paper-with-me

홈 › Papers

LSTMs Exploit Linguistic Attributes of Data

2018-05-29 · WS 2018 7 · Nelson F. Liu, Omer Levy, Roy Schwartz, Chenhao Tan, Noah A. Smith

While recurrent neural networks have found success in a variety of natural language processing applications, they are general models of sequential data. We investigate how the properties of natural language data affect an LSTM's ability to learn a nonlinguistic task: recalling elements from its input. We find that models trained on natural language data are able to recall tokens from much longer sequences than models trained on non-language sequential data. Furthermore, we show that the LSTM learns to solve the memorization task by explicitly using a subset of its neurons to count timesteps in the input. We hypothesize that the patterns and structure in natural language data enable LSTMs to learn by providing approximate ways of reducing loss, but understanding the effect of different training data on the learnability of LSTMs remains an open question.

📄 PDF Abstract BibTeX arXiv:1805.11653

Code (0)

등록된 구현이 없습니다.

Tasks

MemorizationOpen-Ended Question Answering

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Do LSTMs See Gender? Probing the Ability of LSTMs to Learn Abstract Syntactic Rules

2022-10-31 · Priyanka Sukumaran, Conor Houghton, Nina Kazanina

LSTMs trained on next-word prediction can accurately perform linguistic tasks that require tracking long-distance syntactic dependencies. Notably, model accuracy approaches human performance on number agreement tasks (Gu…

Articles

Video Captioning with Multi-Faceted Attention

2016-12-01 · TACL 2018 1 · Xiang Long, Chuang Gan, Gerard de Melo

Recently, video captioning has been attracting an increasing amount of interest, due to its potential for improving accessibility and information retrieval. While existing methods rely on different kinds of visual featur…

Information RetrievalRetrievalSentenceVideo Captioning

CLiMP: A Benchmark for Chinese Language Model Evaluation

2021-01-26 · EACL 2021 2 · Beilei Xiang, Changbing Yang, Yu Li, Alex Warstadt 외

Linguistically informed analyses of language models (LMs) contribute to the understanding and improvement of these models. Here, we introduce the corpus of Chinese linguistic minimal pairs (CLiMP), which can be used to i…

Language Model EvaluationLanguage ModelingLanguage Modellingmodel

From Visual Attributes to Adjectives through Decompositional Distributional Semantics

2015-01-12 · TACL 2015 1 · Angeliki Lazaridou, Georgiana Dinu, Adam Liska, Marco Baroni

As automated image analysis progresses, there is increasing interest in richer linguistic annotation of pictures, with attributes of objects (e.g., furry, brown...) attracting most attention. By building on the recent "z…

AttributeObjectObject RecognitionRetrieval+2

Accurate 3D Body Shape Regression using Metric and Semantic Attributes

2022-06-14 · CVPR 2022 1 · Vasileios Choutas, Lea Muller, Chun-Hao P. Huang, Siyu Tang 외

While methods that regress 3D human meshes from images have progressed rapidly, the estimated body shapes often do not capture the true human shape. This is problematic since, for many applications, accurate body shape i…

3D Human Reconstruction3D Human Shape Estimation