Learning target side syntactic structure has been shown to improve Neural Machine Translation (NMT). However, incorporating syntax through latent variables introduces additional complexity in inference, as the models need to marginalize over the latent syntactic structures. To avoid this, models often resort to greedy search which only allows them to explore a limited portion of the latent space. In this work, we introduce a new latent variable model, LaSyn, that captures the co-dependence between syntax and semantics, while allowing for effective and efficient inference over the latent space. LaSyn decouples direct dependence between successive latent variables, which allows its decoder to exhaustively search through the latent syntactic choices, while keeping decoding speed proportional to the size of the latent variable vocabulary. We implement LaSyn by modifying a transformer-based NMT system and design a neural expectation maximization algorithm that we regularize with part-of-speech information as the latent sequences. Evaluations on four different MT tasks show that incorporating target side syntax with LaSyn improves both translation quality, and also provides an opportunity to improve diversity.

One prominent approach for data collection has been to automatically generate pseudo-language paired with logical forms, and paraphrase the pseudo-language to natural language through crowdsourcing (Wang et al., 2015). However, this data collection procedure often leads to low performance on real data, due to a mismatch between the true distribution of examples and the distribution induced by the data collection procedure. In this paper, we thoroughly analyze two sources of mismatch in this process: the mismatch in logical form distribution and the mismatch in language distribution between the true and induced distributions. We quantify the effects of these mismatches, and propose a new data collection approach that mitigates them. Assuming access to unlabeled utterances from the true distribution, we combine crowdsourcing with a paraphrase model to detect correct logical forms for the unlabeled utterances. On two datasets, our method leads to 70.6 accuracy on average on the true distribution, compared to 51.3 in paraphrasing-based data collection. 1 Introduction Conversing with a virtual assistant in natural language is one of the most exciting current applications of semantic parsing, the task of mapping natural language utterances to executable logical forms (Zelle and Mooney, 1996; Zettlemoyer and Collins, 2005; Liang et al., 2011). Semantic parsing models rely on supervised training data that pairs natural language utterances with logical forms. Alas, such data does not occur naturally, especially in virtual assistants that are meant to support thousands of different applications and use-cases. Thus, efficient data collection is per-Figure 1: An overview of G RA NNO, a method for annotating unlabeled utterances with their logical forms.

Existing computational methods for the analysis of corpora of text in natural language are still far from approaching a human level of understanding. We attempt to advance the state of the art by introducing a model and algorithmic framework to transform text into recursively structured data. We apply this to the analysis of news titles extracted from a social news aggregation website. We show that a recursive ordered hypergraph is a sufficiently generic structure to represent significant number of fundamental natural language constructs, with advantages over conventional approaches such as semantic graphs. We present a pipeline of transformations from the output of conventional NLP algorithms to such hypergraphs, which we denote as semantic hypergraphs. The features of these transformations include the creation of new concepts from existing ones, the organisation of statements into regular structures of predicates followed by an arbitrary number of entities and the ability to represent statements about other statements. We demonstrate knowledge inference from the hypergraph, identifying claims and expressions of conflicts, along with their participating actors and topics. We show how this enables the actor-centric summarization of conflicts, comparison of topics of claims between actors and networks of conflicts between actors in the context of a given topic. On the whole, we propose a hypergraphic knowledge representation model that can be used to provide effective overviews of a large corpus of text in natural language.

We aim at segmenting words in the Complete Tang Poems (CTP). Although it is possible to do some research about CTP without doing full-scale word segmentation, we must move forward to word-level analysis of CTP for conducting advanced research topics. In November 2018 when we submitted the manuscript for DH 2019 (ADHO), we collected only 2433 poems that were segmented by trained experts, and used the segmented poems to evaluate the segmenter that considered domain knowledge of Chinese poetry. We trained pointwise mutual information (PMI) between Chinese characters based on the CTP poems (excluding the 2433 poems, which were used exclusively only for testing) and the domain knowledge. The segmenter relied on the PMI information to the recover 85.7% of words in the test poems. We could segment a poem completely correct only 17.8% of the time, however. When we presented our work at DH 2019, we have annotated more than 20000 poems. With a much larger amount of data, we were able to apply biLSTM models for this word segmentation task, and we segmented a poem completely correct above 20% of the time. In contrast, human annotators completely agreed on their annotations about 40% of the time.

