English
Related papers

Related papers: Representation biases in sentence transformers

200 papers

The combination of Transformer-based encoders with contrastive learning represents the current mainstream paradigm for sentence representation learning. This paradigm is typically based on the hidden states of the last Transformer block of…

Computation and Language · Computer Science 2025-08-26 Jianxiang Zang , Nijia Mo , Yonda Wei , Meiling Ning , Hui Liu

Syntactic parsing is the task of assigning a syntactic structure to a sentence. There are two popular syntactic parsing methods: constituency and dependency parsing. Recent works have used syntactic embeddings based on constituency trees,…

Computation and Language · Computer Science 2023-02-20 Subba Reddy Oota , Mounika Marreddy , Manish Gupta , Bapi Raju Surampud

We use the English model of BERT and explore how a deletion of one word in a sentence changes representations of other words. Our hypothesis is that removing a reducible word (e.g. an adjective) does not affect the representation of other…

Computation and Language · Computer Science 2019-06-28 Rudolf Rosa , David Mareček

Recently, much progress has been made in learning general-purpose sentence representations that can be used across domains. However, most of the existing models typically treat each word in a sentence equally. In contrast, extensive studies…

Computation and Language · Computer Science 2017-05-10 Shaonan Wang , Jiajun Zhang , Chengqing Zong

Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in…

Computation and Language · Computer Science 2021-03-19 Daniel Loureiro , Kiamehr Rezaee , Mohammad Taher Pilehvar , Jose Camacho-Collados

For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is essential to improve its performance. Traditional attentive…

Computation and Language · Computer Science 2019-11-21 Zhuosheng Zhang , Yuwei Wu , Junru Zhou , Sufeng Duan , Hai Zhao , Rui Wang

Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for different contexts, to developing algorithms to mitigate…

Computation and Language · Computer Science 2019-11-06 Yi Chern Tan , L. Elisa Celis

This paper proposes serialized output training (SOT), a novel framework for multi-speaker overlapped speech recognition based on an attention-based encoder-decoder approach. Instead of having multiple output layers as with the permutation…

Computation and Language · Computer Science 2020-08-11 Naoyuki Kanda , Yashesh Gaur , Xiaofei Wang , Zhong Meng , Takuya Yoshioka

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…

Computation and Language · Computer Science 2018-08-30 Haoyue Shi , Hao Zhou , Jiaze Chen , Lei Li

We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Zhicheng Huang , Zhaoyang Zeng , Bei Liu , Dongmei Fu , Jianlong Fu

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP…

Computation and Language · Computer Science 2021-03-09 Jiangang Bai , Yujing Wang , Yiren Chen , Yaming Yang , Jing Bai , Jing Yu , Yunhai Tong

Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe. However, such embeddings are dynamic, calculated according…

Computation and Language · Computer Science 2020-04-07 Yile Wang , Leyang Cui , Yue Zhang

Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer…

Computation and Language · Computer Science 2022-06-28 Snehal Khandve , Vedangi Wagh , Apurva Wani , Isha Joshi , Raviraj Joshi

Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient ability to capture subtle differences. Minor noise like word…

Computation and Language · Computer Science 2023-04-17 Sirui Wang , Di Liang , Jian Song , Yuntao Li , Wei Wu

Sentence embedding is a significant research topic in the field of natural language processing (NLP). Generating sentence embedding vectors reflecting the intrinsic meaning of a sentence is a key factor to achieve an enhanced performance in…

Computation and Language · Computer Science 2019-01-17 Myeongjun Jang , Pilsung Kang

Word Representations form the core component for almost all advanced Natural Language Processing (NLP) applications such as text mining, question-answering, and text summarization, etc. Over the last two decades, immense research is…

Computation and Language · Computer Science 2020-12-02 Shree Charran R , Rahul Kumar Dubey

Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning. Variants of this method have been used as regularization mechanisms to achieve SOTA results on NLP benchmarks, and…

Computation and Language · Computer Science 2021-09-30 Javid Ebrahimi , Hao Yang , Wei Zhang

Prediction head is a crucial component of Transformer language models. Despite its direct impact on prediction, this component has often been overlooked in analyzing Transformers. In this study, we investigate the inner workings of the…

Computation and Language · Computer Science 2023-05-30 Goro Kobayashi , Tatsuki Kuribayashi , Sho Yokoi , Kentaro Inui

This paper introduces a sentence to vector encoding framework suitable for advanced natural language processing. Our latent representation is shown to encode sentences with common semantic information with similar vector representations.…

Computation and Language · Computer Science 2018-09-30 Chi Zhang , Shagan Sah , Thang Nguyen , Dheeraj Peri , Alexander Loui , Carl Salvaggio , Raymond Ptucha

BERT (Bidirectional Encoder Representations from Transformers) and ALBERT (A Lite BERT) are methods for pre-training language models which can later be fine-tuned for a variety of Natural Language Understanding tasks. These methods have…

Computation and Language · Computer Science 2020-07-21 Diego de Vargas Feijo , Viviane Pereira Moreira