The impact of lexical and grammatical processing on generating code from natural language

02/28/2022
by   Nathanaël Beau, et al.
0

Considering the seq2seq architecture of TranX for natural language to code translation, we identify four key components of importance: grammatical constraints, lexical preprocessing, input representations, and copy mechanisms. To study the impact of these components, we use a state-of-the-art architecture that relies on BERT encoder and a grammar-based decoder for which a formalization is provided. The paper highlights the importance of the lexical substitution component in the current natural language to code systems.

READ FULL TEXT
research
11/10/2019

Semantic Noise Matters for Neural Natural Language Generation

Neural natural language generation (NNLG) systems are known for their pa...
research
12/31/2021

How do lexical semantics affect translation? An empirical study

Neural machine translation (NMT) systems aim to map text from one langua...
research
10/19/2019

MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity

We present a new logic-based inference engine for natural language infer...
research
04/19/2021

Natural Language Generation Using Link Grammar for General Conversational Intelligence

Many current artificial general intelligence (AGI) and natural language ...
research
09/26/2017

Lexical Disambiguation in Natural Language Questions (NLQs)

Question processing is a fundamental step in a question answering (QA) a...
research
09/12/2016

Modelling Creativity: Identifying Key Components through a Corpus-Based Approach

Creativity is a complex, multi-faceted concept encompassing a variety of...
research
04/24/2018

A Visual Distance for WordNet

Measuring the distance between concepts is an important field of study o...

Please sign up or login with your details

Forgot password? Click here to reset