Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
- Ben Bogin, Matt Gardner, Jonathan Berant
- Computer ScienceAnnual Meeting of the Association for…
- 15 May 2019
This paper presents an encoder-decoder semantic parser, where the structure of the DB schema is encoded with a graph neural network, and this representation is later used at both encoding and decoding time.
Global Reasoning over Database Structures for Text-to-SQL Parsing
- Ben Bogin, Matt Gardner, Jonathan Berant
- Computer ScienceConference on Empirical Methods in Natural…
- 29 August 2019
This work uses message-passing through a graph neural network to softly select a subset of database constants for the output query, conditioned on the question, and trains a model to rank queries based on the global alignment ofdatabase constants to question words.
Evaluating Models’ Local Decision Boundaries via Contrast Sets
- Matt Gardner, Yoav Artzi, Ben Zhou
- Computer ScienceFindings
- 6 April 2020
A more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data, and recommends that the dataset authors manually perturb the test instances in small but meaningful ways that (typically) change the gold label, creating contrast sets.
Towards an argumentative content search engine using weak supervision
- Ran Levy, Ben Bogin, Shai Gretz, R. Aharonov, N. Slonim
- Computer ScienceInternational Conference on Computational…
- 1 August 2018
This work uses a weak signal to define weak signals for training DNNs to obtain significantly greater performance, and adapts the system to solve a recent argument mining task of identifying argumentative sentences in Web texts retrieved from heterogeneous sources, and obtain F1 scores comparable to the supervised baseline.
Emergence of Communication in an Interactive World with Consistent Speakers
- Ben Bogin, Mor Geva, Jonathan Berant
- Computer ScienceArXiv
- 3 September 2018
A new model and training algorithm is proposed, that utilizes the structure of a learned representation space to produce more consistent speakers at the initial phases of training, which stabilizes learning and increases context-independence compared to policy gradient and other competitive baselines.
Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data
- Moshe Hazoom, Vibhor Malik, Ben Bogin
- Computer ScienceNLP4PROG
- 9 June 2021
This work releases SEDE, a dataset with 12,023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website, and shows that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset.
Evaluating NLP Models via Contrast Sets
- Matt Gardner, Yoav Artzi, Ben Zhou
- Computer ScienceArXiv
- 6 April 2020
A new annotation paradigm for NLP is proposed that helps to close systematic gaps in the test data, and it is recommended that after a dataset is constructed, the dataset authors manually perturb the test instances in small but meaningful ways that change the gold label, creating contrast sets.
Language Generation with Recurrent Generative Adversarial Networks without Pre-training
- Ofir Press, Amir Bar, Ben Bogin, Jonathan Berant, Lior Wolf
- Computer ScienceArXiv
- 5 June 2017
It is shown that recurrent neural networks can be trained to generate text with GANs from scratch by slowly teaching the model to generate sequences of increasing and variable length, which vastly improves the quality of generated sequences compared to a convolutional baseline.
Grammar-based Neural Text-to-SQL Generation
- Kevin Lin, Ben Bogin, Mark Neumann, Jonathan Berant, Matt Gardner
- Computer ScienceArXiv
- 30 May 2019
The sequence-to-sequence paradigm employed by neural text-to-SQL models typically performs token-level decoding and does not consider generating SQL hierarchically from a grammar. Grammar-based…
COVR: A Test-Bed for Visually Grounded Compositional Generalization with Real Images
- Ben Bogin, Shivanshu Gupta, Matt Gardner, Jonathan Berant
- Computer ScienceConference on Empirical Methods in Natural…
- 22 September 2021
This work proposes COVR, a new test-bed for visually-grounded compositional generalization with real images, and proposes an almost fully automatic procedure for generating question-answer pairs along with a set of context images.
...
...