paper-with-me

홈 › Papers

What do you mean, BERT? Assessing BERT as a Distributional Semantics Model

2019-11-13 · Timothee Mickus, Denis Paperno, Mathieu Constant, Kees Van Deemter

Contextualized word embeddings, i.e. vector representations for words in context, are naturally seen as an extension of previous noncontextual distributional semantic models. In this work, we focus on BERT, a deep neural network that produces contextualized embeddings and has set the state-of-the-art in several semantic tasks, and study the semantic coherence of its embedding space. While showing a tendency towards coherence, BERT does not fully live up to the natural expectations for a semantic vector space. In particular, we find that the position of the sentence in which a word occurs, while having no meaning correlates, leaves a noticeable trace on the word embeddings and disturbs similarity relationships.

📄 PDF Abstract BibTeX arXiv:1911.05758

Code (0)

등록된 구현이 없습니다.

Tasks

PositionSentenceWord Embeddings

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
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 &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Don't Invite BERT to Drink a Bottle: Modeling the Interpretation of Metonymies Using BERT and Distributional Representations

2020-12-01 · COLING 2020 8 · Paolo Pedinotti, Alessandro Lenci

In this work, we carry out two experiments in order to assess the ability of BERT to capture the meaning shift associated with metonymic expressions. We test the model on a new dataset that is representative of the most …

Why is penguin more similar to polar bear than to sea gull? Analyzing conceptual knowledge in distributional models

2020-07-01 · ACL 2020 6 · Pia Sommerauer

What do powerful models of word mean- ing created from distributional data (e.g. Word2vec (Mikolov et al., 2013) BERT (Devlin et al., 2019) and ELMO (Peters et al., 2018)) represent? What causes words to be similar in th…

Distributionally Robust Finetuning BERT for Covariate Drift in Spoken Language Understanding

2022-05-01 · ACL 2022 5 · Samuel Broscheit, Quynh Do, Judith Gaspers

In this study, we investigate robustness against covariate drift in spoken language understanding (SLU). Covariate drift can occur in SLUwhen there is a drift between training and testing regarding what users request or …

Spoken Language Understanding

Vector-Valued Distributional Reinforcement Learning Policy Evaluation: A Hilbert Space Embedding Approach

2026-01-26 · Mehrdad Mohammadi, Qi Zheng, Ruoqing Zhu arxiv

We propose an (offline) multi-dimensional distributional reinforcement learning framework (KE-DRL) that leverages Hilbert space mappings to estimate the kernel mean embedding of the multi-dimensional value distribution u…

Reinforcement Learning

Assessing ASR Model Quality on Disordered Speech using BERTScore

2022-09-21 · Jimmy Tobin, Qisheng Li, Subhashini Venugopalan, Katie Seaver 외

Word Error Rate (WER) is the primary metric used to assess automatic speech recognition (ASR) model quality. It has been shown that ASR models tend to have much higher WER on speakers with speech impairments than typical…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition+1