Challenge: Existing methods for text generation do not fully reflect the rich diversity of human language.
Approach: They propose to use F2-Softmax and MefMax to train a balanced frequency distribution using a frequency class-based method.
Outcome: The proposed methods improve the diversity and quality of generated texts.

Similar Papers

Speeding Up Entmax (2022.findings-naacl)

Copied to clipboard

Challenge: Recent studies suggest that sparsity is a problem when the trained model is used for inference.
Approach: They propose an alternative to softmax that produces a dense probability distribution but is slower than softmax.
Outcome: The proposed method keeps its virtuous characteristics but is slower than softmax and achieves on par or better performance in machine translation task.
Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling (2022.coling-1)

Copied to clipboard

Challenge: Existing methods to generate text using contextual features do not consider syntactic structure clues.
Approach: They propose using linguistic annotation, i.e., part-of-speech (POS), to guide the text generation.
Outcome: The proposed method can generate more diverse text while maintaining comparable quality.
Softmax Bottleneck Makes Language Models Unable to Represent Multi-mode Word Distributions (2022.acl-long)

Copied to clipboard

Challenge: Existing language models can't predict the probability distribution over next words or masked words because of a single hidden state.
Approach: They propose a multi-facet softmax to address the limitations of softmax . they propose LMs that can predict the next word distribution better as their sizes grow .
Outcome: The proposed model achieves two-fold improvements in the perplexity of GPT-2 and BERT.
Extreme Adaptation for Personalized Neural Machine Translation (P18-2)

Copied to clipboard

Challenge: Existing models that capture speaker-related variations do not include explicit information about the speaker.
Approach: They propose a method that adapts the bias of the output softmax to each particular user . they propose to model speaker-related variations as an additional bias vector in the softmax layer .
Outcome: The proposed technique improves translation accuracy and better reflection of speaker traits in target text.
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.
Token-level Adaptive Training for Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing token imbalance phenomenon in natural language as different tokens appear with different frequencies, which leads to different learning difficulties for tokens in Neural machine translation (NMT).
Approach: They propose to assign tokens with different frequencies to target tokens during training to encourage the model to pay more attention to low-frequency tokens.
Outcome: The proposed model yields consistent improvements on ZH-EN, EN-RO, and EN-DE translation tasks, especially on sentences that contain more low-frequency tokens.
Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning (2021.eacl-main)

Copied to clipboard

Challenge: Existing approaches to language modeling use autoregressive methods, but they can produce repetitive results.
Approach: They propose to add a loss function for regularization to avoid unwanted properties, such as contradiction or repetition, to a language model by using policy gradient reinforcement learning.
Outcome: The proposed method reduces repetition without impacting the language model quality.
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice (2022.acl-long)

Copied to clipboard

Challenge: Probabilistic multiclass classifiers with large number of output classes are commonplace in natural language processing.
Approach: They propose to use argmax to predict words from a large vocabulary in NLP models . they find that 13 out of 150 models do indeed have such unargmaxable tokens .
Outcome: The proposed algorithms detect unargmaxable tokens in large language models and translation models.
Discourse-Aware Soft Prompting for Text Generation (2022.emnlp-main)

Copied to clipboard

Challenge: Recent advances in pre-trained langauge models (PLMs) have made great impact on text generation research.
Approach: They propose to use hierarchical blocking to simulate a higher-level discourse structure of human written text and attention sparsity to learn sparse transformations on the softmax-function.
Outcome: The proposed methods perform better on some generation tasks but don't generalize across all generation tasks.
RankGen: Improving Text Generation with Large Ranking Models (2022.emnlp-main)

Copied to clipboard

Challenge: Modern language models assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix.
Approach: They propose a 1.2B parameter encoder model for English that scores model generations given a prefix.
Outcome: The proposed model outperforms decoding algorithms on automatic metrics and human evaluations with English writers.

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