paper-with-me

Papers

A Surprisingly Robust Trick for Winograd Schema Challenge

2019-05-15 · Vid Kocijan, Ana-Maria Cretu, Oana-Maria Camburu, Yordan Yordanov, Thomas Lukasiewicz

The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance of three language models on WSC273 strongly improves when fine-tuned on a similar pronoun disambiguation problem dataset (denoted WSCR). We additionally generate a large unsupervised WSC-like dataset. By fine-tuning the BERT language model both on the introduced and on the WSCR dataset, we achieve overall accuracies of 72.5% and 74.7% on WSC273 and WNLI, improving the previous state-of-the-art solutions by 8.8% and 9.6%, respectively. Furthermore, our fine-tuned models are also consistently more robust on the "complex" subsets of WSC273, introduced by Trichelair et al. (2018).

📄 PDF Abstract BibTeX arXiv:1905.06290

Code (2)

vid-koci/bert-commonsense 공식 구현 pytorch
TangJiaLong/Knowledge-Projection-for-ERE pytorch

Tasks

Common Sense ReasoningCoreference ResolutionLanguage ModelingLanguage ModellingNatural Language InferenceNatural Language UnderstandingWNLI

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

A Surprisingly Robust Trick for the Winograd Schema Challenge

2019-07-01 · ACL 2019 7 · Vid Kocijan, Ana-Maria Cretu, Oana-Maria Camburu, Yordan Yordanov 외

The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance of th…

Language ModelingLanguage ModellingNatural Language UnderstandingWNLI

A Google-Proof Collection of French Winograd Schemas

2017-04-01 · WS 2017 4 · Pascal Amsili, Olga Seminck

This article presents the first collection of French Winograd Schemas. Winograd Schemas form anaphora resolution problems that can only be resolved with extensive world knowledge. For this reason the Winograd Schema Chal…

Coreference ResolutionWorld Knowledge

A Review of Winograd Schema Challenge Datasets and Approaches

2020-04-23 · Vid Kocijan, Thomas Lukasiewicz, Ernest Davis, Gary Marcus 외

The Winograd Schema Challenge is both a commonsense reasoning and natural language understanding challenge, introduced as an alternative to the Turing test. A Winograd schema is a pair of sentences differing in one or tw…

Natural Language Understanding

Winograd Schema - Knowledge Extraction Using Narrative Chains

2018-01-08 · Vatsal Mahajan

The Winograd Schema Challenge (WSC) is a test of machine intelligence, designed to be an improvement on the Turing test. A Winograd Schema consists of a sentence and a corresponding question. To successfully answer these…

Common Sense ReasoningSentence

Experience and Prediction: A Metric of Hardness for a Novel Litmus Test

2023-09-05 · Nicos Isaak, Loizos Michael

In the last decade, the Winograd Schema Challenge (WSC) has become a central aspect of the research community as a novel litmus test. Consequently, the WSC has spurred research interest because it can be seen as the mean…