Papers with Transformer model
Two-Headed Monster and Crossed Co-Attention Networks (2020.aacl-srw)
Copied to clipboard
| Challenge: | a new co-attentional neural structure is proposed for machine translation tasks . a higher-level and more abstract paradigm generalized from CCNs is proposed . |
| Approach: | They propose a paradigm that consists of two symmetric encoder modules and one decoder module connected with co-attention. |
| Outcome: | The proposed model outperforms the current Transformer model on translation tasks but the epoch time increases by circa 75%. |
Resisting the Lure of the Skyline: Grounding Practices in Active Learning for Morphological Inflection (2024.acl-short)
Copied to clipboard
| Challenge: | Several approaches to active learning are available, including confidence-based, diversity-based and committee-based. |
| Approach: | They propose to use a baseline and a skyline to measure the accuracy of the unannotated sample pool. |
| Outcome: | The proposed model outperforms a random selection baseline and a skyline approach. |
Semantic Structural Decomposition for Neural Machine Translation (2020.starsem-1)
Copied to clipboard
| Challenge: | Existing methods for translation of long sentences are limited by the translation of single sentences to single sentences. |
| Approach: | They propose to use semantic splitting of the source sentence as preprocessing for machine translation. |
| Outcome: | The proposed approach tackles two main limitations of state-of-the-art machine translation. |
A Multiscale Visualization of Attention in the Transformer Model (P19-3)
Copied to clipboard
| Challenge: | Various tools have been developed to visualize attention in NLP models, ranging from attention-matrix heatmaps to bipartite graph representations. |
| Approach: | They propose an open-source tool that visualizes attention at multiple scales and provides a unique perspective on the attention mechanism. |
| Outcome: | The proposed model outperforms OpenAI GPT-2 and BERT on several language modeling benchmarks. |
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation (P18-1)
Copied to clipboard
Mia Xu Chen, Orhan Firat, Ankur Bapna, Melvin Johnson, Wolfgang Macherey, George Foster, Llion Jones, Mike Schuster, Noam Shazeer, Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Zhifeng Chen, Yonghui Wu, Macduff Hughes
| Challenge: | In recent years, the emergence of seq2seq models has revolutionized the field of machine translation by replacing traditional phrase-based approaches with neural machine translation (NMT) systems based on the encoder-decoder paradigm. |
| Approach: | They propose to use a convolutional seq2seq model to combine the strengths of the two approaches. |
| Outcome: | The proposed architectures outperform the existing models on the WMT’14 benchmark dataset. |
Making Asynchronous Stochastic Gradient Descent Work for Transformers (D19-56)
Copied to clipboard
| Challenge: | Asynchronous stochastic gradient descent (SGD) converges poorly for Transformer models . synchronous SGD is faster at raw training speed since it avoids waiting for synchronization . |
| Approach: | They propose a method to restore convergence by summing several asynchronous updates instead of applying them immediately. |
| Outcome: | The proposed method achieves the same BLEU score 1.36 times faster than asynchronous SGD. |
Combining Subword Representations into Word-level Representations in the Transformer Architecture (2020.acl-srw)
Copied to clipboard
| Challenge: | Currently dominant approaches use word-level tokens, but this increases the length of the sequences and makes it difficult to profit from word-based information. |
| Approach: | They propose to combine subword-level representations into word-level ones in the first layers of the encoder, reducing the effective length of the sequences in the following layers. |
| Outcome: | The proposed model maintains translation quality with no extra word-level information . it is superior to the current dominant method for incorporating word- level source language information a priori . |
Long Warm-up and Self-Training: Training Strategies of NICT-2 NMT System at WAT-2019 (D19-52)
Copied to clipboard
| Challenge: | NICT-2 neural machine translation system was presented at the 6th Workshop on Asian Translation (WAT-2019) |
| Approach: | They describe a NICT-2 neural machine translation system at the 6th Workshop on Asian Translation . they employ a long warm-up strategy and a self-training strategy that uses multiple back-translations generated by sampling to improve the translation quality. |
| Outcome: | The proposed system improves translation quality and learning rate by using the long warm-up and self-training strategies. |
Supervised neural machine translation based on data augmentation and improved training & inference process (D19-52)
Copied to clipboard
| Challenge: | This paper describes the neural machine translation systems for the shared translation tasks of WAT 2019 . |
