Abstract | We identify whether a candidate word pair has hypernym—hyponym relation by using the word-embedding-based semantic projections between words and their hypernyms. |
Introduction | Subsequently, we identify whether an unknown word pair is a hypernym—hyponym relation using the projections (Section 3.4). |
Method | Table l: Embedding offsets on a sample of hypernym—hyponym word pairs . |
Method | Looking at the well-known example: v(king) — v(queen) % v(man) —v(woman), it indicates that the embedding offsets indeed represent the shared semantic relation between the two word pairs . |
Method | As a preliminary experiment, we compute the embedding offsets between some randomly sampled hypernym—hyponym word pairs and measure their similarities. |
Experiments | The prior tree has about 1000 word pairs (dict). |
Experiments | We then remove the word pairs appearing more than 50K times or fewer than 500 times and construct a second prior tree with about 2500 word pairs (align). |
Polylingual Tree-based Topic Models | Figure 1: An example of constructing a prior tree from a bilingual dictionary: word pairs with the same meaning but in different languages are concepts; we create a common parent node to group words in a concept, and then connect to the root; un-correlated words are connected to the root directly. |
Polylingual Tree-based Topic Models | The word pairs define concepts for the prior tree (align). |
Topic Models for Machine Translation | The phrase pair probabilities pw (6| f) are the normalized product of lexical probabilities of the aligned word pairs within that phrase pair (Koehn et al., 2003). |
Topic Models for Machine Translation | where cd(o) is the number of occurrences of the word pair in document d. The lexical probability conditioned on topic k is the unsmoothed probability estimate of those expected counts |
Topic Models for Machine Translation | While vanilla topic models (LDA) can only be applied to monolingual data, there are a number of topic models for parallel corpora: Zhao and Xing (2006) assume aligned word pairs share same topics; Mimno et al. |
Experimental Setup | 4435 word pairs constitute the overlap between Nelson et al.’s norms (1998) and McRae et al.’s (2005) nouns. |
Experimental Setup | This resulted in 7,576 word pairs for which we obtained similarity ratings using Amazon Mechanical Turk (AMT). |
Experimental Setup | Word Pairs Semantic Visual |
Introduction | We performed a large-scale evaluation on a new dataset consisting of human similarity judgments for 7,576 word pairs . |
Results | Table 4: Word pairs with highest semantic and visual similarity according to SAE model. |
Results | Table 4 shows examples of word pairs with highest semantic and visual similarity according to the SAE model. |
Extensions | We use a seed dictionary of 12,630 word pairs to establish node-node correspondences between the two graphs. |
Extensions | As the seed dictionary contains 12,630 word pairs , this means that only every fourth entry of the PPR vector (the German graph has 47,439 nodes) is used for similarity calculation. |
Extensions | synonym extraction lexicon extraction (68 word pairs) (1000 word pairs ) |
Phrase Pair Embedding | Word 1G 500K 20 X 500K Word Pair 7M (500K)2 20 X (500K)2 Phrase Pair 7M (500104 20 X (500104 |
Phrase Pair Embedding | For word pair and phrase pair embedding, the numbers are calculated on IWSLT 2009 dialog training set. |
Phrase Pair Embedding | But for source-target word pair , we may only have 7M bilingual corpus for training (taking IWSLT data set as an example), and there are 20 ><(500K)2 parameters to be tuned. |