Learning Universal Sentence Representations with Mean-Max Attention Autoencoder (D18-1)
Copied to clipboard
| Challenge: | Existing methods to learn universal sentence representations focus on supervised learning. |
| Approach: | They propose a mean-max attention autoencoder that uses a multi-head mechanism to reconstruct the input sequence. |
| Outcome: | The proposed model outperforms state-of-the-art unsupervised single methods on a wide range of 10 transfer tasks. |
Similar Papers
Phrase-level Self-Attention Networks for Universal Sentence Encoding (D18-1)
Copied to clipboard
| Challenge: | Phrase-level self-attention networks (PSAN) can capture context dependencies at the phrase level instead of the sentence level. |
| Approach: | They propose to perform self-attention across words inside a phrase to capture context dependencies at the phrase level and use the gated memory updating mechanism to refine each word’s representation hierarchically with longer-term context dependency captured in a larger phrase. |
| Outcome: | The proposed model can achieve state-of-the-art performance across a plethora of NLP tasks including binary and multi-class classification, natural language inference and sentence similarity. |
Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems (2021.emnlp-main)
Copied to clipboard
| Challenge: | Training and inference using large transformer models can be computationally expensive because the self-attention's time and memory grow quadratically with sequence length. |
| Approach: | They propose a modified transformer architecture that constrains the encoder-decoder attention mechanism to a subset of input sentences while maintaining system performance. |
| Outcome: | The proposed architecture can be trained and inferenced using large transformer models with expensive training and induction costs. |
RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition (P18-4)
Copied to clipboard
| Challenge: | Using RETURNN, we train and decode attention models for translation and speech recognition. |
| Approach: | They propose a layer-wise pretraining scheme for recurrent attention models and show its significant effect on deep recurrence encoder networks. |
| Outcome: | The proposed training and decoding scheme improves 1% on expected training and improves on WMT 2017 and Switchboard. |
Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning (P19-1)
Copied to clipboard
| Challenge: | Encoder-decoder models for unsupervised sentence representation learning discard decoder after training . decoded sentences are often used to make better predictions of words in a given sentence . |
| Approach: | They propose two types of decoding functions whose inverse can be easily derived without expensive inverse calculation. |
| Outcome: | The proposed models can learn good representations from encoders and decoders without expensive calculations. |
Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak Decoder (2021.emnlp-main)
Copied to clipboard
Shuqi Lu, Di He, Chenyan Xiong, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tie-Yan Liu, Arnold Overwijk
| Challenge: | Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. |
| Approach: | They propose a self-learning method that pre-trains the autoencoder using a weak decoder to push the encoder to provide better sequence representations. |
| Outcome: | The proposed model significantly boosts the effectiveness and few-shot ability of dense retrieval models on web search, news recommendation, and open domain question answering. |
Deep Attentive Sentence Ordering Network (D18-1)
Copied to clipboard
| Challenge: | Existing methods for sentence ordering tasks rely on linguistic knowledge and are domain specific. |
| Approach: | They propose a deep attentive sentence ordering network which integrates self-attention mechanism with LSTMs in the encoding of input sentences. |
| Outcome: | The proposed model outperforms the state-of-the-art models on Sentence Ordering and Order Discrimination tasks and is shown to be highly efficient. |
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. |
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation (P18-1)
Copied to clipboard
| Challenge: | Existing encoder-decoder dialog models cannot output interpretable actions as in traditional systems. |
| Approach: | They propose an unsupervised discrete sentence representation learning method that integrates with existing encoder-decoder dialog models for interpretable response generation. |
| Outcome: | The proposed model can be integrated with existing encoder-decoder dialog models and discover interpretable semantics via either auto encoding or context predicting. |
Sentence Representation Learning with Generative Objective rather than Contrastive Objective (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing sentences-level training objectives focus on acquiring sentence-level representations, but they lack effective self-supervised objectives. |
| Approach: | They propose a generative self-supervised learning objective based on phrase reconstruction to improve sentence representation. |
| Outcome: | Empirical results show that the proposed objective outperforms current methods on STS benchmarks and retrieval and reranking tasks. |
Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks (D18-1)
Copied to clipboard
| Challenge: | a popular approach to learning data representations involves the use of an auto-encoder that compresses data into a latent-space representation without supervision. |
| Approach: | They propose to train an auto-encoder that encodes input text into human-readable sentences . they use comprehensible natural language as a latent representation of the input source text . |
| Outcome: | The proposed auto-encoder can encode input text into human-readable sentences without document-summary pairs. |