Experiments | The ZC07 dataset contains annotated logical forms for each sentence, which we do not use. |
Experiments | Since our goal is not to produce a specific logical form , we directly evaluate on the end-to-end task of translating questions into database queries and measure question-answering accuracy. |
Experiments | Both ZC07 and FUBL used annotated logical forms in training, whereas GUSP-FULL and GUSP++ did not. |
Grounded Unsupervised Semantic Parsing | GUSP is unsupervised and does not require example logical forms or question-answer pairs. |
Introduction | Semantic parsing maps text to a formal meaning representation such as logical forms or structured queries. |
Introduction | However, although these methods exonerate annotators from mastering specialized logical forms , finding the answers for complex ques- |
Introduction | While their approach completely obviates the need for direct supervision, their target logic forms are self-induced clusters, which do not align with existing database or ontology. |
Experiments | Figure 2: Example questions with their logical forms . |
Experiments | The logical forms make use of Freebase symbols as logical constants, as well as a few additional symbols such as count and argmin, to allow for aggregation queries. |
Experiments | We also created a dataset of alignments from these annotated questions by creating an alignment for each Freebase relation mentioned in the logical form for a question, paired with a manually-selected word from the question. |
Extending a Semantic Parser Using a Schema Alignment | Using A, UBL selects a logical form 2 for a sentence 8 by selecting the z with the most likely parse derivations y: h(S) = arg maxz 2y p(y, z|$; 6, A). |
Extending a Semantic Parser Using a Schema Alignment | The probabilistic model is a log-linear model with features for lexical entries used in the parse, as well as indicator features for relation-argument pairs in the logical form , to capture selectional preferences. |
Extending a Semantic Parser Using a Schema Alignment | Inference (parsing) and parameter estimation are driven by standard dynamic programming algorithms (Clark and Curran, 2007), while lexicon induction is based on a novel search procedure through the space of possible higher-order logic unification operations that yield the desired logical form for a training sentence. |
Introduction | (sentence, Relations logical form ) Freebase Extracted |
Related Work | For example, Zettlemoyer and Collins (2007) learn a mapping from textual queries to a logical form . |
Related Work | Importantly, the logical form of these parses contain all of the predicates and entities used in the parse — unlike the label provided in our case, where a grounded time can correspond to any of a number of latent parses. |
Related Work | (2011) relax supervision to require only annotated answers rather than full logical forms . |