BERTScore: Evaluating Text Generation with BERT
- Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, Yoav Artzi
- Computer ScienceInternational Conference on Learning…
- 21 April 2019
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.
Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies
- Max Grusky, Mor Naaman, Yoav Artzi
- Computer ScienceNorth American Chapter of the Association for…
- 30 April 2018
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.
A Corpus for Reasoning about Natural Language Grounded in Photographs
- Alane Suhr, Stephanie Zhou, Iris Zhang, Huajun Bai, Yoav Artzi
- Computer ScienceAnnual Meeting of the Association for…
- 1 November 2018
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.
Learning to Automatically Solve Algebra Word Problems
- Nate Kushman, Luke Zettlemoyer, R. Barzilay, Yoav Artzi
- Computer ScienceAnnual Meeting of the Association for…
- 1 June 2014
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.
TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
- Howard Chen, Alane Suhr, Dipendra Kumar Misra, Noah Snavely, Yoav Artzi
- Computer ScienceComputer Vision and Pattern Recognition
- 29 November 2018
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.
Simple Recurrent Units for Highly Parallelizable Recurrence
- Tao Lei, Yu Zhang, Sida I. Wang, Huijing Dai, Yoav Artzi
- Computer ScienceConference on Empirical Methods in Natural…
- 8 September 2017
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.
Training RNNs as Fast as CNNs
- Tao Lei, Yu Zhang, Yoav Artzi
- Computer ScienceConference on Empirical Methods in Natural…
- 8 September 2017
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
- Yoav Artzi, Luke Zettlemoyer
- Computer ScienceInternational Conference on Topology, Algebra and…
- 31 March 2013
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.
Scaling Semantic Parsers with On-the-Fly Ontology Matching
- T. Kwiatkowski, Eunsol Choi, Yoav Artzi, Luke Zettlemoyer
- Computer ScienceConference on Empirical Methods in Natural…
- 1 October 2013
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.
Revisiting Few-sample BERT Fine-tuning
- Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Q. Weinberger, Yoav Artzi
- BusinessInternational Conference on Learning…
- 10 June 2020
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.
...
...