| Approach: | They propose a model for translation tasks of WAT 2019 that employs a Transformer model as the baseline and a deep layer model to improve translation quality. |
| Outcome: | The proposed methods can improve translation quality over traditional statistical machine translation (SMT) The proposed models can improve the translation quality of Japanese-English and Japanese-Chinese corpus. |
Detecting Annotation Errors in Morphological Data with the Transformer (2022.acl-short)
Copied to clipboard
| Challenge: | Annotation errors that stem from various sources are usually unavoidable when performing large-scale annotation of linguistic data. |
| Approach: | They evaluate the feasibility of using a deep learning model to detect annotator errors in morphological data sets that contain inflected word forms. |
| Outcome: | The proposed model detects typographic errors, linguistic confusion errors and self-adversarial errors on four languages. |
Our Neural Machine Translation Systems for WAT 2019 (D19-52)
Copied to clipboard
| Challenge: | In the last five years, statistical machine translation is gradually fading out in favor of neural machine translation. |
| Approach: | They describe a novel Neural Machine Translation (NMT) system for the WAT 2019 translation tasks they focus on. |
| Outcome: | The proposed system improves translation accuracy while replacing absolute position representations with relative positions. |
Idiap NMT System for WAT 2019 Multimodal Translation Task (D19-52)
Copied to clipboard
| Challenge: | In the past few decades, multi-modality has received critical attention in translation studies, although the benefit of visual modality in machine translation is still in debate. |
| Approach: | They propose to use the Transformer model and IITB English-Hindi parallel corpus as additional data sources for the evaluation and challenge test sets. |
| Outcome: | The proposed system outperforms systems that consider visual information in the English-Hindi Multi-Modal Translation task. |
What Works and Doesn’t Work, A Deep Decoder for Neural Machine Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Deep learning has demonstrated performance advantages in a wide range of natural language processing tasks. |
| Approach: | They propose to deepen the decoder layer in a Transformer model to reduce the difficulty of deep learning. |
| Outcome: | The proposed method can deepen the model on both the encoder and decoder at the same time, resulting in a deeper model and improved performance. |
English-Indonesian Neural Machine Translation for Spoken Language Domains (P19-2)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a data-driven method that requires a large amount of data to build a robust model. |
| Approach: | They conduct a study on Neural Machine Translation (NMT) for English-Indonesian and Indonesian-English (ID-EN) they build NMT systems using the Transformer model for both translation directions and implement domain adaptation method to train pre-trained NMT on speech language data. |
| Outcome: | The proposed model can learn formal translation outputs for English-Indonesian and Indonesian-English (ID-EN) given a small dataset of speech-styled language and a larger dataset of less formal language, the proposed model will be useful for learning formality level. |
Improving the Transformer Translation Model with Document-Level Context (D18-1)
Copied to clipboard
| Challenge: | Existing models for document-level context translation ignore documentlevel context. |
| Approach: | They propose a document-level context encoder to represent document- level context and integrate it into the Transformer model. |
| Outcome: | Experiments on NIST Chinese-English and IWSLT French-English datasets show that the proposed translation model outperforms the Transformer model significantly. |
Scheduled Sampling for Transformers (P19-2)
Copied to clipboard
| Challenge: | Existing studies show that scheduled sampling can be applied to recurrent neural networks to avoid exposure bias. |
| Approach: | They propose to use teacher forced embeddings and model predictions to avoid exposure bias in sequence-to-sequence generation. |
| Outcome: | The proposed technique achieves performance close to a teacher-forcing baseline on two language pairs and is promising for future research. |
Improving Compositional Generalization in Classification Tasks via Structure Annotations (2021.acl-short)
Copied to clipboard
| Challenge: | Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. |
| Approach: | They propose to convert a natural language sequence-to-sequence dataset into a classification dataset that requires compositional generalization. |
| Outcome: | The proposed model can generalize compositionally by providing hints on the structure of the input. |
