paper-with-me

홈 › Papers

Are Neural Networks Extracting Linguistic Properties or Memorizing Training Data? An Observation with a Multilingual Probe for Predicting Tense

2021-04-01 · EACL 2021 2 · Bingzhi Li, Guillaume Wisniewski

We evaluate the ability of Bert embeddings to represent tense information, taking French and Chinese as a case study. In French, the tense information is expressed by verb morphology and can be captured by simple surface information. On the contrary, tense interpretation in Chinese is driven by abstract, lexical, syntactic and even pragmatic information. We show that while French tenses can easily be predicted from sentence representations, results drop sharply for Chinese, which suggests that Bert is more likely to memorize shallow patterns from the training data rather than uncover abstract properties.

📄 PDF Abstract BibTeX

Code (1)

bingzhilee/tense_representation_bert 공식 구현

Tasks

Sentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention 설명 없음
Adam 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 &…
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.
Residual Connection 설명 없음
WordPiece 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Similar Papers 제목 키워드 기반

Measuring Memorization Effect in Word-Level Neural Networks Probing

2020-06-29 · Rudolf Rosa, Tomáš Musil, David Mareček

Multiple studies have probed representations emerging in neural networks trained for end-to-end NLP tasks and examined what word-level linguistic information may be encoded in the representations. In classical probing, a…

Machine TranslationMemorizationTranslation

MemCap: Memorizing Style Knowledge for Image Captioning

2020-04-03 · AAAI 2020 4 · Wentian Zhao, Xinxiao wu, Xiaoxun Zhang

Generating stylized captions for images is a challenging task since it requires not only describing the content of the image accurately but also expressing the desired linguistic style appropriately. In this paper, we pr…

Image CaptioningLanguage ModelingLanguage ModellingSentence

GRAIN: Bridging Name and Narrative Shifts in Real-World Graph Reasoning through Invariance-Rewarded Agentic RL

2026-08-27 · Zike Yuan, Han Zhang, Jianzhi Yan, Le Liu 외 arxiv

Despite their potential in standardized graph tasks, Large Language Models (LLMs) remain brittle to real-world shifts in node identifiers and task formulation. While deterministic graph tools are invariant to such shifts…

Reinforcement LearningSemantic Parsing

What to Do Next? Memorizing skills from Egocentric Instructional Video

2025-07-01 · Jing Bi, Chenliang Xu arxiv

Learning to perform activities through demonstration requires extracting meaningful information about the environment from observations. In this research, we investigate the challenge of planning high-level goal-oriented…

Measuring global properties of neural generative model outputs via generating mathematical objects

2021-05-28 · Bernt Ivar Utstøl Nødland

We train deep generative models on datasets of reflexive polytopes. This enables us to compare how well the models have picked up on various global properties of generated samples. Our datasets are complete in the sense …