Papers with token-level embeddings
KeywordScape: Visual Document Exploration using Contextualized Keyword Embeddings (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Existing tools for document visualization assume that keywords have static meanings, but contextualized word embeddings are unrealistic. |
| Approach: | They propose a visual exploration tool that visualizes contextualized word embeddings in documents based on keywords. |
| Outcome: | The proposed tool visualizes keywords in terms of their contextualized embeddings in a semantic landscape that keeps keywords with similar context close to each other, allowing for a more precise search and comparison of documents. |
Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Quantitative investing relies on extracting quantitative features or signals from various data sources including market prices, economic indicators, financial text, etc. |
| Approach: | They propose to integrate LLMs’ token-level embeddings into a forecasting module and compare their results to those of encoder-only and decoder-based models. |
| Outcome: | The proposed model outperforms conventional sentiment scores on multiple investment universes and is based on encoder-only and decoder-based models. |
Sequence Repetition Enhances Token Embeddings and Improves Sequence Labeling with Decoder-only Language Models (2026.findings-eacl)
Copied to clipboard
| Challenge: | Modern language models (LMs) are trained in autoregressive manner, conditioned on the prefix. sequence labeling (SL) tasks assign labels to each individual input token, naturally benefiting from bidirectional context. |
| Approach: | They explore sequence repetition (SR) as a less invasive alternative to decoder-only models . they show that increasing the number of repetitions does not degrade SL performance . |
| Outcome: | The proposed technique improves the quality of token-level embeddings and surpasses encoders and unmasked decoders. |
Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for creating metaembeddings from static word embeddings have been proposed, but they are not tied to a particular downstream task. |
| Approach: | They propose a sentence-level meta-embedding learning method that takes contextualised word embedding models and learns a phrase embeddable that preserves complementary strengths of the input source NLMs. |
| Outcome: | The proposed method outperforms existing methods on semantic textual similarity benchmarks on a supervised baseline and on token-level embeddings. |
Detecting Contact-Induced Semantic Shifts: What Can Embedding-Based Methods Do in Practice? (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on semantic change detection methods has focused on generic research questions and datasets, using them as a training ground for proof-of-concept studies. |
| Approach: | They propose to use type-level embeddings to detect new semantic shifts and token-level embeddeds to isolate regionally specific occurrences. |
| Outcome: | The proposed method is comparable to state-of-the-art on diachrony tasks, but it does not translate to practical value in detecting new semantic shifts. |