| Challenge: | Existing work has focused on learning monotonic attention behavior via specialized attention functions or pretraining. |
| Approach: | They introduce a monotonicity loss function compatible with standard attention mechanisms and test it on sequence-to-sequence tasks. |
| Outcome: | The proposed monotonicity loss function can achieve largely monotonic behavior on grapheme-to-phoneme conversion, morphological inflection, transliteration, and dialect normalization tasks. |
Similar Papers
Exact Hard Monotonic Attention for Character-Level Transduction (P19-1)
Copied to clipboard
| Challenge: | Neural sequence-to-sequence models with soft attention outperform monotonic models . current dominant method is the neural sequenceto-Sequency model with soft focus . |
| Approach: | They develop a hard attention sequence-to-sequence model that enforces strict monotonicity and learns alignment jointly. |
| Outcome: | The proposed model achieves state-of-the-art on grapheme-to-phoneme conversion and morphological inflection generation. |
Hard Non-Monotonic Attention for Character-Level Transduction (D18-1)
Copied to clipboard
| Challenge: | Character-level string-to-string transductions are an important component of NLP tasks . hard non-monotonic attention models have been used for sequence modeling tasks involving characters . |
| Approach: | They propose an exact algorithm for marginalizing over the exponential number of non-monotonic alignments between two strings. |
| Outcome: | The proposed algorithm outperforms soft attention and improves performance over stochastic approximation. |
On the Distribution, Sparsity, and Inference-time Quantization of Attention Values in Transformers (2021.findings-acl)
Copied to clipboard
Tianchu Ji, Shraddhan Jain, Michael Ferdman, Peter Milder, H. Andrew Schwartz, Niranjan Balasubramanian
| Challenge: | Recent work shows that attention can be pruned to zeros with minimal loss in accuracy. |
| Approach: | They propose a pruning technique which quantizes attention to a 3-bit format without retraining . they find that 80% of attention values can be pruned to zeros with minimal loss in accuracy . |
| Outcome: | The proposed approach produces only a few unique attention values with minimal loss in accuracy. |
Alleviating the Inequality of Attention Heads for Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Recent studies show that the attention heads in Transformer are not equal. |
| Approach: | They propose a masking method to mask attention heads in Transformer . they empirically validate the inequality and propose 'head mask' method to avoid bottleneck . |
| Outcome: | The proposed masking method improves translation performance on multiple languages . it can be used to remove a small subset of heads without affecting performance . |
Systematicity Emerges in Transformers when Abstract Grammatical Roles Guide Attention (2022.naacl-srw)
Copied to clipboard
| Challenge: | Existing systems that use transformers lack systematicity, but they are inferior to human learners in sample efficiency and difficult generalization problems. |
| Approach: | They propose to modify a transformer so that it controls attention distributions and fills in the gaps. |
| Outcome: | The proposed model shows that the performance of natural language processing systems is improved when abstract role labels are assigned to the input stream and provided to the role stream. |
Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Tasks (2022.naacl-main)
Copied to clipboard
| Challenge: | Recent advances in machine learning have led to the use of contrastive loss for representation learning. |
| Approach: | They propose to use batch-softmax contrastive loss to train pairwise sentence embeddings . they propose to take a batch-softermax contrastitive loss and train it with different loss functions . |
| Outcome: | The proposed model improves on a number of datasets and pairwise sentence scoring tasks. |
Monotonic Infinite Lookback Attention for Simultaneous Machine Translation (P19-1)
Copied to clipboard
Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey, Chung-Cheng Chiu, Semih Yavuz, Ruoming Pang, Wei Li, Colin Raffel
| Challenge: | Simultaneous machine translation begins to translate each source sentence before the source speaker has finished speaking, with applications to live and streaming scenarios. |
| Approach: | They propose a simultaneous translation system that learns an adaptive schedule with a neural machine translation model that attends over all source tokens read thus far. |
| Outcome: | The proposed system can achieve latency-quality trade-offs favorable to a proposed wait-k strategy for many latency values. |
Guiding Attention for Self-Supervised Learning with Transformers (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies show that self-attention patterns in trained models contain a majority of non-linguistic regularities. |
| Approach: | They propose a technique to allow efficient self-supervised learning with bi-directional Transformers by using an auxiliary loss function to guide attention heads to conform to such patterns. |
| Outcome: | The proposed method achieves state-of-the-art in low-resource settings and is agnostic to pre-training objectives. |
Frequency Balanced Datasets Lead to Better Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evidence that high-frequency tokens in pretraining data might bias learning, causing undesired effects, is not clear. |
| Approach: | They propose a sampling algorithm that iteratively assesses token frequencies and removes sentences that contain still high-frequency tokens, resulting in a balanced dataset. |
| Outcome: | The proposed method reduces the amount of pre-training data required for training attention-based transformer language models by up to three times. |
Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models (2022.acl-short)
Copied to clipboard
| Challenge: | morphological inflection models have been successful with shared tasks . but they fail at generalizing inflation patterns when trained on a limited number of lemmata . |
| Approach: | They find that standard models fail at generalizing inflection patterns when trained on a limited number of lemmata and asked to inflect previously unseen lemma. |
| Outcome: | The proposed model can perform well on morphological inflection tasks if training data covers a diversity of lemmata or some variant of the input lemma has been witnessed during training. |