Search Results for author:
Found 20 papers, 14 papers with code
CM-Gen: A Neural Framework for Chinese Metaphor Generation with Explicit Context Modelling
The metaphor identification module is able to perform a self-training procedure, which discovers novel metaphors from a large-scale unlabeled corpus for NM generation.
On the Rigour of Scientific Writing: Criteria, Analysis, and Insights
Rigour is crucial for scientific research as it ensures the reproducibility and validity of results and findings.
With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models
To investigate this, we analyse the ability of VLMs and LLMs to demonstrate sound symbolism (i. e., to recognise a non-arbitrary link between sounds and concepts) as well as their ability to ``hear'' via the interplay of the language and vision modules of open and closed-source multimodal models.
Data Contamination Report from the 2024 CONDA Shared Task
The workshop fostered a shared task to collect evidence on data contamination in current available datasets and models.
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs.
Evaluating Large Language Models for Generalization and Robustness via Data Compression
We measure: 1) the compression performance on the testing period as a measure of generalization on unseen data; and 2) the performance gap between the training and testing period as a measure of robustness.
Finding Challenging Metaphors that Confuse Pretrained Language Models
In this paper, we test various NLP models on the VUA metaphor dataset and quantify to what extent metaphors affect models' performance on various downstream tasks.
LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction
LatestEval avoids data contamination by only using texts published within a recent time window, ensuring no overlap with the training corpora of pre-trained language models.
An Open Source Data Contamination Report for Large Language Models
We also introduce an open-source pipeline that enables the community to perform contamination analysis on customised data and models.
Compressing Context to Enhance Inference Efficiency of Large Language Models
This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact.
Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation
Data contamination in model evaluation is getting increasingly prevalent as the massive training corpora of large language models often unintentionally include benchmark samples.
Metaphor Detection via Explicit Basic Meanings Modelling
One noticeable trend in metaphor detection is the embrace of linguistic theories such as the metaphor identification procedure (MIP) for model architecture design.
Unlocking Context Constraints of LLMs: Enhancing Context Efficiency of LLMs with Self-Information-Based Content Filtering
Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks.
Metaphor Detection with Effective Context Denoising
We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection.
FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning
In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection.
The Secret of Metaphor on Expressing Stronger Emotion
Metaphors are proven to have stronger emotional impact than literal expressions.
Nominal Metaphor Generation with Multitask Learning
Metaphor generation is a challenging task which can impact many downstream tasks such as improving user satisfaction with dialogue systems and story generation.
Cache-Augmented Inbatch Importance Resampling for Training Recommender Retriever
Recommender retrievers aim to rapidly retrieve a fraction of items from the entire item corpus when a user query requests, with the representative two-tower model trained with the log softmax loss.
Hierarchical Region Learning for Nested Named Entity Recognition
Named Entity Recognition (NER) is deeply explored and widely used in various tasks.
GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring
We also applied GPU-FV for realtime video monitoring tasks and found that GPU-FV outperforms a number of previous works.
