Papers with TLM
Boost Transformer-based Language Models with GPU-Friendly Sparsity and Quantization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that transformer-based language models can achieve state-of-the-art performance on various natural language processing tasks. |
| Approach: | They propose a GPU-friendly 2:4 fine-grained structured sparsity and quantization scheme to maximize the GPU's acceleration constraints. |
| Outcome: | The proposed scheme achieves state-of-the-art compression on TLM model of various encoder and decoder blocks with negligible accuracy degradation on SQuAD, GLUE, CNN-DM & XSum and WikiText benchmarking tasks. |
Language-agnostic BERT Sentence Embedding (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning bilingual sentence embeddings are not well explored. |
| Approach: | They propose to combine best methods for learning multilingual sentence embeddings with pre-trained models to achieve 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba. |
| Outcome: | The proposed model achieves 83.7% bi-text retrieval accuracy over 112 languages on Tatoeba, above the 65.5% achieved by LASER. |
Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing word alignment models capture few interactions between input sentence pairs, which severely degrades the word alignment quality. |
| Approach: | They propose to model deep interactions between input and target sentences using a two-stage training framework to train the model. |
| Outcome: | The proposed model achieves the state-of-the-art (SOTA) performance on four out of five language pairs. |
Automatic Machine Translation Evaluation using Source Language Inputs and Cross-lingual Language Model (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for machine translation evaluation use source sentences as pseudo references instead of word symbols. |
| Approach: | They propose an automatic machine translation evaluation method that uses source sentences as pseudo references instead of source sentences. |
| Outcome: | The proposed method achieves higher correlation with human judgments than baseline evaluation method that uses only hypothesis and reference sentences. |
Intermediate Self-supervised Learning for Machine Translation Quality Estimation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for machine translation quality estimation (QE) rely on annotated data. |
| Approach: | They propose a self-supervised learning task for machine translation (MT) that orients a pre-trained model towards the target task. |
| Outcome: | The proposed method outperforms existing methods on English-to-German and English- to-Russian translation directions and is comparable to existing models. |
Disentangling Transformer Language Models as Superposed Topic Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Topic Modelling is an established area of research where the quality of a given topic is measured using coherence metrics. |
| Approach: | They propose a weight-based approach to search and disentangle decoder-only TLM by a Wikipedia corpus. |
| Outcome: | The proposed approach can be applied to GPT-2 models and LLaMA models. |
TLM: Token-Level Masking for Transformers (2023.emnlp-main)
Copied to clipboard
| Challenge: | Structured dropout approaches have been investigated to regularize the multi-head attention mechanism in Transformers. |
| Approach: | They propose a new regularization scheme based on token-level rather than structure-level to reduce overfitting by manipulating the connections between tokens in the multi-head attention via masking. |
| Outcome: | The proposed regularization scheme outperforms attention dropout and DropHead on 18 datasets and can establish a new record on the data-to-text benchmark Rotowire (18.93 BLEU). |
Sub-Table Rescorer for Table Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Tabular language models truncate the sequence of a long table due to their input token limits. |
| Approach: | They propose a sub-table rescorer to improve the performance of an inner table retriever-based inference. |
| Outcome: | The proposed sub-table rescorer improves the performance of an ITR-based inference. |