We propose a non-parametric Bayesian model for unsupervised semantic parsing. Following Poon and Domingos (2009), we consider a semantic parsing setting where the goal is to (1) decompose the syntactic dependency tree of a sentence into fragments, (2) assign each of these fragments to a cluster of semantically equivalent syntactic structures, and (3) predict predicate-argument relations between the fragments. We use hierarchical Pitman-Yor processes to model statistical dependencies between meaning representations of predicates and those of their arguments, as well as the clusters of their syntactic realizations. We develop a modification of the Metropolis-Hastings split-merge sampler, resulting in an efficient inference algorithm for the model. The method is experimentally evaluated by using the induced semantic representation for the question answering task in the biomedical domain. 1

We consider the problem of learning factored probabilistic CCG grammars for semantic parsing from data containing sentences paired with logical-form meaning representations. Traditional CCG lexicons list lexical items that pair words and phrases with syntactic and semantic content. Such lexicons can be inefficient when words appear repeatedly with closely related lexical content. In this paper, we introduce factored lexicons, which include both lexemes to model word meaning and templates to model systematic variation in word usage. We also present an algorithm for learning factored CCG lexicons, along with a probabilistic parse-selection model. Evaluations on benchmark datasets demonstrate that the approach learns highly accurate parsers, whose generalization performance benefits greatly from the lexical factoring. 1

We introduce two Bayesian models for unsupervised semantic role labeling (SRL) task. The models treat SRL as clustering of syntactic signatures of arguments with clusters corresponding to semantic roles. The first model induces these clusterings independently for each predicate, exploiting the Chinese Restaurant Process (CRP) as a prior. In a more refined hierarchical model, we inject the intuition that the clusterings are similar across different predicates, even though they are not necessarily identical. This intuition is encoded as a distance-dependent CRP with a distance between two syntactic signatures indicating how likely they are to correspond to a single semantic role. These distances are automatically induced within the model and shared across predicates. Both models achieve state-of-the-art results when evaluated on PropBank, with the coupled model consistently outperforming the factored counterpart in all experimental set-ups. 1

Conversations provide rich opportunities for interactive, continuous learning. When something goes wrong, a system can ask for clarification, rewording, or otherwise redirect the interaction to achieve its goals. In this paper, we present an approach for using conversational interactions of this type to induce semantic parsers. We demonstrate learning without any explicit annotation of the meanings of user utterances. Instead, we model meaning with latent variables, and introduce a loss function to measure how well potential meanings match the conversation. This loss drives the overall learning approach, which induces a weighted CCG grammar that could be used to automatically bootstrap the semantic analysis component in a complete dialog system. Experiments on DARPA Communicator conversational logs demonstrate effective learning, despite requiring no explicit meaning annotations. 1

Reducing the reliance of semantic role labeling (SRL) methods on human-annotated data has become an active area of research. However, the prior work has largely focused on either (1) looking into ways to improve supervised SRL systems by producing surrogate annotated data and reducing sparsity of lexical features or (2) considering completely unsupervised semantic role induction settings. In this work, we aim to link these two veins of research by studying how unsupervised techniques can be improved by exploiting small amounts of labeled data. We extend a state-of-the-art Bayesian model for unsupervised semantic role induction to better accommodate for annotated sentences. Our semi-supervised method outperforms a strong supervised baseline when only a small amount of labeled data is available.

We present a method for training a semantic parser using only a knowledge base and an unlabeled text corpus, without any individually annotated sentences. Our key observation is that multiple forms of weak supervision can be combined to train an accurate semantic parser: semantic supervision from a knowledge base, and syntactic supervision from dependencyparsed sentences. We apply our approach to train a semantic parser that uses 77 relations from Freebase in its knowledge representation. This semantic parser extracts instances of binary relations with state-of-theart accuracy, while simultaneously recovering much richer semantic structures, such as conjunctions of multiple relations with partially shared arguments. We demonstrate recovery of this richer structure by extracting logical forms from natural language queries against Freebase. On this task, the trained semantic parser achieves 80 % precision and 56 % recall, despite never having seen an annotated logical form. 1

We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervised induction of semantic roles from sentences annotated with automatically-predicted syntactic dependency representations and use a stateof-the-art generative Bayesian non-parametric model. At inference time, instead of only seeking the model which explains the monolingual data available for each language, we regularize the objective by introducing a soft constraint penalizing for disagreement in argument labeling on aligned sentences. We propose a simple approximate learning algorithm for our set-up which results in efficient inference. When applied to German-English parallel data, our method obtains a substantial improvement over a model trained without using the agreement signal, when both are tested on non-parallel sentences. 1