Revisiting Representation Degeneration Problem in Language Modeling (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Language modeling is a fundamental task in natural language processing, applications include machine translation, image captioning and speech recognition. |
| Approach: | They propose a cosine regularization method to solve the representation degeneration problem by analyzing the limitations of the proposed method and then propose an alternative regularization technique to tackle the problem. |
| Outcome: | The proposed method is effective in language modeling and image captioning. |
Similar Papers
Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have determined that the learned token embeddings of large-scale neural language models are degenerated to be anisotropic with a narrow-cone shape. |
| Approach: | They propose a method to degenerate the learning gradient for rare token embeddings by gating the specific part of the gradient for all tokens during training stage. |
| Outcome: | The proposed method improves the performance of the models but lacks the training dynamics needed to solve the representation degeneration problem. |
Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to multilingual neural machine translation (MNMT) are limited in their ability to handle large amounts of data. |
| Approach: | They propose a framework which only requires target-side monolingual data and a bilingual dictionary to improve the performance of the MNMT model. |
| Outcome: | The proposed framework is more effective than baselines in long-tail and high-resource languages. |
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. |
Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing studies have shown that word embeddings do not occupy a narrow cone, but rather drift in common directions. |
| Approach: | They show that anisotropy can be restored using a simple transformation of word embeddings. |
| Outcome: | The proposed model can restore anisotropy using a simple transformation. |
Typology Guided Multilingual Position Representations: Case on Dependency Parsing (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent multilingual models benefit from strong unified semantic representation models, but conflicting linguistic regularities may break the effectiveness of word position features in multilingual learning. |
| Approach: | They propose to combine prior knowledge from typology features and existing position vectors to create a position generation network which combines prior knowledge of a language's position space and typological characterization. |
| Outcome: | The proposed model can achieve the best multilingual parsing results by combining prior knowledge from typology features and existing position vectors. |
Unsupervised Cross-Lingual Representation Learning (P19-4)
Copied to clipboard
| Challenge: | a comprehensive survey of cutting-edge weakly-supervised and unsupervised cross-lingual word representations is presented . |
| Approach: | This tutorial provides a comprehensive survey of recent work on weakly-supervised and unsupervised cross-lingual word representations. |
| Outcome: | This tutorial provides a comprehensive survey of cutting-edge weakly-supervised and unsupervised word representations. |
From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings (2025.coling-main)
Copied to clipboard
| Challenge: | Existing work in this field has looked most commonly into gender bias, racial bias, and religious bias. |
| Approach: | They propose an algorithm that uses a neural network to perform ‘soft debiasing’ and build on the seminal work of (CITATION) and (CitATION). |
| Outcome: | The proposed algorithm outperforms current methods on gender, race, and religion metrics on a wide range of metrics. |
Weight Tying Biases Token Embeddings Towards the Output Space (2026.findings-acl)
Copied to clipboard
| Challenge: | Weight tying is a common practice in language model design, but its impact on learning embedding space remains unclear. |
| Approach: | They show that weight tying optimizes the embedding matrix for output prediction . they also show that tied embeddable matrices align more closely with output embedders . |
| Outcome: | The proposed weight tying approach harms performance at scale and has implications for training smaller LLMs. |
Analyzing the Limitations of Cross-lingual Word Embedding Mappings (P19-1)
Copied to clipboard
| Challenge: | Existing methods for cross-lingual word embeddings have limited results . existing methods require little or no cross-linguistic signal to work . |
| Approach: | They compare offline mapping methods to an extension of skip-gram that jointly learns both embedding spaces. |
| Outcome: | The proposed method yields more isomorphic embeddings, is less sensitive to hubness, and achieves stronger results in bilingual lexicon induction. |
A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation (P19-1)
Copied to clipboard
| Challenge: | Recent neural language generation systems often hallucinate contents when trained on loosely corresponding pairs of the input structure and text. |
| Approach: | They propose to integrate a language understanding module for data refinement with self-training iterations to induce strong equivalence between the input data and the paired text. |
| Outcome: | Experiments on the E2E challenge dataset show that the proposed framework reduces relative unaligned noise by 50% compared with the current state-of-the-art ensemble generator. |