Towards Modeling the Style of Translators in Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | a key ingredient of neural machine translation is the use of large datasets with different but consistent translation styles . however, the models do not capture the variety of translators' styles from the data . a recent study shows that style-augmented models can capture the style variations of translator . |
| Approach: | They propose to augment a neural machine translation model with translator information . they use TED talk datasets to model and control translator-related stylistic variations . |
| Outcome: | The proposed models capture the style variations of translators and generate translations with different styles on new data. |
Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for text generation ignore faithfulness between generated text and table . current methods ignore faithfulity, leading to generated information that goes beyond table content . |
| Approach: | They propose a Transformer-based generation framework to enforce faithfulness between generated text and table . they propose metric to evaluate faithfulness and automatic metric for automatic generating . |
| Outcome: | The proposed framework outperforms state-of-the-art methods in automatic evaluations and human evaluations. |
Modeling Recurrence for Transformer (N19-1)
Copied to clipboard
| Challenge: | Existing studies show that the lack of recurrence modeling hinders the development of a translation model. |
| Approach: | They propose to model recurrence for Transformer with an additional recurrent encoder. |
| Outcome: | The proposed model outperforms the deep model on EnglishGerman and ChineseEnglish translation tasks. |
UserAdapter: Few-Shot User Learning in Sentiment Analysis (2021.findings-acl)
Copied to clipboard
| Challenge: | Adapting a model to a handful of personalized data is challenging, authors say . standard fine-tuning requires hundreds of millions of parameters for each user . |
| Approach: | They propose a lightweight method that clamps millions of parameters of a Transformer model and optimizes a tiny user-specific vector. |
| Outcome: | The proposed method improves accuracy on Yelp and IMDB datasets and reduces the number of parameters added for each user. |
Hero-Gang Neural Model For Named Entity Recognition (2022.naacl-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is a fundamental and important task in natural language processing. |
| Approach: | They propose a novel Hero-Gang Neural structure to leverage both global and local information to promote NER by using a Transformer-based encoder and a Gang module. |
| Outcome: | The proposed model can extract local features and position information from the Hero and Gang modules, and it performs on multiple datasets. |
End-to-End Neural Word Alignment Outperforms GIZA++ (2020.acl-main)
Copied to clipboard
| Challenge: | Word alignment was once a core unsupervised learning task in natural language processing . but word alignment still plays an important role in interactive applications of neural machine translation, such as annotation transfer and lexicon injection. |
| Approach: | They propose to use a Transformer model to train an unsupervised word alignment model. |
| Outcome: | The proposed method outperforms GIZA++ on three data sets and is tightly integrated and does not affect translation quality. |
Enhancing Machine Translation with Dependency-Aware Self-Attention (2020.acl-main)
Copied to clipboard
| Challenge: | Currently, most neural machine translation models rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. |
| Approach: | They propose a parameter-free, dependency-aware self-attention mechanism that integrates syntactic knowledge into a Transformer model and propose 'a parameter free approach' they also propose - a novel mechanism that improves translation quality for long sentences and in low-resource scenarios. |
| Outcome: | The proposed approach improves translation quality on English-German and English-Turkish translation tasks and in low-resource scenarios. |
Data Augmentation and Learned Layer Aggregation for Improved Multilingual Language Understanding in Dialogue (2022.findings-acl)
Copied to clipboard
| Challenge: | Multi-SentAugment and LayerAgg are self-training methods that augment available training data with similar (automatically labelled) in-domain sentences from large monolingual Web-scale corpora. |
| Approach: | They propose to use multi-sentaugment and layeragg to improve dialogue natural language understanding across multiple languages. |
| Outcome: | The proposed methods generalise well in zero- and few-shot scenarios and leverage external unannotated data sources. |
Image Caption Generation for News Articles (2020.coling-main)
Copied to clipboard
| Challenge: | Existing work on news-image captioning requires a joint understanding of image and text. |
| Approach: | They propose a Transformer model that integrates text and image modalities and attends to textual features from visual features in generating a caption. |
