-specific fine-tuning on NLI, sentence similarity, or paraphrasing tasks using annotated task data. |
| Approach: | They propose a contrastive learning technique which turns pretrained MLMs into effective universal lexical and sentence encoders without additional data. |
| Outcome: | The proposed technique can turn MLMs into effective universal lexical and sentence encoders even without additional data. |
MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER (2022.acl-long)
Copied to clipboard
| Challenge: | Named entity recognition (NER) tasks have limited amount of labeled data . data augmentation methods suffer from token-label misalignment, which leads to unsatsifactory performance. |
| Approach: | They propose a data augmentation framework that explicitly injects NER labels into sentence context and generates high-quality augmented data with novel entities. |
| Outcome: | The proposed framework outperforms baseline methods on low-resource tasks. |
EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning (2024.emnlp-main)
Copied to clipboard
| Challenge: | EH-MAM is a self-supervised learning approach for speech representation learning . prior methods used random masking schemes to learn speech representations . |
| Approach: | They propose a self-supervised approach that automatically selects hard regions during SSL training and introduces them to the model for reconstruction. |
| Outcome: | The proposed approach outperforms state-of-the-art models across low-resource speech recognition and SUPERB benchmarks by 5%-10%. |
LLM Explainability via Attributive Masking Learning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | In this paper, we introduce Attributive Masking Learning (AML), a method designed for explaining language model predictions by learning input masks. |
| Approach: | They introduce a method for explaining language model predictions by learning input masks and ensuring a significant change in the model's explanation when applying the inverse mask to the input. |
| Outcome: | The proposed method outperforms state-of-the-art explanation methods on multiple benchmarks. |
ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding (2023.findings-acl)
Copied to clipboard
| Challenge: | Despite efforts to improve ASR robustness, errors from pipeline approaches can lead to error propagation. |
| Approach: | They propose a framework for improving ASR robustness in SLU by using mutual learning and large-margin contrastive learning. |
| Outcome: | The proposed framework outperforms existing models and achieves new state-of-the-art performance on three datasets. |
Curriculum Masking in Vision-Language Pretraining to Maximize Cross Modal Interaction (2024.naacl-long)
Copied to clipboard
| Challenge: | masked language modeling is widely used as a pretraining component in Vision and language (V+L) but performance on benchmarks has not received the attention it deserves. |
| Approach: | They propose a curriculum masking scheme that uses a parallel mask selection agent to mask tokens at a frequency proportional to the level of cross modal interaction necessary to reconstruct them. |
| Outcome: | The proposed method improves relational understanding on a wide range of V+L tasks. |