Abstract | Our algorithm instead learns the template structure automatically from raw text, inducing template schemas as sets of linked events (e.g., bombings include detonate, set ofi, and destroy events) associated with semantic roles . |
Introduction | A template defines a specific type of event (e.g., a bombing) with a set of semantic roles (or slots) for the typical entities involved in such an event (e.g., perpetrator, target, instrument). |
Introduction | Our approach learns narrative-like knowledge in the form of IE templates; we learn sets of related events and semantic roles , as shown in this sample output from our system: |
Introduction | A semantic role , such as target, is a cluster of syntactic functions of the template’s event words (e.g., the objects of detonate and explode). |
Learning Templates from Raw Text | The previous section clustered events from the MUC-4 corpus, but its 1300 documents do not provide enough examples of verbs and argument counts to further learn the semantic roles in each |
Learning Templates from Raw Text | 4.3 Inducing Semantic Roles (Slots) |
Learning Templates from Raw Text | Having successfully clustered event words and retrieved an IR-corpas for each cluster, we now address the problem of inducing semantic roles . |
Previous Work | (2006) integrate named entities into pattern learning (PERSON won) to approximate unknown semantic roles . |
Previous Work | Our approach draws on this idea of using unlabeled documents to discover relations in text, and of defining semantic roles by sets of entities. |
Previous Work | Scripts are sets of related event words and semantic roles learned by linking syntactic functions with coreferring arguments. |
Abstract | In this paper we describe an unsupervised method for semantic role induction which holds promise for relieving the data acquisition bottleneck associated with supervised role labelers. |
Abstract | We present an algorithm that iteratively splits and merges clusters representing semantic roles , thereby leading from an initial clustering to a final clustering of better quality. |
Abstract | By combining role induction with a rule-based component for argument identification we obtain an unsupervised end-to-end semantic role labeling system. |
Introduction | The term is most commonly used to describe the automatic identification and labeling of the semantic roles conveyed by sentential constituents (Gildea and J urafsky, 2002). |
Introduction | Semantic roles describe the relations that hold between a predicate and its arguments, abstracting over surface syntactic configurations. |
Introduction | window occupies different syntactic positions — it is the object of broke in sentences (la,b), and the subject in (IC) — while bearing the same semantic role , i.e., the physical object affected by the breaking event. |
Abstract | We introduce a novel semiautomated metric, MEANT, that assesses translation utility by matching semantic role fillers, producing scores that correlate with human judgment as well as HTER but at much lower labor cost. |
Abstract | We first show that when using untrained monolingual readers to annotate semantic roles in MT output, the nonautomatic version of the metric HMEANT achieves a 0.43 correlation coefficient with human adequacy judgments at the sentence level, far superior to BLEU at only 0.20, and equal to the far more expensive HTER. |
Abstract | We then replace the human semantic role annotators with automatic shallow semantic parsing to further automate the evaluation metric, and show that even the semiautomated evaluation metric achieves a 0.34 correlation coefficient with human adequacy judgment, which is still about 80% as closely correlated as HTER despite an even lower labor co st for the evaluation procedure. |
Approach to Semantic Representation of Negation | Instead, we use generic semantic roles . |
Approach to Semantic Representation of Negation | Given s: The cow didn’t eat grass with a fork, typical semantic roles encode AGENT(the cow, eat), THEME(grass, eat), INSTRUMENT(With a fork, eat) and NEGATION(n’t, eat). |
Approach to Semantic Representation of Negation | Like typical semantic roles , option (2) does not reveal the implicit positive meaning carried by statement s. Options (3—5) encode different interpretations: |
Learning Algorithm | Because PropBank adds semantic role annotation on top of the Penn TreeB ank, we have available syntactic annotation and semantic role labels for all instances. |
Negation in Natural Language | State-of-the-art semantic role labelers (e.g., the ones trained over PropBank) do not completely represent the meaning of negated statements. |