| Outcome: | The proposed model outperforms the state-of-the-art model and improves the quality of news-image captions. |
Paraphrase Generation and Evaluation on Colloquial-Style Sentences (2020.lrec-1)
Copied to clipboard
| Challenge: | a new study investigates the quality and novelty of generated paraphrases . paraphrase models can be used for information retrieval and data mining . |
| Approach: | They use state-of-the-art neural machine translation models trained on the Opusparcus corpus to generate paraphrases in six languages. |
| Outcome: | The proposed model outperforms the existing model on human evaluation in five of the six languages. |
QueryForm: A Simple Zero-shot Form Entity Query Framework (2023.findings-acl)
Copied to clipboard
Zifeng Wang, Zizhao Zhang, Jacob Devlin, Chen-Yu Lee, Guolong Su, Hao Zhang, Jennifer Dy, Vincent Perot, Tomas Pfister
| Challenge: | Form-like document understanding is a key yet under-investigated problem . endlessly training specialized models on new document types is not scalable in many practical scenarios. |
| Approach: | They propose to use large-scale query-entity pairs generated from form-like webpages to pre-train QueryForm. |
| Outcome: | The proposed framework sets state-of-the-art average F1 score on XFUND and Payment benchmarks. |
Adversarial Grammatical Error Correction (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that adversarial-GEC can achieve competitive GEC quality compared to NMT-based baselines. |
| Approach: | They propose an adversarial approach to Grammatical Error Correction using a transformer-based model and a sentence-pair classification model. |
| Outcome: | The proposed approach achieves competitive GEC quality compared to baselines. |
Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Experimental results show that the Reinforce-NAT system surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed. |
| Approach: | They propose a sequence-level training method and a Transformer decoder to fuse the target sequential information into the top layer of the decoded Transformer. |
| Outcome: | The proposed model surpasses the baseline NAT system on BLEU without decelerating the decoding speed and achieves comparable translation performance to the autoregressive Transformer model with considerable speedup. |
Optimizing Transformer for Low-Resource Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Language pairs with limited amounts of parallel data remain a challenge for neural machine translation. |
| Approach: | They propose to optimize a Transformer model for low-resource conditions to improve translation quality by 7.3 BLEU points compared to the default settings. |
| Outcome: | The proposed model improves translation quality up to 7.3 BLEU points compared to the default settings on the IWSLT14 training data compared with the Transformer model. |
Code Execution with Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
Chenxiao Liu, Shuai Lu, Weizhu Chen, Daxin Jiang, Alexey Svyatkovskiy, Shengyu Fu, Neel Sundaresan, Nan Duan
| Challenge: | Pre-trained code intelligence models ignore the execution trace and only rely on source code and syntactic structures to understand code execution. |
| Approach: | They develop a mutation-based data augmentation technique to create a Python dataset and task for code execution that challenges existing models. |
| Outcome: | The proposed model outperforms existing models on code execution and shows its potential for zero-shot code-to-code search and text-to code generation. |
Incorporating Noisy Length Constraints into Transformer with Length-aware Positional Encodings (2020.coling-main)
Copied to clipboard
| Challenge: | Neural Machine Translation suffers from an under-translation problem due to limited modeling of output sequence lengths. |
| Approach: | They propose a method to train a Transformer model using length constraints based on positional encoding. |
| Outcome: | The proposed method outperforms a vanilla Transformer in an English-to-Japanese translation by 3.22 points . the noise injection improved robustness for length prediction errors, especially within the window size. |
Quantifying Attention Flow in Transformers (2020.acl-main)
Copied to clipboard
| Challenge: | In the Transformer model, “self-attention” combines information from attended embeddings into the representation of the focal embeddable in the next layer. |
| Approach: | They propose two methods to quantify flow of information through self-attention using attention weights as relative relevance of input tokens. |
| Outcome: | The proposed methods give complementary views on the flow of information and yield higher correlations with importance scores of input tokens. |
Multi-Path Transformer is Better: A Case Study on Neural Machine Translation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Extensive experiments on 12 WMT tasks show that shallower multi-path models can achieve similar or even better performance than the deeper model. |
