Grammatical error correction, like other machine learning tasks, greatly benefits from large quantities of high quality training data, which is typically expensive to produce. While writing a program to automatically generate realistic grammatical errors would be difficult, one could learn the distribution of naturallyoccurring errors and attempt to introduce them into other datasets. Initial work on inducing errors in this way using statistical machine translation has shown promise; we investigate cheaply constructing synthetic samples, given a small corpus of human-annotated data, using an off-the-rack attentive sequence-to-sequence model and a straight-forward post-processing procedure. Our approach yields error-filled artificial data that helps a vanilla bi-directional LSTM to outperform the previous state of the art at grammatical error detection, and a previously introduced model to gain further improvements of over 5% $F_{0.5}$ score. When attempting to determine if a given sentence is synthetic, a human annotator at best achieves 39.39 $F_1$ score, indicating that our model generates mostly human-like instances.

Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by this, we introduce a deep neural model for learning structure-to-substructure tree transductions by extending the standard Long Short-Term Memory, considering the parent-child relationships in the structural recursion. The proposed model can achieve state of the art performance on sentence compression benchmarks, both in terms of accuracy and compression rate.

Abstract-- This paper presents a novel approach for automatic rule learning applicable to an autonomous driving system using real driving data. We represent the actions of other agents (provided by sensors) in the scene via temporal sequences called "episodes". The proposed method adaptively creates new rules automatically by extracting and segmenting valuable information about other agents and their interactions. These rules, which take the form of a "spatiotemporal grammar" or "episodic memory" are stored in a "semantic memory" module for later use. During the testing phase, the system segments constantly changing situations, finds the corresponding parse tree for the current state of the self-car and other agents, and applies the rules stored in semantic memory to stop, yield, continue driving, etc. The method also allows for continues online training during agent driving. Unlike traditional deep driving and machine learning methods that require significant amount of training data to achieve desired quality, the proposed method demonstrates good results with just a few training examples.

Probabilistic context free grammars (PCFG) have been the core of the probabilistic reasoning based parsers for several years especially in the context of the NLP. Multi entity bayesian networks (MEBN) a First Order Logic probabilistic reasoning methodology and is widely adopted and used method for uncertainty reasoning. Further upper ontology like Probabilistic Ontology Web Language (PR-OWL) built using MEBN takes care of probabilistic ontologies which model and capture the uncertainties inherent in the domain's semantic information. The paper attempts to establish a link between probabilistic reasoning in PCFG and MEBN by proposing a formal description of PCFG driven by MEBN leading to usage of PR-OWL modeled ontologies in PCFG parsers.

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).