Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules

06/01/2017
by   Ivan Vulić, et al.
0

Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that have similar distributional signatures. These effects are detrimental for language understanding systems, which may infer that 'inexpensive' is a rephrasing for 'expensive' or may not associate 'acquire' with 'acquires'. In this work, we propose a novel morph-fitting procedure which moves past the use of curated semantic lexicons for improving distributional vector spaces. Instead, our method injects morphological constraints generated using simple language-specific rules, pulling inflectional forms of the same word close together and pushing derivational antonyms far apart. In intrinsic evaluation over four languages, we show that our approach: 1) improves low-frequency word estimates; and 2) boosts the semantic quality of the entire word vector collection. Finally, we show that morph-fitted vectors yield large gains in the downstream task of dialogue state tracking, highlighting the importance of morphology for tackling long-tail phenomena in language understanding tasks.

READ FULL TEXT
research
05/08/2018

Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources

Word vector specialisation (also known as retrofitting) is a portable, l...
research
03/02/2016

Counter-fitting Word Vectors to Linguistic Constraints

In this work, we present a novel counter-fitting method which injects an...
research
06/01/2017

Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

We present Attract-Repel, an algorithm for improving the semantic qualit...
research
09/11/2018

Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization

Semantic specialization is the process of fine-tuning pre-trained distri...
research
09/30/2022

Evaluation of taxonomic and neural embedding methods for calculating semantic similarity

Modelling semantic similarity plays a fundamental role in lexical semant...
research
10/24/2020

Word2vec Conjecture and A Limitative Result

Being inspired by the success of word2vec <cit.> in capturing analogies,...
research
10/11/2018

Towards Understanding Linear Word Analogies

A surprising property of word vectors is that vector algebra can often b...

Please sign up or login with your details

Forgot password? Click here to reset