| Approach: | They propose to use a parameter-efficient multi-path structure to fuse features extracted from different paths to achieve better performance. |
| Outcome: | The proposed model can achieve better performance with the same number of parameters than the deeper model. |
Analyzing the Inner Workings of Transformers in Compositional Generalization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on compositional generalization abilities of neural models have focused on benchmarks, but the results do not reflect the underlying competence of the model. |
| Approach: | They propose to find an existing subnetwork that contributes to the generalization performance and perform causal analyses on how the model utilizes syntactic features. |
| Outcome: | The proposed model relies on syntactic features but the subnetwork with better generalization performance relies mainly on a non-compositional algorithm . |
Towards Learning (Dis)-Similarity of Source Code from Program Contrasts (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models that focus on identifying functional (dis)similarity of source code get confused when trying to identify functional (Dis)-similarities. |
| Approach: | They propose to pre-train a Transformer model with such automatically generated program contrasts to better identify similar code in the wild and differentiate vulnerable programs from benign ones. |
| Outcome: | The proposed model outperforms existing models in vulnerability and code clone detection tasks even with much less data. |
A Transformer-based Approach for Source Code Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Generating a readable summary that describes the functionality of a program is known as source code summarization. |
| Approach: | They propose a Transformer model that uses a self-attention mechanism to capture long-range dependencies by encoding source code tokens relative to the code token position. |
| Outcome: | The proposed model outperforms the state-of-the-art methods by a significant margin. |
Jointly Learning to Align and Translate with Transformer Models (D19-1)
Copied to clipboard
| Challenge: | Existing word alignment models are not accurate for word alignments. |
| Approach: | They propose a method to train a Transformer model to produce accurate translations and alignments. |
| Outcome: | The proposed model outperforms GIZA++ trained models on translation and alignment tasks while maintaining translation accuracy. |
Simple Recurrent Units for Highly Parallelizable Recurrence (D18-1)
Copied to clipboard
| Challenge: | recurrent neural networks scale poorly due to the intrinsic difficulty in parallelizing their state computations. |
| Approach: | They propose a simple recurrent unit that provides expressive recurrence and allows highly parallel implementation. |
| Outcome: | The proposed model achieves 5—9x speed-up over cuDNN-optimized LSTM on classification and question answering datasets and delivers stronger results than LS and convolutional models. |
Eeny, meeny, miny, moe. How to choose data for morphological inflection. (2022.emnlp-main)
Copied to clipboard
| Challenge: | Data scarcity is a major bottleneck for many natural language processing tasks . active learning aims to reduce the cost of data annotation by selecting the most informative examples to label. |
| Approach: | They propose to use oracle experiments to select data that is most informative for the model. |
| Outcome: | The proposed sampling strategies show that they improve on the oracle experiment and the 10-cycle iteration using Natügu as a case study. |
Transkimmer: Transformer Learns to Layer-wise Skim (2022.acl-long)
Copied to clipboard
| Challenge: | Prior work has proposed to augment Transformer model with the capability of skimming tokens to improve its computational efficiency. |
| Approach: | They propose to add a parameterized predictor before each layer that learns to make the skimming decision. |
| Outcome: | The proposed model achieves 10.97x speedup on GLUE benchmark compared with BERT-base baseline with less than 1% accuracy degradation. |
OpinionDigest: A Simple Framework for Opinion Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Abstractive opinion summarization framework outperforms competitors' summarizing frameworks . extractive approaches produce well-formed text, but selecting the most popular opinions is challenging . |
| Approach: | They propose an abstractive opinion summarization framework that trains a Transformer model to reconstruct reviews from extracted opinions. |
| Outcome: | The proposed framework outperforms baselines on Yelp and shows promising customization capabilities. |
Linear Recency Bias During Training Improves Transformers’ Fit to Reading Times (2025.coling-main)
Copied to clipboard
| Challenge: | Recent research has shown a strong fit between surprisal values from Transformers and reading times. |
