paper-with-me

Papers STS-B

“STS-B” 태그가 달린 논문 17편 · 필터 해제

Parameter-Efficient Transformer Embeddings

2025-05-04 · Henry Ndubuaku, Mouad Talhi

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+1

Exploring Activation Patterns of Parameters in Language Models

2024-05-28 · Yudong Wang, Damai Dai, Zhifang Sui

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-B

Span-Aggregatable, Contextualized Word Embeddings for Effective Phrase Mining

2024-05-12 · Eyal Orbach, Lev Haikin, Nelly David, Avi Faizakof

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+3

Rematch: Robust and Efficient Matching of Local Knowledge Graphs to Improve Structural and Semantic Similarity

2024-04-02 · Findings of the Association for Computational Linguistics: NAACL 2024 6 · Zoher Kachwala, Jisun An, Haewoon Kwak, Filippo Menczer

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+5

Empirical Analysis of Efficient Fine-Tuning Methods for Large Pre-Trained Language Models

2024-01-08 · Nigel Doering, Cyril Gorlla, Trevor Tuttle, Adhvaith Vijay

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-B

Unsupervised hard Negative Augmentation for contrastive learning

2024-01-05 · Yuxuan Shu, Vasileios Lampos

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+3

Semantic similarity prediction is better than other semantic similarity measures

2023-09-22 · Steffen Herbold

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-B

An Automatic and Efficient BERT Pruning for Edge AI Systems

2022-06-21 · Shaoyi Huang, Ning Liu, Yueying Liang, Hongwu Peng 외

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+3

RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression

2022-05-30 · Yu Gong, Greg Mori, Frederick Tung

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+1

Extracting Latent Steering Vectors from Pretrained Language Models

2022-05-10 · Findings (ACL) 2022 5 · Nishant Subramani, Nivedita Suresh, Matthew E. Peters

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+3

EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English

2022-03-28 · Findings (ACL) 2022 5 · Weicheng Ma, Samiha Datta, Lili Wang, Soroush Vosoughi

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+4

Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity

2021-11-01 · EMNLP 2021 11 · Po-Nien Kung, Sheng-Siang Yin, Yi-Cheng Chen, Tse-Hsuan Yang 외

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+2

Noisy Text Data: Achilles’ Heel of BERT

2020-11-01 · EMNLP (WNUT) 2020 11 · Ankit Kumar, Piyush Makhija, Anuj Gupta

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

Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning

2020-10-16 · EMNLP 2020 11 · Wanyun Cui, Guangyu Zheng, Wei Wang

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+1

Evaluating the Effectiveness of Efficient Neural Architecture Search for Sentence-Pair Tasks

2020-10-08 · EMNLP (insights) 2020 11 · Ansel MacLaughlin, Jwala Dhamala, Anoop Kumar, Sriram Venkatapathy 외

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+7

Why Not Simply Translate? A First Swedish Evaluation Benchmark for Semantic Similarity

2020-09-07 · Tim Isbister, Magnus Sahlgren

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+2

Noisy Text Data: Achilles' Heel of BERT

2020-03-29 · Ankit Kumar, Piyush Makhija, Anuj Gupta

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
1–17 / 17