Semantic Parsing with Less Prior and More Monolingual Data

• URL: http://arxiv.org/abs/2101.00259v1
• Date: Fri, 1 Jan 2021 16:02:38 GMT
• Title: Semantic Parsing with Less Prior and More Monolingual Data
• Authors: Sajad Norouzi, Yanshuai Cao
• Abstract summary: This work investigates whether a generic transformer-based seq2seq model can achieve competitive performance with minimal semantic-parsing specific inductive bias design. By exploiting a relatively large monolingual corpus of the target programming language, which is cheap to mine from the web, unlike a parallel corpus, we achieved 80.75% exact match accuracy on Django and 32.57 BLEU score on CoNaLa, both are SOTA to the best of our knowledge.
• Score: 12.715221084359085
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Semantic parsing is the task of converting natural language utterances to machine-understandable meaning representations, such as logic forms or programming languages. Training datasets for semantic parsing are typically small due to the higher expertise required for annotation than most other NLP tasks. As a result, models for this application usually require additional prior knowledge to be built into the architecture or algorithm. The increased dependency on human experts hinders automation and raises the development and maintenance costs in practice. This work investigates whether a generic transformer-based seq2seq model can achieve competitive performance with minimal semantic-parsing specific inductive bias design. By exploiting a relatively large monolingual corpus of the target programming language, which is cheap to mine from the web, unlike a parallel corpus, we achieved 80.75% exact match accuracy on Django and 32.57 BLEU score on CoNaLa, both are SOTA to the best of our knowledge. This positive evidence highlights a potentially easier path toward building accurate semantic parsers in the wild.

Related papers

• How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases [28.58785395946639]
  We show that pre-training can teach language models to rely on hierarchical syntactic features when performing tasks after fine-tuning. We focus on architectural features (depth, width, and number of parameters), as well as the genre and size of the pre-training corpus.
  arXiv  Detail & Related papers  (2023-05-31T14:38:14Z)
• On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex [48.588772371355816]
  This paper presents the first empirical study on the adversarial robustness of a large prompt-based language model of code, codex. Our results demonstrate that the state-of-the-art (SOTA) code-language models are vulnerable to carefully crafted adversarial examples.
  arXiv  Detail & Related papers  (2023-01-30T13:21:00Z)
• Training Naturalized Semantic Parsers with Very Little Data [10.709587018625275]
  State-of-the-art (SOTA) semantics are seq2seq architectures based on large language models that have been pretrained on vast amounts of text. Recent work has explored a reformulation of semantic parsing whereby the output sequences are themselves natural language sentences. We show that this method delivers new SOTA few-shot performance on the Overnight dataset.
  arXiv  Detail & Related papers  (2022-04-29T17:14:54Z)
• Neural Abstructions: Abstractions that Support Construction for Grounded Language Learning [69.1137074774244]
  Leveraging language interactions effectively requires addressing limitations in the two most common approaches to language grounding. We introduce the idea of neural abstructions: a set of constraints on the inference procedure of a label-conditioned generative model. We show that with this method a user population is able to build a semantic modification for an open-ended house task in Minecraft.
  arXiv  Detail & Related papers  (2021-07-20T07:01:15Z)
• Pre-training Universal Language Representation [46.51685959045527]
  This work introduces universal language representation learning, i.e., embeddings of different levels of linguistic units or text with quite diverse lengths in a uniform vector space. We empirically verify that well designed pre-training scheme may effectively yield universal language representation.
  arXiv  Detail & Related papers  (2021-05-30T09:29:01Z)
• Constrained Language Models Yield Few-Shot Semantic Parsers [73.50960967598654]
  We explore the use of large pretrained language models as few-shot semantics. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. We use language models to paraphrase inputs into a controlled sublanguage resembling English that can be automatically mapped to a target meaning representation.
  arXiv  Detail & Related papers  (2021-04-18T08:13:06Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)
• Is Supervised Syntactic Parsing Beneficial for Language Understanding? An Empirical Investigation [71.70562795158625]
  Traditional NLP has long held (supervised) syntactic parsing necessary for successful higher-level semantic language understanding (LU) Recent advent of end-to-end neural models, self-supervised via language modeling (LM), and their success on a wide range of LU tasks, questions this belief. We empirically investigate the usefulness of supervised parsing for semantic LU in the context of LM-pretrained transformer networks.
  arXiv  Detail & Related papers  (2020-08-15T21:03:36Z)
• Information-Theoretic Probing for Linguistic Structure [74.04862204427944]
  We propose an information-theoretic operationalization of probing as estimating mutual information. We evaluate on a set of ten typologically diverse languages often underrepresented in NLP research.
  arXiv  Detail & Related papers  (2020-04-07T01:06:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.