Skip to search formSkip to main contentSkip to account menu

BERTScore: Evaluating Text Generation with BERT

TLDR
This work proposes BERTScore, an automatic evaluation metric for text generation that correlates better with human judgments and provides stronger model selection performance than existing metrics.
View PDF on arXiv (opens in a new tab)

Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies

TLDR
The NEWSROOM dataset is presented, a summarization dataset of 1.3 million articles and summaries written by authors and editors in newsrooms of 38 major news publications between 1998 and 2017, and the summaries combine abstractive and extractive strategies.
View on ACL (opens in a new tab)

A Corpus for Reasoning about Natural Language Grounded in Photographs

TLDR
This work introduces a new dataset for joint reasoning about natural language and images, with a focus on semantic diversity, compositionality, and visual reasoning challenges, and Evaluation using state-of-the-art visual reasoning methods shows the data presents a strong challenge.
View on ACL (opens in a new tab)

Learning to Automatically Solve Algebra Word Problems

TLDR
An approach for automatically learning to solve algebra word problems by reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers to the problem text.
View on ACL (opens in a new tab)

TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

TLDR
This work introduces the Touchdown task and dataset, where an agent must first follow navigation instructions in a Street View environment to a goal position, and then guess a location in its observed environment described in natural language to find a hidden object.
View on IEEE (opens in a new tab)

Training RNNs as Fast as CNNs

TLDR
The Simple Recurrent Unit architecture is proposed, a recurrent unit that simplifies the computation and exposes more parallelism, and is as fast as a convolutional layer and 5-10x faster than an optimized LSTM implementation.

Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions

TLDR
This paper shows semantic parsing can be used within a grounded CCG semantic parsing approach that learns a joint model of meaning and context for interpreting and executing natural language instructions, using various types of weak supervision.
View on ACL (opens in a new tab)

Scaling Semantic Parsers with On-the-Fly Ontology Matching

TLDR
A new semantic parsing approach that learns to resolve ontological mismatches, which is learned from question-answer pairs, uses a probabilistic CCG to build linguistically motivated logicalform meaning representations, and includes an ontology matching model that adapts the output logical forms for each target ontology.
View on ACL (opens in a new tab)

Simple Recurrent Units for Highly Parallelizable Recurrence

TLDR
The Simple Recurrent Unit is proposed, a light recurrent unit that balances model capacity and scalability, designed to provide expressive recurrence, enable highly parallelized implementation, and comes with careful initialization to facilitate training of deep models.
View on ACL (opens in a new tab)

Revisiting Few-sample BERT Fine-tuning

TLDR
It is found that parts of the BERT network provide a detrimental starting point for fine-tuning, and simply re-initializing these layers speeds up learning and improves performance.
View PDF on arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)