Distinguishing Antonyms and Synonyms in a Pattern-based Neural Network
Add this Pith Number to your LaTeX paper
What is a Pith Number?\usepackage{pith}
\pithnumber{T4GW4V5L}
Prints a linked pith:T4GW4V5L badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more
read the original abstract
Distinguishing between antonyms and synonyms is a key task to achieve high performance in NLP systems. While they are notoriously difficult to distinguish by distributional co-occurrence models, pattern-based methods have proven effective to differentiate between the relations. In this paper, we present a novel neural network model AntSynNET that exploits lexico-syntactic patterns from syntactic parse trees. In addition to the lexical and syntactic information, we successfully integrate the distance between the related words along the syntactic path as a new pattern feature. The results from classification experiments show that AntSynNET improves the performance over prior pattern-based methods.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Soft Head Selection for Injecting ICL-Derived Task Embeddings
SITE applies soft gradient-based head selection to inject ICL-derived task embeddings, outperforming prior embedding adaptation and few-shot ICL across generation, reasoning, and NLU tasks on 12 LLMs from 4B to 70B pa...
-
How Do Language Models Compose Functions?
LLMs solve compositional factual recall either by computing intermediates or directly, with mechanism choice correlated to translation geometry in embedding spaces.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.