paper-with-me

Papers

Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings

2023-05-18 · Qian Chen, Wen Wang, Qinglin Zhang, Siqi Zheng, Chong Deng, Hai Yu, Jiaqing Liu, Yukun Ma, Chong Zhang

Prior studies diagnose the anisotropy problem in sentence representations from pre-trained language models, e.g., BERT, without fine-tuning. Our analysis reveals that the sentence embeddings from BERT suffer from a bias towards uninformative words, limiting the performance in semantic textual similarity (STS) tasks. To address this bias, we propose a simple and efficient unsupervised approach, Diagonal Attention Pooling (Ditto), which weights words with model-based importance estimations and computes the weighted average of word representations from pre-trained models as sentence embeddings. Ditto can be easily applied to any pre-trained language model as a postprocessing operation. Compared to prior sentence embedding approaches, Ditto does not add parameters nor requires any learning. Empirical evaluations demonstrate that our proposed Ditto can alleviate the anisotropy problem and improve various pre-trained models on STS tasks.

📄 PDF Abstract BibTeX arXiv:2305.10786

Code (1)

alibaba-damo-academy/spokennlp 공식 구현 tf

Tasks

Language ModelingLanguage ModellingSemantic Textual SimilaritySentenceSentence EmbeddingSentence-EmbeddingSentence EmbeddingsSTS

Methods 이 논문이 사용한 방법론

Attention Pooling 설명 없음
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Adam 설명 없음
Residual Connection 설명 없음
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

Deep Entity Matching with Pre-Trained Language Models

2020-04-01 · Yuliang Li, Jinfeng Li, Yoshihiko Suhara, AnHai Doan 외

We present Ditto, a novel entity matching system based on pre-trained Transformer-based language models. We fine-tune and cast EM as a sequence-pair classification problem to leverage such models with a simple architectu…

Data AugmentationEntity Resolution

Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation

2022-06-06 · Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai 외

While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decod…

SentenceText GenerationText Summarization

Ditto: Fair and Robust Federated Learning Through Personalization

2020-12-08 · Tian Li, Shengyuan Hu, Ahmad Beirami, Virginia Smith

Fairness and robustness are two important concerns for federated learning systems. In this work, we identify that robustness to data and model poisoning attacks and fairness, measured as the uniformity of performance acr…

FairnessFederated LearningModel PoisoningMulti-Task Learning+1

Linear Cross-Lingual Mapping of Sentence Embeddings

2023-05-23 · Oleg Vasilyev, Fumika Isono, John Bohannon

Semantics of a sentence is defined with much less ambiguity than semantics of a single word, and we assume that it should be better preserved by translation to another language. If multilingual sentence embeddings intend…

SentenceSentence EmbeddingsTranslation

IRL Dittos: Embodied Multimodal AI Agent Interactions in Open Spaces

2025-04-30 · Seonghee Lee, Denae Ford, John Tang, Sasa Junuzovic 외

We introduce the In Real Life (IRL) Ditto, an AI-driven embodied agent designed to represent remote colleagues in shared office spaces, creating opportunities for real-time exchanges even in their absence. IRL Ditto offe…

AI Agent