The ZC07 dataset contains annotated logical forms for each sentence, which we do not use.

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.

Both ZC07 and FUBL used annotated logical forms in training, whereas GUSP-FULL and GUSP++ did not.

GUSP is unsupervised and does not require example logical forms or question-answer pairs.

Semantic parsing maps text to a formal meaning representation such as logical forms or structured queries.

However, although these methods exonerate annotators from mastering specialized logical forms , finding the answers for complex ques-

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.

Figure 2: Example questions with their logical forms .

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.

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.

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).

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.

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.

(sentence, Relations logical form ) Freebase Extracted

For example, Zettlemoyer and Collins (2007) learn a mapping from textual queries to a logical form .

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.

(2011) relax supervision to require only annotated answers rather than full logical forms .