| Approach: | They evaluate a Transformer model that uses a recency bias added to attention scores to improve the fit to human reading times. |
| Outcome: | The proposed model improves on a Transformer that includes a recency bias added to attention scores. |
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation (2025.acl-long)
Copied to clipboard
Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li
| Challenge: | Extensive experiments demonstrate that treating attention as a feature map and applying convolution as . a processing method significantly enhances Transformer performance. |
| Approach: | They propose to use the convolution operator to mimic the processing methods in computer vision to treat attention as a feature map and apply it to neighboring attention scores across different heads. |
| Outcome: | The proposed model can be adapted to various attention-related models and achieves high performance. |
Adaptive Attention for Sparse-based Long-sequence Transformer (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that Transformers can process longer sequences because of their complexity and time scales quadratic to the sequence length. |
| Approach: | They propose an efficient Transformer model with adaptive attention that can select useful tokens automatically in sparse attention by learnable position vectors. |
| Outcome: | The proposed model can select useful tokens automatically in sparse attention by learnable position vectors. |
Sparsifying Transformer Models with Trainable Representation Pooling (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to sparsify attention in the Transformer model are based on quadratic memory complexity and a lack of information for each word. |
| Approach: | They propose a method to sparsify attention in a Transformer model by learning to select the most-informative token representations during the training process. |
| Outcome: | The proposed model performs better than the current SOTA model while being 1.8 faster during training, 4.5 faster inference and 13 more efficient in the decoder. |
A Multi-Perspective Analysis of Memorization in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can generate the same sequences contained in the pre-train corpus, known as memorization. |
| Approach: | They analyze the relationship between memorization and outputs from Large Language Models (LLMs) they show a sudden drop and increase in the frequency of input tokens when generating memorized/unmemorized sequences . |
| Outcome: | The proposed model can generate the same sequences contained in the pre-train corpus, and it can predict unmemorized tokens. |
Humanistic Buddhism Corpus: A Challenging Domain-Specific Dataset of English Translations for Classical and Modern Chinese (2024.lrec-main)
Copied to clipboard
| Challenge: | Compared to existing machine translation datasets, HBC presents unique challenges . classical and modern Chinese texts are often translated in distant languages . |
| Approach: | They propose a dataset containing 80,000 Chinese-English parallel phrases extracted and translated from publications in the domain of Buddhism. |
| Outcome: | The Humanistic Buddhism Corpus (HBC) contains 80,000 parallel Chinese-English phrases extracted and translated from publications in the domain of Buddhism. |
Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings (2021.emnlp-main)
Copied to clipboard
| Challenge: | Semantic sentence embeddings are usually supervisedly built minimizing distances between pairs of embeddable sentences labelled as semantically similar by annotators. |
| Approach: | They propose a language-independent approach to build large datasets of pairs of informal texts weakly similar, without manual human effort, exploiting Twitter’s powerful signals of relatedness: replies and quotes of tweets. |
| Outcome: | The proposed model learns classical Semantic Textual Similarity, and excels on tasks where pairs of sentences are not exact paraphrases. |
myMediCon: End-to-End Burmese Automatic Speech Recognition for Medical Conversations (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing medical conversation speech corpora for Burmese are limited, despite advances in ASR. |
| Approach: | They propose to use a manually curated medical conversation speech corpus for Burmese to examine the performance of ASR models. |
| Outcome: | The proposed model outperforms the Transformer model and the Recurrent Neural Network (RNN) models. |
Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train large language models that require a non-uniform model norm are not effective. |
| Approach: | They propose a technique that allows for uniformity of the norm of the model parameters . they propose 'weight scaling as reparameterization' to adjust the norm to the parameter . |
| Outcome: | The proposed technique outperforms existing methods and stabilizes training with the transformer decoders. |