| Challenge: | Neural language models are universally autoregressive, generating sentences one token at a time from left to right. |
| Approach: | They propose a two-pass language model that generates partially-filled sentences and fills in missing tokens. |
| Outcome: | The proposed model produces partially-filled sentences and fills in missing tokens. |
Similar Papers
An Empirical Study of Generation Order for Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | a recent study of generation order for machine translation shows it does not affect output quality . Neural sequence models have been successfully applied to a broad range of tasks in recent years . |
| Approach: | They propose a soft order-reward framework that enables models to follow arbitrary oracle generation policies. |
| Outcome: | The proposed framework explores a wide variety of generation orders including uninformed orders, location-based orders, frequency-based or model-based orderings, and model-driven orders. |
Sentence-Level Content Planning and Style Specification for Neural Text Generation (D19-1)
Copied to clipboard
| Challenge: | Recent advances in text generation systems often produce incoherent and unfaithful outputs . a novel automated text generation system takes into account content selection, text planning, and surface realization. |
| Approach: | They propose an end-to-end trained two-step text generation model that considers sentence-level content planners and language styles. |
| Outcome: | The proposed model outperforms competing models in three domains with diverse topics and varying language styles. |
Learning and Analyzing Generation Order for Undirected Sequence Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Undirected neural sequence models generate monotonically from left to right in machine translation tasks. |
| Approach: | They train a policy that learns the generation order for a pre-trained, undirected translation model via reinforcement learning. |
| Outcome: | The proposed policy outperforms heuristic generation orders on three out of four language pairs. |
The Amazing World of Neural Language Generation (2020.emnlp-tutorials)
Copied to clipboard
| Challenge: | Recent years have seen a paradigm shift in neural text generation due to advances in deep contextual language modeling and transfer learning. |
| Approach: | They will discuss how and why NLG models succeed/fail at generating coherent text. |
| Outcome: | This paper will discuss how and why these models succeed/fail at generating coherent text, and provide insights on several applications. |
How to represent a word and predict it, too: Improving tied architectures for language modelling (D18-1)
Copied to clipboard
| Challenge: | Recent state-of-the-art models use word embeddings as input and output mappings instead of tied models. |
| Approach: | They propose to decouple hidden state from word embedding prediction . they extend their proposed modification to word2vec models . |
| Outcome: | The proposed architectures achieve comparable or better results compared to previous models without tying . the proposed architecture reduces parameters, enabling more compact models and faster learning. |
Overestimation of Syntactic Representation in Neural Language Models (2020.acl-main)
Copied to clipboard
| Challenge: | Several testing methodologies have been developed to probe models’ syntactic representations. |
| Approach: | They propose a method to determine syntactic structure by training a model on strings generated according to a template and testing its ability to distinguish between similar ones with different syntax. |
| Outcome: | The proposed method reproduces positive results with two non-syntactic baseline language models: an n-gram model and an LSTM model trained on scrambled inputs. |
Attribute Alignment: Controlling Text Generation from Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models can generate text with sentiment polarity or specific topics without changing the original model parameters. |
| Approach: | They propose a method for controlling text generation by aligning disentangled attribute representations. |
| Outcome: | The proposed method shows large performance gains while maintaining diversity and fluency. |
A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation (N18-1)
Copied to clipboard
| Challenge: | a recent study has shown that natural language generators produce utterances with humanlike coherence and naturalness for many different kinds of content. |
| Approach: | They propose to use a neural language generator to generate a syntactically and semantically correct utterance from a given MR. |
| Outcome: | The proposed model outperforms state-of-the-art models on restaurant, TV and laptop datasets. |
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (D18-1)
Copied to clipboard
| Challenge: | Neural machine translation suffers from exposure bias and error propagation problem. |
| Approach: | They conduct a series of analyses to deeply understand the accuracy drop problem . they find that the left part of the translated sentence is often better than its right part . |
| Outcome: | The results show that the left part of the translated sentence is often better than its right part in left-to-right decoding models. |
Language Modeling with a General Second-Order RNN (2020.lrec-1)
Copied to clipboard
| Challenge: | a number of RNNs update their state as the input sequence is processed . second-order RNN architectures show promising performance in language modeling . |
| Approach: | They propose a second-order RNN architecture that generalizes existing ones . they use a Penn Treebank dataset to analyze how their different components affect performance . |
| Outcome: | The proposed architecture generalizes existing RNNs on a Penn Treebank dataset . it shows that removing the first-order terms does not hinder performance . |