While some education experts applaud the advancement of high-tech grammar tools as a way to help people more clearly express their thoughts, others aren't so sure. Artificial intelligence, according to the contrarians, is only as smart as the humans who program it, and often just as biased. "Language is part of your heritage and identity, and if you're using a tool that is constantly telling you, 'You're wrong,' that is not a good thing," said Paulo Blikstein, associate professor of communications, media and learning technology design at Columbia University Teachers College. "There is not one mythical, monolithical (English) … And every time we have tried to curtail the evolution of a language, it has never gone well." In the era of spellcheck and auto-correct, does it matter that my son can't spell?

The process of classifying words into their parts of speech and labeling them accordingly is known as part-of-speech tagging or POS-tagging, or simply tagging. Parts of speech are also known as word classes or lexical categories. The part of speech explains how a word is used in a sentence. There are eight main parts of speech -- nouns, pronouns, adjectives, verbs, adverbs, prepositions, conjunctions and interjections. The collection of tags used for a particular task is known as a Tagset.

Language identification ("LI") is the problem of determining the natural language that a document or part thereof is written in. Automatic LI has been extensively researched for over fifty years. Today, LI is a key part of many text processing pipelines, as text processing techniques generally assume that the language of the input text is known. Research in this area has recently been especially active. This article provides a brief history of LI research, and an extensive survey of the features and methods used in the LI literature. We describe the features and methods using a unified notation, to make the relationships between methods clearer. We discuss evaluation methods, applications of LI, as well as off-the-shelf LI systems that do not require training by the end user. Finally, we identify open issues, survey the work to date on each issue, and propose future directions for research in LI.

Measuring of text complexity is a needed task in several domains and applications (such as NLP, semantic web, smart education and etc.). The Semantic layer of a text is more tacit than its syntactic structure and as a result, calculation of semantic complexity is more difficult. Whereas there are famous and powerful academic and commercial syntactic complexity measures, the problem of measuring Semantic complexity is a challenging one, yet. In this article, we introduce the DAST model which stands for Deciding About Semantic Complexity of a Text. In this model, an intuitionistic approach to semantics lets us have a well-defined definition for semantic of a text and its complexity: we consider semantic and meaning as a lattice of intuitions. Semantic complexity is defined as the result of a calculation on this lattice. A set theoretic formal definition of semantic complexity, as a 6-tuple formal system, is provided. By using this formal system, a method for measuring semantic complexity is presented. The evaluation of the proposed approach is done by a detailed example and a case study, a set of eighteen human-judgment experiments and a corpus-based evaluation. The results show that DAST model is capable of deciding about semantic complexity of a text. Furthermore, Analysis of the experiment results leads us to introduce a Markovian model for the process of common-sense multi-steps semantic-complexity reasoning in people. The Experiments-result demonstrates that our method consistently outperforms the random baseline in terms of better precision and accuracy.

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. As a response to this controversy, we present a set of tests that provide a bridge between, on the one hand, the vast amount of linguistic and philosophical theory about compositionality and, on the other, the successful neural models of language. We collect different interpretations of compositionality and translate them into five theoretically grounded tests that are formulated on a task-independent level. In particular, we provide tests to investigate (i) if models systematically recombine known parts and rules (ii) if models can extend their predictions beyond the length they have seen in the training data (iii) if models' composition operations are local or global (iv) if models' predictions are robust to synonym substitutions and (v) if models favour rules or exceptions during training. To demonstrate the usefulness of this evaluation paradigm, we instantiate these five tests on a highly compositional data set which we dub PCFG SET and apply the resulting tests to three popular sequence-to- sequence models: a recurrent, a convolution based and a transformer model. We provide an in depth analysis of the results, that uncover the strengths and weaknesses of these three architectures and point to potential areas of improvement.

Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. This primary goal has been studied under different tasks, such as Question Answering (QA) and Textual Entailment (TE). In this thesis, we investigate the NLU problem through the QA task and focus on the aspects that make it a challenge for the current state-of-the-art technology. This thesis is organized into three main parts: In the first part, we explore multiple formalisms to improve existing machine comprehension systems. We propose a formulation for abductive reasoning in natural language and show its effectiveness, especially in domains with limited training data. Additionally, to help reasoning systems cope with irrelevant or redundant information, we create a supervised approach to learn and detect the essential terms in questions. In the second part, we propose two new challenge datasets. In particular, we create two datasets of natural language questions where (i) the first one requires reasoning over multiple sentences; (ii) the second one requires temporal common sense reasoning. We hope that the two proposed datasets will motivate the field to address more complex problems. In the final part, we present the first formal framework for multi-step reasoning algorithms, in the presence of a few important properties of language use, such as incompleteness, ambiguity, etc. We apply this framework to prove fundamental limitations for reasoning algorithms. These theoretical results provide extra intuition into the existing empirical evidence in the field.