We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics of SQL. It detects and excludes faulty programs during the decoding procedure by conditioning on the execution of partially generated program. The mechanism can be used with any autoregressive generative model, which we demonstrate on four state-of-the-art recurrent or template-based semantic parsing models. We demonstrate that execution guidance universally improves model performance on various text-to-SQL datasets with different scales and query complexity: WikiSQL, ATIS, and GeoQuery. As a result, we achieve new state-of-the-art execution accuracy of 83.8% on WikiSQL.

Identifying the salience (i.e. importance) of discourse units is an important task in language understanding. While events play important roles in text documents, little research exists on analyzing their saliency status. This paper empirically studies the Event Salience task and proposes two salience detection models based on content similarities and discourse relations. The first is a feature based salience model that incorporates similarities among discourse units. The second is a neural model that captures more complex relations between discourse units. Tested on our new large-scale event salience corpus, both methods significantly outperform the strong frequency baseline, while our neural model further improves the feature based one by a large margin. Our analyses demonstrate that our neural model captures interesting connections between salience and discourse unit relations (e.g., scripts and frame structures).

Text representations using neural word embeddings have proven effective in many NLP applications. Recent researches adapt the traditional word embedding models to learn vectors of multiword expressions (concepts/entities). However, these methods are limited to textual knowledge bases (e.g., Wikipedia). In this paper, we propose a novel and simple technique for integrating the knowledge about concepts from two large scale knowledge bases of different structure (Wikipedia, and Probase) in order to learn concept representations. We adapt the efficient skip-gram model to seamlessly learn from the knowledge in Wikipedia text and Probase concept graph. We evaluate our concept embedding models on two tasks: 1) analogical reasoning, where we achieve a stateof-the-art performance of 91% on semantic analogies, 2) concept categorization, where we achieve a state-of-the-art performance on two benchmark datasets achieving categorization accuracy of 100% on one and 98% on the other. Additionally, we present a case study to evaluate our model on unsupervised argument type identification for neural semantic parsing. We demonstrate the competitive accuracy of our unsupervised method and its ability to better generalize to out of vocabulary entity mentions compared to the tedious and error prone methods which depend on gazetteers and regular expressions. In this paper, we use the terms "concept" and "entity" interchangeably. Hongxia Jin Samsung Research America 665 Clyde Avenue, Mountain View, CA 94043, USA Email: hongxia.jin@samsung.com 2 Walid Shalaby et al. Figure 1 Integrating knowledge from Wikipedia text (left) and Probase concept graph (right). Local concept-concept, concept-word, and word-word contexts are generated from both KBs and used for training the skip-gram model.

Answering compositional questions requiring multi-step reasoning is challenging. We introduce an end-to-end differentiable model for interpreting questions about a knowledge graph (KG), which is inspired by formal approaches to semantics. Each span of text is represented by a denotation in a KG and a vector that captures ungrounded aspects of meaning. Learned composition modules recursively combine constituent spans, culminating in a grounding for the complete sentence which answers the question. For example, to interpret "not green", the model represents "green" as a set of KG entities and "not" as a trainable ungrounded vector---and then uses this vector to parameterize a composition function that performs a complement operation. For each sentence, we build a parse chart subsuming all possible parses, allowing the model to jointly learn both the composition operators and output structure by gradient descent from end-task supervision. The model learns a variety of challenging semantic operators, such as quantifiers, disjunctions and composed relations, and infers latent syntactic structure. It also generalizes well to longer questions than seen in its training data, in contrast to RNN, its tree-based variants, and semantic parsing baselines.

While neural networks have shown impressive performance on large datasets, applying these models to tasks where little data is available remains a challenging problem. In this paper we propose to use feature transfer in a zero-shot experimental setting on the task of semantic parsing. We first introduce a new method for learning the shared space between multiple domains based on the prediction of the domain label for each example. Our experiments support the superiority of this method in a zero-shot experimental setting in terms of accuracy metrics compared to state-of-the-art techniques. In the second part of this paper we study the impact of individual domains and examples on semantic parsing performance. We use influence functions to this aim and investigate the sensitivity of domain-label classification loss on each example. Our findings reveal that cross-domain adversarial attacks identify useful examples for training even from the domains the least similar to the target domain. Augmenting our training data with these influential examples further boosts our accuracy at both the token and the sequence level.

Ever since diving into Natural Language Processing (NLP), I've always wanted to write something rather introductory about it at a high level, to provide some structure in my understanding, and to give another perspective of the area -- in contrast to the popularity of doing NLP using Deep Learning. Given a sentence, traditionally the following are the different stages on how a sentence would be analyzed to gain deeper insights. At this stage we care about the words that make up the sentence, how they are formed, and how do they change depending on their context. In this stage, we focus more on the relationship of the words within a sentence -- how a sentence is constructed. To derive this understanding, syntactical analysis is usually done at a sentence-level, where as for morphology the analysis is done at word level. Once we've understood the syntactic structures, we are more prepared to get into the "meaning" of the sentence (for a fun read on what meaning can actually mean in NLP -- head over here to dive into a Twitter discussion on the subject).

Existing neural semantic parsers mainly utilize a sequence encoder, i.e., a sequential LSTM, to extract word order features while neglecting other valuable syntactic information such as dependency graph or constituent trees. In this paper, we first propose to use the \textit{syntactic graph} to represent three types of syntactic information, i.e., word order, dependency and constituency features. We further employ a graph-to-sequence model to encode the syntactic graph and decode a logical form. Experimental results on benchmark datasets show that our model is comparable to the state-of-the-art on Jobs640, ATIS and Geo880. Experimental results on adversarial examples demonstrate the robustness of the model is also improved by encoding more syntactic information.

A common question when studying a class of context-free grammars (CFGs) is whether equivalence is decidable within this class. We answer this question positively for the class of Clark-congruential grammars, which are of interest to grammatical inference. We also consider the problem of checking whether a given CFG is Clark-congruential, and show that it is decidable given that the CFG is a deterministic CFG.

Given a text description, most existing semantic parsers synthesize a program in one shot. However, in reality, the description can be ambiguous or incomplete, solely based on which it is quite challenging to produce a correct program. In this paper, we investigate interactive semantic parsing for If-Then recipes where an agent can interact with users to resolve ambiguities. We develop a hierarchical reinforcement learning (HRL) based agent that can improve the parsing performance with minimal questions to users. Results under both simulation and human evaluation show that our agent substantially outperforms non-interactive semantic parsers and rule-based agents.

Designing a reliable natural language (NL) interface for querying tables has been a longtime goal of researchers in both the data management and natural language processing (NLP) communities. Such an interface receives as input an NL question, translates it into a formal query, executes the query and returns the results. Errors in the translation process are not uncommon, and users typically struggle to understand whether their query has been mapped correctly. We address this problem by explaining the obtained formal queries to non-expert users. Two methods for query explanations are presented: the first translates queries into NL, while the second method provides a graphic representation of the query cell-based provenance (in its execution on a given table). Our solution augments a state-of-the-art NL interface over web tables, enhancing it in both its training and deployment phase. Experiments, including a user study conducted on Amazon Mechanical Turk, show our solution to improve both the correctness and reliability of an NL interface.