Abstract | Most existing algorithms for learning continuous word representations typically only model the syntactic context of words but ignore the sentiment of text. |
Abstract | This is problematic for sentiment analysis as they usually map words with similar syntactic context but opposite sentiment polarity, such as good and bad, to neighboring word vectors. |
Introduction | The most serious problem is that traditional methods typically model the syntactic context of words but ignore the sentiment information of text. |
Related Work | (2011) introduce C&W model to learn word embedding based on the syntactic contexts of words. |
Related Work | The C&W model learns word embedding by modeling syntactic contexts of words but ignoring sentiment information. |
Related Work | By contrast, SSWEh and SSWET learn sentiment-specific word embedding by integrating the sentiment polarity of sentences but leaving out the syntactic contexts of words. |
Abstract | We present a novel technique for semantic frame identification using distributed representations of predicates and their syntactic context ; this technique leverages automatic syntactic parses and a generic set of word embeddings. |
Abstract | Given labeled data annotated with frame-semantic parses, we learn a model that projects the set of word representations for the syntactic context around a predicate to a low dimensional representation. |
Frame Identification with Embeddings | First, we extract the words in the syntactic context of runs; next, we concatenate their word embeddings as described in §2.2 to create an initial vector space representation. |
Frame Identification with Embeddings | Formally, let cc represent the actual sentence with a marked predicate, along with the associated syntactic parse tree; let our initial representation of the predicate context be Suppose that the word embeddings we start with are of dimension n. Then 9 is a function from a parsed sentence cc to Rm“, where k is the number of possible syntactic context types. |
Overview | We use word embeddings to represent the syntactic context of a particular predicate instance as a vector. |
Overview | We could represent the syntactic context of runs as a vector with blocks for all the possible dependents warranted by a syntactic parser; for example, we could assume that positions 0 . |
Compositional distributional semantics | Another issue is that the same or similar items that occur in different syntactic contexts are assigned different semantic types with incomparable representations. |
Compositional distributional semantics | Besides losing the comparability of the semantic contribution of a word across syntactic contexts , we also worsen the data sparseness issues. |
The practical lexical function model | We may still want to represent word meanings in different syntactic contexts differently, but at the same time we need to incorporate a formal connection between those representations, e.g., between the transitive and the intransitive instantiations of the verb to eat. |
The practical lexical function model | 2To determine the number and ordering of matrices representing the word in the current syntactic context , our plf implementation relies on the syntactic type assigned to the word in the categorial grammar parse of the sentence. |
The practical lexical function model | Table 4: The verb to eat associated to different sets of matrices in different syntactic contexts . |
Abstract | Although a: and 33’ are not identical, it is likely that 293/ (2, 3) is similar to 233(1, 2) because the determiner and the noun appear in similar syntactic context . |
Abstract | 233/ (5, 7) also may be somewhat similar, but 233/ (2, 7) should not be very similar to 233(1, 2) because the noun and the determiner appear in a different syntactic context . |
Abstract | The observation that the covariance matrices depend on local syntactic context is the main driving force behind our solution. |
Introduction | 0 Our low dimensional embeddings are tailored to the syntactic context of words (head, modifier). |
Results | More interestingly, we can consider the impact of syntactic context on the derived projections. |
Results | The two bottom parts of the table demonstrate that how the projections change depending on the syntactic context of the word. |