Generating Topic-Specific Lexicons | Extract all syntactic contexts of clue words |
Generating Topic-Specific Lexicons | 3.1 Step 1: Extracting syntactic contexts |
Generating Topic-Specific Lexicons | First, we identify syntactic contexts in which specific clue words can be used to express |
Qualitative Analysis of Lexicons | Because our topic-specific lexicons consist of triples (clue word, syntactic context , target), they actually contain more words than topic-independent lexicons of the same size, but topic-specific entries are more selective, which makes the lexicon more focused. |
Quantitative Evaluation of Lexicons | D: the number of syntactic contexts per clue |
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. |
Analysis | By allowing appropriate violations to translate non-syntactic phrases according to particular syntactic contexts , our SDB model better inherits the strength of phrase-based approach than XP+. |
Introduction | whether the current phrase can be translated as a unit or not within particular syntactic contexts (Fox, 2002)2, than that of constituent matching/violation. |
Introduction | It is able to reward non-syntactic translations by assigning an adequate probability to them if these translations are appropriate to particular syntactic contexts on the source side, rather than always punish them. |
The Syntax-Driven Bracketing Model 3.1 The Model | We consider this task as a binary-class classification problem: whether the current source phrase s is bracketable (1)) within particular syntactic contexts (7(3)). |
The Syntax-Driven Bracketing Model 3.1 The Model | If two neighboring sub-phrases 31 and 32 are given, we can use more inner syntactic contexts to complete this binary classification task. |
The Syntax-Driven Bracketing Model 3.1 The Model | new feature into the log-linear translation model: PSDB (b|T, This feature is computed by the SDB model described in equation (3) or equation (4), which estimates a probability that a source span is to be translated as a unit within particular syntactic contexts . |
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 . |
A Generative PCFG Model | Our use of an unweighted lattice reflects our belief that all the segmentations of the given input sentence are a-priori equally likely; the only reason to prefer one segmentation over the another is due to the overall syntactic context which is modeled via the PCFG derivations. |
Discussion and Conclusion | The overall performance of our joint framework demonstrates that a probability distribution obtained over mere syntactic contexts using a Treebank grammar and a data-driven lexicon outperforms upper bounds proposed by previous joint disambiguation systems and achieves segmentation and parsing results on a par with state-of-the-art standalone applications results. |
Introduction | Tsarfaty (2006) argues that for Semitic languages determining the correct morphological segmentation is dependent on syntactic context and shows that increasing information sharing between the morphological and the syntactic components leads to improved performance on the joint task. |
Model Preliminaries | We suggest that in unlexicalized PCFGs the syntactic context may be explicitly modeled in the derivation probabilities. |
Results and Analysis | Yet we note that the better grammars without pruning outperform the poorer grammars using this technique, indicating that the syntactic context aids, to some extent, the disambiguation of unknown tokens. |
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. |