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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations