Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction

@article{Nguyen2016IntegratingDL,
  title={Integrating Distributional Lexical Contrast into Word Embeddings for Antonym-Synonym Distinction},
  author={Kim Anh Nguyen and Sabine Schulte im Walde and Ngoc Thang Vu},
  journal={ArXiv},
  year={2016},
  volume={abs/1605.07766}
}
We propose a novel vector representation that integrates lexical contrast into distributional vectors and strengthens the most salient features for determining degrees of word similarity. The improved vectors significantly outperform standard models and distinguish antonyms from synonyms with an average precision of 0.66-0.76 across word classes (adjectives, nouns, verbs). Moreover, we integrate the lexical contrast vectors into the objective function of a skip-gram model. The novel embedding… Expand
Antonym-Synonym Classification Based on New Sub-space Embeddings
TLDR
Experimental results show that the proposed model outperforms existing research on antonym synonym distinction in both speed and performance. Expand
Distinguishing antonymy, synonymy and hypernymy with distributional and distributed vector representations and neural networks
TLDR
A novel weighted feature for constructing word vectors by relying on distributional lexical contrast, a feature capable of differentiating between antonymy and synonymy, and a novel neural model to learn hierarchical embeddings for hypernymy detection and directionality are proposed. Expand
Revisit Word Embeddings with Semantic Lexicons for Modeling Lexical Contrast
TLDR
The results of the first two experiments show that LWET significantly improves the ability of word embeddings to detect antonyms, thus achieving the state-of-the-art performance and can remain and strengthen the semantic structure rather than destroy it when tuning word distributions in vector space. Expand
Injecting Lexical Contrast into Word Vectors by Guiding Vector Space Specialisation
TLDR
It is shown that a careful selection of the external constraints can steer and improve the specialisation of word vector space specialisation models. Expand
Simplified Natural Language Processing and Discrimination in Antonyms-Synonyms Word Structure in a Neural Network Approach to Exploit Lexico-Semantic Pattern
To get high efficiency or high yielding in NLP system the vital challenge is to distinguish between antonym and synonym. By using lexico-syntactic patterns in pattern-based models, which areExpand
Improving Word Embeddings for Antonym Detection Using Thesauri and SentiWordNet
TLDR
To generate word embeddings that are capable of detecting antonyms, the objective function of Skip-Gram model is modified, and the supervised synonym and antonym information in thesauri as well as the sentiment information of each word in SentiWordNet are utilized. Expand
Intuitive Contrasting Map for Antonym Embeddings
TLDR
It is shown that modern word embeddings contain information that distinguishes synonyms and antonyms despite small cosine similarities between corresponding vectors, and a contrasting map trained on a small labeled subset of the data is shown to improve the performance on downstream tasks. Expand
Synonyms and Antonyms: Embedded Conflict
TLDR
It is shown that modern embeddings contain information that distinguishes synonyms and antonyms despite small cosine similarities between corresponding vectors. Expand
Learning Lexical Subspaces in a Distributional Vector Space
TLDR
This paper proposes LexSub, a novel approach towards unifying lexical and distributional semantics by defining subspaces of the distributional vector space in which a lexical relation should hold, which outperforms previous systems on extrinsic classification tasks that benefit from exploiting lexical relational cues. Expand
Explicit Retrofitting of Distributional Word Vectors
TLDR
This work transforms external lexico-semantic relations into training examples which are used to learn an explicit retrofitting model (ER), which allows us to learn a global specialization function and specialize the vectors of words unobserved in the training data as well. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 34 REFERENCES
Uncovering Distributional Differences between Synonyms and Antonyms in a Word Space Model
TLDR
It is demonstrated that using suitable features, differences in the contexts of synonymous and antonymous German adjective pairs can be identified with a simple word space model. Expand
A Multitask Objective to Inject Lexical Contrast into Distributional Semantics
TLDR
The multitask Lexical Contrast Model (mLCM), an extension of the effective Skip-gram method that optimizes semantic vectors on the joint tasks of predicting corpus contexts and making the representations of WordNet synonyms closer than that of matching WordNet antonyms, is introduced. Expand
Word Embedding-based Antonym Detection using Thesauri and Distributional Information
TLDR
This paper proposes a novel approach to train word embeddings to capture antonyms by utilizing supervised synonym and antonym information from thesauri, as well as distributional information from large-scale unlabelled text data. Expand
Evaluating WordNet-based Measures of Lexical Semantic Relatedness
TLDR
An information-content-based measure proposed by Jiang and Conrath is found superior to those proposed by Hirst and St-Onge, Leacock and Chodorow, Lin, and Resnik, and why distributional similarity is not an adequate proxy for lexical semantic relatedness. Expand
Taking Antonymy Mask off in Vector Space
TLDR
APAnt is introduced, a new AveragePrecision-based measure for the unsupervised discrimination of antonymy from synonymy using Distributional Semantic Models (DSMs) using Average Precision to estimate the extent and salience of the intersection among the most descriptive contexts of two target words. Expand
Directional distributional similarity for lexical inference
TLDR
This paper investigates the nature of directional (asymmetric) similarity measures that aim to quantify distributional feature inclusion, identifies desired properties of such measures for lexical inference, specifies a particular measure based on Average Precision that addresses these properties, and demonstrates the empirical benefit of directional measures for two different NLP datasets. Expand
Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification
TLDR
It is demonstrated that statistics over discourse relations, collected via explicit discourse markers as proxies, can be utilized as salient indicators for paradigmatic relations in multiple languages, outperforming patterns in terms of recall and F1-score. Expand
Efficient Estimation of Word Representations in Vector Space
TLDR
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities. Expand
WordNet: A Lexical Database for English
TLDR
WordNet1 provides a more effective combination of traditional lexicographic information and modern computing, and is an online lexical database designed for use under program control. Expand
Using Mined Coreference Chains as a Resource for a Semantic Task
TLDR
It is shown that coreference-based word embeddings improve F1 on the task of antonym classification by up to .09, and coreference chains extracted from a large corpus are used as a resource for semantic tasks. Expand
...
1
2
3
4
...