Detecting user intents from utterances is the basis of natural language understanding (NLU) task. To understand the meaning of utterances, some work focuses on fully representing utterances via semantic parsing in which annotation cost is labor-intentsive. While some researchers simply view this as intent classification or frequently asked questions (FAQs) retrieval, they do not leverage the shared utterances among different intents. We propose a simple and novel multi-point semantic representation framework with relatively low annotation cost to leverage the fine-grained factor information, decomposing queries into four factors, i.e., topic, predicate, object/condition, query type. Besides, we propose a compositional intent bi-attention model under multi-task learning with three kinds of attention mechanisms among queries, labels and factors, which jointly combines coarse-grained intent and fine-grained factor information. Extensive experiments show that our framework and model significantly outperform several state-of-the-art approaches with an improvement of 1.35%-2.47% in terms of accuracy.

This paper proposed a novel scheme for extracting character relation from unstructured text based on dependency grammar rules. First of all, we took the Three Kingdoms characters as our research object, then selected articles containing target relationships and thus constructed a corpus consisting of 1000 sentences. Secondly, We analyzed the corpus and developed a set of dependent grammar rules for relation extraction. Finally, we proposed a system, which makes it possible for computers to automatically extract and identify character relationships.

Automatic anaphora resolution is useful for many natural language process tasks, including automatic summarization, information extraction and machine translation. This paper took the novel Life as the original corpus, and then annotated the anaphora relations in this corpus. Based on this corpus, we analyzed the distribution of different types of anaphora phenomena, and then developed a set of rules for automatic anaphora resolution, which might be useful for future automatic processing.

We present a novel annotation framework for representing predicate-argument structures, which uses dependency trees to encode the syntactic and semantic roles of a sentence simultaneously. The main contribution is a semantic role transmission model, which eliminates the structural gap between syntax and shallow semantics, making them compatible. A Chinese semantic treebank was built under the proposed framework, and the first release containing about 14K sentences is made freely available. The proposed framework enables semantic role labeling to be solved as a sequence labeling task, and experiments show that standard sequence labelers can give competitive performance on the new treebank compared with state-of-the-art graph structure models.

Word segmentation is a necessary first step for automaticsyntactic analysis of Chinese text. Chinese segmentationis highly accurate on news data, but the accuraciesdrop significantly on other domains, such as science andliterature. For scientific domains, a significant portionof out-of-vocabulary words are domain-specific terms, and therefore lexicons can be used to improve segmentationsignificantly. For the literature domain, however,there is not a fixed set of domain terms. For example,each novel can contain a specifiac set of person, organizationand location names. We investigate a method forautomatically mining common noun entities for eachnovel using information extraction techniques, and usethe resulting entities to improve a state-of-the-art segmentationmodel for the novel. In particular, we designa novel double-propagation algorithm that mines nounentities together with common contextual patterns, anduse them as plug-in features to a model trained on thesource domain. An advantage of our method is that noretraining for the segmentation model is needed for eachnovel, and hence it can be applied efficiently given thehuge number of novels on the web. Results on five differentnovels show significantly improved accuracies,in particular for OOV words.

Distributed word representations capture relational similarities by means of vector arithmetics, giving high accuracies on analogy detection.We empirically investigate the use of syntactic dependencies on improving Chinese analogy detection based on distributed word representations, showing that a dependency-based embeddings does not perform better than an ngram-based embeddings, but dependency structures can be used to improve analogy detection by filtering candidates.In addition, we show that distributed representations of dependency structure can be used for measuring relational similarities, thereby help analogy mining.

Open Relation Extraction (ORE) overcomes the limitations of traditional IE techniques, which train individual extractors for every single relation type.Systems such as ReVerb, PATTY, OLLIE, and Exemplar have attracted much attention on English ORE.However, few studies have been reported on ORE for languages beyond English.This paper presents a syntax-based Chinese (Zh) ORE system, ZORE, for extracting relations and semantic patterns from Chinese text.ZORE identifies relation candidates from automatically parsed dependency trees, and then extracts relations with their semantic patterns iteratively through a novel double propagation algorithm.Empirical results on two data sets show the effectiveness of the proposed system.

This paper presents the SELC Model (SElf-Supervised, (Lexicon-based and (Corpus-based Model) for sentiment classification. The SELC Model includes two phases. The first phase is a lexicon-based iterative process. In this phase, some reviews are initially classified based on a sentiment dictionary. Then more reviews are classified through an iterative process with a negative/positive ratio control. In the second phase, a supervised classifier is learned by taking some reviews classified in the first phase as training data. Then the supervised classifier applies on other reviews to revise the results produced in the first phase. Experiments show the effectiveness of the proposed model. SELC totally achieves 6.63% F1-score improvement over the best result in previous studies on the same data (from 82.72% to 89.35%). The first phase of the SELC Model independently achieves 5.90% improvement (from 82.72% to 88.62%). Moreover, the standard deviation of F1-scores is reduced, which shows that the SELC Model could be more suitable for domain-independent sentiment classification.