Revisiting Word Embedding for Contrasting Meaning

@inproceedings{Chen2015RevisitingWE,
  title={Revisiting Word Embedding for Contrasting Meaning},
  author={Zhigang Chen and Wei Lin and Qian Chen and Xiaoping Chen and Si Wei and Hui Jiang and Xiao-Dan Zhu},
  booktitle={ACL},
  year={2015}
}
Contrasting meaning is a basic aspect of semantics. Recent word-embedding models based on distributional semantics hypothesis are known to be weak for modeling lexical contrast. We present in this paper the embedding models that achieve an F-score of 92% on the widely-used, publicly available dataset, the GRE “most contrasting word” questions (Mohammad et al., 2008). This is the highest performance seen so far on this dataset. Surprisingly at the first glance, unlike what was suggested in most… 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
Task Independent Fine Tuning for Word Embeddings
  • Xuefeng Yang, K. Mao
  • Computer Science
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2017
TLDR
A task-independent fine tuning framework to integrate multiple word embeddings and lexical semantic resources to fine tune a target word embedding is proposed and tested by tasks of semantic similarity prediction, analogical reasoning, and sentence completion. Expand
Incorporating Prior Knowledge into Word Embedding for Chinese Word Similarity Measurement
TLDR
A three-stage framework for measuring the Chinese word similarity by incorporating prior knowledge obtained from lexicons and statistics into word embedding is proposed and results show that the system also performs well on other Chinese datasets, which proves its transferability. Expand
Combining Word Embedding and Semantic Lexicon for Chinese Word Similarity Computation
TLDR
A novel framework for measuring the Chinese word similarity by combining word embedding and Tongyici Cilin is proposed and it is shown that the embedding model outperforms the state-of-the-art performance to the best of the authors' knowledge. Expand
Contradiction Detection with Contradiction-Specific Word Embedding
TLDR
A tailored neural network to learn contradiction-specific word embedding (CWE), which can separate antonyms in the opposite ends of a spectrum and performs comparably with the top-performing system in accuracy of three-category classification. Expand
Embedding WordNet Knowledge for Textual Entailment
TLDR
This paper embeds the lexical entailment knowledge contained in WordNet in specially-learned word vectors, which they are called “entailment vectors,” and incorporates these entailment vectors into a decomposable attention model for textual entailment. Expand
Learning Semantic Word Embeddings based on Ordinal Knowledge Constraints
TLDR
Under this framework, semantic knowledge is represented as many ordinal ranking inequalities and the learning of semantic word embeddings (SWE) is formulated as a constrained optimization problem, where the data-derived objective function is optimized subject to all ordinal knowledge inequality constraints extracted from available knowledge resources. Expand
Joint approaches for learning word representations from text corpora and knowledge bases
TLDR
Three main joint approaches for learning word representations are presented: (i) Joint Representation Learning for Additional Evidence (JointReps), (ii) Joint Hierarchical Word representation (HWR) and (iii) Sense-Aware Word Representations (SAWR). Expand
A distant supervision method based on paradigmatic relations for learning word embeddings
TLDR
A distant supervision method based on paradigmatic relations is proposed for learning word embeddings and it outperformed when compared against other existing models. 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
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
Computing Lexical Contrast
TLDR
An automatic and empirical measure of lexical contrast that relies on the contrast hypothesis, corpus statistics, and the structure of a Roget-like thesaurus is presented, which obtains high precision and large coverage, outperforming existing methods. Expand
Learning Semantic Word Embeddings based on Ordinal Knowledge Constraints
TLDR
Under this framework, semantic knowledge is represented as many ordinal ranking inequalities and the learning of semantic word embeddings (SWE) is formulated as a constrained optimization problem, where the data-derived objective function is optimized subject to all ordinal knowledge inequality constraints extracted from available knowledge resources. Expand
An Empirical Study on the Effect of Negation Words on Sentiment
TLDR
A sentiment treebank is used to show that existing heuristics used to estimate the sentiment of negated expressions are poor estimators of sentiment and a recently proposed composition model that relies on both the negator and the argument is evaluated. Expand
Polarity Inducing Latent Semantic Analysis
TLDR
The key contribution of this work is to show how to assign signs to the entries in the co-occurrence matrix on which LSA operates, so as to induce a subspace with the desired property. Expand
Computing Word-Pair Antonymy
TLDR
A new automatic and empirical measure of antonymy that combines corpus statistics with the structure of a published thesaurus is presented, obtaining a precision of over 80%. Expand
From Frequency to Meaning: Vector Space Models of Semantics
TLDR
The goal in this survey is to show the breadth of applications of VSMs for semantics, to provide a new perspective on VSMs, and to provide pointers into the literature for those who are less familiar with the field. Expand
Distributed Representations of Words and Phrases and their Compositionality
TLDR
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling. Expand
Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification
TLDR
Three neural networks are developed to effectively incorporate the supervision from sentiment polarity of text (e.g. sentences or tweets) in their loss functions and the performance of SSWE is improved by concatenating SSWE with existing feature set. Expand
One billion word benchmark for measuring progress in statistical language modeling
TLDR
A new benchmark corpus to be used for measuring progress in statistical language modeling, with almost one billion words of training data, is proposed, which is useful to quickly evaluate novel language modeling techniques, and to compare their contribution when combined with other advanced techniques. 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
...
1
2
3
4
...