| Challenge: | Conventionally, neural language models are trained by minimizing perplexity (PPL) on grammatical sentences. |
| Approach: | They propose a large margin criterion for training neural language models by minimizing perplexity on grammatical sentences and propose enlarged margins for task-specific training. |
| Outcome: | The proposed method gains up to 1.1 WER reduction for speech recognition and 1.0 BLEU increase for machine translation. |
Similar Papers
Revisiting Simple Neural Probabilistic Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent advances in language modeling have been driven not only by advances in neural architectures, but also through hardware and optimization improvements. |
| Approach: | They revisit the neural probabilistic language model (NPLM) of Bengio et al. (2003) which simply concatenates word embeddings within a fixed window and passes the result through a feed-forward network to predict the next word. |
| Outcome: | The proposed model performs better on word-level language model benchmarks than a baseline Transformer with short input contexts but struggles to handle long-term dependencies. |
Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach (2020.acl-main)
Copied to clipboard
| Challenge: | incorporating syntactic structure into language models has been a challenge since the 1990s. |
| Approach: | They propose to use syntactic information to integrate syntastic structure into neural language models by providing ground truth parse trees as additional training signals. |
| Outcome: | The proposed model achieves lower perplexity and better quality when ground truth parse trees are provided as training signals. |
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. |
Improving Neural Language Models by Segmenting, Attending, and Predicting the Future (P19-1)
Copied to clipboard
| Challenge: | Common language models typically predict the next word given a past context. |
| Approach: | They propose a method that aligns the given context and the following phrase . they define syntactic heights and phrase segmentation rules to enable it to learn . |
| Outcome: | The proposed model outperforms strong baseline models on Wikitext-103 dataset. |
Using Large Corpus N-gram Statistics to Improve Recurrent Neural Language Models (N19-1)
Copied to clipboard
| Challenge: | a technique that uses large corpus n-gram statistics as a regularizer for training a neural network LM on a smaller corpus is effective, and more time-efficient than training on ngrams. |
| Approach: | They propose a technique that uses large corpus n-gram statistics as a regularizer for training on a smaller corpus. |
| Outcome: | The proposed technique is effective and more time-efficient than training on a larger corpus. |
Distant Supervision from Disparate Sources for Low-Resource Part-of-Speech Tagging (D18-1)
Copied to clipboard
| Challenge: | Low-resource languages lack manual annotated data to learn basic models such as part-of-speech (POS) taggers. |
| Approach: | They propose a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision in a uniform framework. |
| Outcome: | The proposed model scales to hundreds of low-resource languages without access to gold annotated data. |
Methods for Estimating and Improving Robustness of Language Models (2022.naacl-srw)
Copied to clipboard
| Challenge: | Large language models suffer from weak generalisation ability due to shallow textual relations over full semantic complexity of the problem. |
| Approach: | They propose to incorporate some of these measures into training objectives to enhance distributional robustness of LLMs. |
| Outcome: | The proposed models outperform human models on complex tasks and outperformed other models on deep networks. |
Prevent the Language Model from being Overconfident in Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Neural Machine Translation models are based on partial translation and a language model that predicts the next token based only on partial. |
| Approach: | They propose a Margin-based Token-level Objective and a Sentence-level Goal to maximize the Margin . they propose to model the next token based on partial translation . |
| Outcome: | The proposed approach improves translation adequacy and fluency on English-to-German, Chinese-to English and French translation tasks. |
Phrase-Based & Neural Unsupervised Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Recent advances in machine translation have reported near human-level performance on several languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences. |
| Approach: | They propose two models that leverage a careful initialization of the parameters and denoising effect of language models. |
| Outcome: | The proposed models outperform the current methods on English-French and German-English benchmarks while being simpler and having fewer hyper-parameters. |
Do Neural Language Models Overcome Reporting Bias? (2020.coling-main)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained language models can overcome reporting bias by estimating the plausibility of rare but unspoken facts. |
| Approach: | They revisit the experiments conducted by Gordon and Van Durme (2013) . they find that pre-trained language models overestimate the very rare . |
| Outcome: | The proposed approach overestimates the rare at the expense of the rare, while minimizing reporting bias. |