Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Recent unsupervised sentence compression approaches use custom objectives to guide discrete search, but guided search is expensive at inference time. |
| Approach: | They propose to use reinforcement learning to train effective sentence compression models that are also fast when generating predictions. |
| Outcome: | The proposed model outperforms other unsupervised models while being faster at inference time. |
Similar Papers
SCAR: Sentence Compression using Autoencoders for Reconstruction (2020.acl-srw)
Copied to clipboard
| Challenge: | Sentence compression is the task of shortening a sentence while retaining its meaning. |
| Approach: | They propose to use a supervised deep learning framework to shorten sentences while retaining their meaning by a compressor and reconstructor. |
| Outcome: | The proposed model achieves higher ROUGE scores on benchmark datasets than the existing state-of-the-art methods and baselines. |
SEQˆ3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression (N19-1)
Copied to clipboard
| Challenge: | Neural sequence-to-sequence models are currently the dominant approach in natural language processing tasks, but require massive parallel corpora. |
| Approach: | They propose a sequence-to-sequence-tosequnce autoencoder with words as latent variables . they apply the model to unsupervised abstractive sentence compression . |
| Outcome: | The proposed model achieves promising results in unsupervised sentence compression on benchmark datasets. |
Generating Multiple-Length Summaries via Reinforcement Learning for Unsupervised Sentence Summarization (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models to summarize texts without ground-truth summaries are extractive, which remove words from texts and thus are less flexible than abstractive models. |
| Approach: | They propose an unsupervised model that extracts words from texts and makes them mutually enhance each other. |
| Outcome: | The proposed model outperforms both abstractive and extractive models, while generating new words not contained in input texts. |
Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features (N18-1)
Copied to clipboard
| Challenge: | Currently, unsupervised word embeddings are routinely trained on large amounts of raw text data. |
| Approach: | They propose to use unsupervised word embeddings to train distributed representations of sentences. |
| Outcome: | The proposed method outperforms state-of-the-art models on most benchmark tasks and is robust to the produced general-purpose sentence embeddings. |
Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction (N19-1)
Copied to clipboard
| Challenge: | In reinforcement learning-based sentence generation, the large action space is often too computa-tionally demanding to be used with large training data. |
| Approach: | They propose to reduce the action space by using dynamic vocabulary prediction to generate a fixed-size small vocabulary for each input to generate its target sentence. |
| Outcome: | The proposed method achieves faster reinforcement learning (2.7x faster) with less GPU memory (2.3x less) and more rewards with fewer iterations of supervised pre-training. |
Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent transformer language models achieve outstanding results on many downstream tasks, but their enormous size often makes them impractical on memory-constrained devices. |
| Approach: | They propose an offline compression approach that reduces the complexity of the model by enabling collaboration between modules. |
| Outcome: | The proposed approach outperforms commonly used factorization-based offline compression methods on various NLP tasks. |
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT (2021.tacl-1)
Copied to clipboard
Prakhar Ganesh, Yao Chen, Xin Lou, Mohammad Ali Khan, Yin Yang, Hassan Sajjad, Preslav Nakov, Deming Chen, Marianne Winslett
| Challenge: | Popular pre-trained Transformers have improved performance for various NLP tasks by sizable margins, but are too resource-hungry and computation-intensive to suit low-capacity devices or applications with strict latency requirements. |
| Approach: | They present a literature review of the compression of Transformers, focusing on the popular BERT model, which has attracted considerable research attention. |
| Outcome: | The proposed models improve Sentiment analysis, paraphrase detection, machine reading comprehension, question answering, text summarization, and other tasks by sizable margins. |
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to learn sentence embeddings require labeled data, but it is expensive. |
| Approach: | They propose an unsupervised method which learns sentence embeddings using unlabeled data . they propose a transformer-based sequence denoising auto-encoder which can be used for training . |
| Outcome: | The proposed method outperforms existing methods on four datasets from heterogeneous domains. |
Learning Compressed Sentence Representations for On-Device Text Processing (P19-1)
Copied to clipboard
Dinghan Shen, Pengyu Cheng, Dhanasekar Sundararaman, Xinyuan Zhang, Qian Yang, Meng Tang, Asli Celikyilmaz, Lawrence Carin
| Challenge: | Existing methods for learning sentence embeddings assume they are continuous and real-valued. |
| Approach: | They propose four different strategies to transform continuous and generic sentence embeddings into a binarized form while preserving their rich semantic information. |
| Outcome: | The proposed methods reduce storage requirements by over 98% and improve performance on downstream tasks. |
Towards Lossless Encoding of Sentences (P19-1)
Copied to clipboard
| Challenge: | Existing methods for encoding text into lossless representations focus on performing well on downstream tasks and are unable to reconstruct original sequence from learned embedding. |
| Approach: | They propose a lossless method for encoding long sequences of texts into feature rich representations by recursive autoencoding. |
| Outcome: | The proposed method performs well on sentiment analysis and sentiment classification tasks. |