Papers STS-B
“STS-B” 태그가 달린 논문 17편 · 필터 해제
Parameter-Efficient Transformer Embeddings
Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternati…
Natural Language InferenceSentenceSentence-EmbeddingSTS+1Exploring Activation Patterns of Parameters in Language Models
Most work treats large language models as black boxes without in-depth understanding of their internal working mechanism. In order to explain the internal representations of LLMs, we propose a gradient-based metric to as…
STSSTS-BSpan-Aggregatable, Contextualized Word Embeddings for Effective Phrase Mining
Dense vector representations for sentences made significant progress in recent years as can be seen on sentence similarity tasks. Real-world phrase retrieval applications, on the other hand, still encounter challenges fo…
RetrievalSentenceSentence EmbeddingsSentence Similarity+3Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity
Knowledge graphs play a pivotal role in various applications, such as question-answering and fact-checking. Abstract Meaning Representation (AMR) represents text as knowledge graphs. Evaluating the quality of these graph…
Abstract Meaning RepresentationFact CheckingGraph MatchingKnowledge Graphs+5Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models
Fine-tuning large pre-trained language models for downstream tasks remains a critical challenge in natural language processing. This paper presents an empirical analysis comparing two efficient fine-tuning methods - BitF…
CoLAMRPCSTSSTS-BUnsupervised hard Negative Augmentation for contrastive learning
We present Unsupervised hard Negative Augmentation (UNA), a method that generates synthetic negative instances based on the term frequency-inverse document frequency (TF-IDF) retrieval model. UNA uses TF-IDF scores to as…
Contrastive LearningData AugmentationRetrievalSemantic Textual Similarity+3Semantic similarity prediction is better than other semantic similarity measures
Semantic similarity between natural language texts is typically measured either by looking at the overlap between subsequences (e.g., BLEU) or by using embeddings (e.g., BERTScore, S-BERT). Within this paper, we argue th…
Semantic SimilaritySemantic Textual SimilaritySTSSTS-BAn Automatic and Efficient BERT Pruning for Edge AI Systems
With the yearning for deep learning democratization, there are increasing demands to implement Transformer-based natural language processing (NLP) models on resource-constrained devices for low-latency and high accuracy.…
CPUModel CompressionMRPCQNLI+3RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression
Data imbalance, in which a plurality of the data samples come from a small proportion of labels, poses a challenge in training deep neural networks. Unlike classification, in regression the labels are continuous, potenti…
Deep imbalanced regressionInductive BiasregressionSTS+1Extracting Latent Steering Vectors from Pretrained Language Models
Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the info…
Language ModelingLanguage ModellingSentenceSentence Similarity+3EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English
While cultural backgrounds have been shown to affect linguistic expressions, existing natural language processing (NLP) research on culture modeling is overly coarse-grained and does not examine cultural differences amon…
Cultural Vocal Bursts Intensity PredictionLanguage ModelingLanguage ModellingQNLI+4Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity
Multi-task auxiliary learning utilizes a set of relevant auxiliary tasks to improve the performance of a primary task. A common usage is to manually select multiple auxiliary tasks for multi-task learning on all data, wh…
Auxiliary LearningMRPCMulti-Task LearningRTE+2Noisy Text Data: Achilles’ Heel of BERT
Owing to the phenomenal success of BERT on various NLP tasks and benchmark datasets, industry practitioners are actively experimenting with fine-tuning BERT to build NLP applications for solving industry use cases. For m…
Sentiment AnalysisSST-2STSSTS-BUnsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning
We propose to solve the natural language inference problem without any supervision from the inference labels via task-agnostic multimodal pretraining. Although recent studies of multimodal self-supervised learning also r…
Contrastive LearningNatural Language InferenceSelf-Supervised LearningSTS+1Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks
Neural Architecture Search (NAS) methods, which automatically learn entire neural model or individual neural cell architectures, have recently achieved competitive or state-of-the-art (SOTA) performance on variety of nat…
image-classificationImage ClassificationLanguage ModelingLanguage Modelling+7Why Not Simply Translate? A First Swedish Evaluation Benchmark for Semantic Similarity
This paper presents the first Swedish evaluation benchmark for textual semantic similarity. The benchmark is compiled by simply running the English STS-B dataset through the Google machine translation API. This paper dis…
Machine TranslationSemantic SimilaritySemantic Textual SimilaritySTS+2Noisy Text Data: Achilles' Heel of BERT
Owing to the phenomenal success of BERT on various NLP tasks and benchmark datasets, industry practitioners are actively experimenting with fine-tuning BERT to build NLP applications for solving industry use cases. For m…
Sentiment AnalysisSST-2STSSTS-B