For the task of entity disambiguation, mention contexts and entity descriptions both contain various kinds of information content while only a subset of them are helpful for disambiguation. In this paper, we propose a type-aware co-attention model for entity disambiguation, which tries to identify the most discriminative words from mention contexts and most relevant sentences from corresponding entity descriptions simultaneously. To bridge the semantic gap between mention contexts and entity descriptions, we further incorporate entity type information to enhance the co-attention mechanism. Our evaluation shows that the proposed model outperforms the state-of-the-arts on three public datasets. Further analysis also confirms that both the co-attention mechanism and the type-aware mechanism are effective.

Hidden variable models are important tools for solving open domain machine comprehension tasks and have achieved remarkable accuracy in many question answering benchmark datasets. Existing models impose strong independence assumptions on hidden variables, which leaves the interaction among them unexplored. Here we introduce linguistic structures to help capturing global evidence in hidden variable modeling. In the proposed algorithms, question-answer pairs are scored based on structured inference results on parse trees and semantic frames, which aims to assign hidden variables in a global optimal way. Experiments on the MCTest dataset demonstrate that the proposed models are highly competitive with state-of-the-art machine comprehension systems.

The machine reading task, where a computer reads a document and answers questions about it, is important in artificial intelligence research. Recently, many models have been proposed to address it. Word-level models, which have words as units of input and output, have proven to yield state-of-the-art results when evaluated on English datasets. However, in morphologically richer languages, many more unique words exist than in English due to highly productive prefix and suffix mechanisms. This may set back word-level models, since vocabulary sizes too big to allow for efficient computing may have to be employed. Multiple alternative input granularities have been proposed to avoid large input vocabularies, such as morphemes, character n-grams, and bytes. Bytes are advantageous as they provide a universal encoding format across languages, and allow for a small vocabulary size, which, moreover, is identical for every input language. In this work, we investigate whether bytes are suitable as input units across morphologically varied languages. To test this, we introduce two large-scale machine reading datasets in morphologically rich languages, Turkish and Russian. We implement 4 byte-level models, representing the major types of machine reading models and introduce a new seq2seq variant, called encoder-transformer-decoder. We show that, for all languages considered, there are models reading bytes outperforming the current state-of-the-art word-level baseline. Moreover, the newly introduced encoder-transformer-decoder performs best on the morphologically most involved dataset, Turkish. The large-scale Turkish and Russian machine reading datasets are released to public.

For many languages and domains, there is a paucity of available Given such valuable data, modern deep learning-based sentiment data and resources. In some cases, it may be challenging analysis methods excel at determining the sentiment to obtain sufficient in-domain training data, both because polarity of what is being said about companies, products, etc. there may be less data available online and because it may be (Wang et al. 2015). Unfortunately, such deep methods require somewhat harder to find annotators. Hence, a question that substantial amounts of training data, because multiple levels arises is whether one can assist deep networks by incorporating of computation, each with additional weights and parameters, external cues that enable the model to generalize better.

Language Modeling (LM) is a fundamental research topic in a range of areas. Recently, inspired by quantum theory, a novel Quantum Language Model (QLM) has been proposed for Information Retrieval (IR). In this paper, we aim to broaden the theoretical and practical basis of QLM. We develop a Neural Network based Quantum-like Language Model (NNQLM) and apply it to Question Answering. Specifically, based on word embeddings, we design a new density matrix, which represents a sentence (e.g., a question or an answer) and encodes a mixture of semantic subspaces. Such a density matrix, together with a joint representation of the question and the answer, can be integrated into neural network architectures (e.g., 2-dimensional convolutional neural networks). Experiments on the TREC-QA and WIKIQA datasets have verified the effectiveness of our proposed models.

Semantic dependency graph has been recently proposed as an extension of tree-structured syntactic or semantic representation for natural language sentences. It particularly features the structural property of multi-head, which allows nodes to have multiple heads, resulting in a directed acyclic graph(DAG) parsing problem. Yet most statistical parsers focused exclusively on shallow bi-lexical tree structures, DAG parsing remains under-explored. In this paper, we propose a neural transition-based parser, using a variant of list-based arc-eager transition algorithm for dependency graph parsing. Particularly, two non-trivial improvements are proposed for representing the key components of the transition system, to better capture the semantics of segments and internal sub-graph structures. We test our parser on the SemEval-2016 Task 9 dataset (Chinese) and the SemEval-2015 Task 18 dataset (English). On both benchmark datasets, we obtain superior or comparable results to the best performing systems. Our parser can be further improved with a simple ensemble mechanism, resulting in the state-of-the-art performance.

Generating plausible and fluent sentence with desired properties has long been a challenge. Most of the recent works use recurrent neural networks (RNNs) and their variants to predict following words given previous sequence and target label. In this paper, we propose a novel framework to generate constrained sentences via Gibbs Sampling. The candidate sentences are revised and updated iteratively, with sampled new words replacing old ones. Our experiments show the effectiveness of the proposed method to generate plausible and diverse sentences.

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we employ deconvolutional networks as the sequence decoder (generator), providing learned latent codes with more semantic information and better generalization. Our model, trained in an unsupervised manner, yields stronger empirical predictive performance than a decoder based on Long Short-Term Memory (LSTM), with less parameters and considerably faster training. Further, we apply it to text sequence-matching problems. The proposed model significantly outperforms several strong sentence-encoding baselines, especially in the semi-supervised setting.

Generating texts from structured data (e.g., a table) is important for various natural language processing tasks such as question answering and dialog systems. In recent studies, researchers use neural language models and encoder-decoder frameworks for table-to-text generation. However, these neural network-based approaches typically do not model the order of content during text generation. When a human writes a summary based on a given table, he or she would probably consider the content order before wording. In this paper, we propose an order-planning text generation model, where order information is explicitly captured by link-based attention. Then a self-adaptive gate combines the link-based attention with traditional content-based attention. We conducted experiments on the WikiBio dataset and achieve higher performance than previous methods in terms of BLEU, ROUGE, and NIST scores; we also performed ablation tests to analyze each component of our model.

This inconvenience makes us do necessary restorations from character-level dependency parsing results Table 2: Character-level evaluation. Character-level dependency parsing covers all levels of language processing within a Chinese sentence. Our model shows that even integrating the least character position simplifies the pipeline into two steps, character POS tagging, information, it is beneficial to the parser.. and character dependency parsing, while traditional processing Finally, effective integration of two levels of tags boosts has to handle word segmentation, POS tagging for word, the performance most. For CHAR WORD strategy, it is more and word-level dependency parsing as shown in Figure 2. straightforward but also brings too many tags or labels and With different processing hierarchies, we also provide complete thus will slow down the parsing and make the learning more matches (CM) as one metric for the related evaluation. The character parsing performance comparison is given in Table reason might be that since characters instead of words are 1, in which the following observations are obtained.