Wei Song, Shuhui Zhou, Ruiji Fu, Ting Liu, Lizhen Liu. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Metaphor is a figure of speech that describes one thing (a target) by mentioning another thing (a source) in a way that is not literally true. Metaphor understanding is an interesting but challenging problem in natural language processing. This paper presents a novel method for metaphor processing based on knowledge graph (KG) embedding. Conceptually, we abstract the structure of a metaphor as an attribute-dependent relation between the target and the source. Each specific metaphor can be represented as a metaphor triple (target, attribute, source). Therefore, we can model metaphor triples just like modeling fact triples in a KG and exploit KG embedding techniques to learn better representations of concepts, attributes and concept relations. In this way, metaphor interpretation and generation could be seen as KG completion, while metaphor detection could be viewed as a representation learning enhanced concept pair classification problem. Technically, we build a Chinese metaphor KG in the form of metaphor triples based on simile recognition, and also extract concept-attribute collocations to help describe concepts and measure concept relations. We extend the translation-based and the rotation-based KG embedding models to jointly optimize metaphor KG embedding and concept-attribute collocation embedding. Experimental results demonstrate the effectiveness of our method. Simile recognition is feasible for building the metaphor triple resource. The proposed models improve the performance on metaphor interpretation and generation, and the learned representations also benefit nominal metaphor detection compared with strong baselines.

This paper proposes to adapt self-attention to discourse level for modeling discourse elements in argumentative student essays.Specifically, we focus on two issues.First, we propose structural sentence positional encodings to explicitly represent sentence positions.Second, we propose to use inter-sentence attentions to capture sentence interactions and enhance sentence representation.We conduct experiments on two datasets: a Chinese dataset and an English dataset.We find that (i) sentence positional encodings can lead to a large improvement for identifying discourse elements; (ii) a structural relative positional encoding of sentences shows to be most effective; (iii) inter-sentence attention vectors are useful as a kind of sentence representation for identifying discourse elements.

This paper proposes a pre-training based automated Chinese essay scoring method.The method involves three components: weakly supervised pre-training, supervised crossprompt fine-tuning and supervised targetprompt fine-tuning.An essay scorer is first pretrained on a large essay dataset covering diverse topics and with coarse ratings, i.e., good and poor, which are used as a kind of weak supervision.The pre-trained essay scorer would be further fine-tuned on previously rated essays from existing prompts, which have the same score range with the target prompt and provide extra supervision.At last, the scorer is fine-tuned on the target-prompt training data.The evaluation on four prompts shows that this method can improve a state-of-the-art neural essay scorer in terms of effectiveness and domain adaptation ability, while in-depth analysis also reveals its limitations.

Organization evaluation is an important dimension of automated essay scoring. This paper focuses on discourse element (i.e., functions of sentences and paragraphs) based organization evaluation. Existing approaches mostly separate discourse element identification and organization evaluation. In contrast, we propose a neural hierarchical multi-task learning approach for jointly optimizing sentence and paragraph level discourse element identification and organization evaluation. We represent the organization as a grid to simulate the visual layout of an essay and integrate discourse elements at multiple linguistic levels. Experimental results show that the multi-task learning based organization evaluation can achieve significant improvements compared with existing work and pipeline baselines. Multiple level discourse element identification also benefits from multi-task learning through mutual enhancement.

Humor recognition is an interesting and challenging task in natural language processing. This paper proposes to exploit syntactic structure features to enhance humor recognition. Our method achieves significant improvements compared with humor theory driven baselines. We found that some syntactic structure features consistently correlate with humor, which indicate interesting linguistic phenomena. Both the experimental results and the analysis demonstrate that humor can be viewed as a kind of style and content independent syntactic structures can help identify humor and have good interpretability.

Simile is a special type of metaphor, where comparators such as like and as are used to compare two objects.Simile recognition is to recognize simile sentences and extract simile components, i.e., the tenor and the vehicle.This paper presents a study of simile recognition in Chinese.We construct an annotated corpus for this research, which consists of 11.3k sentences that contain a comparator.We propose a neural network framework for jointly optimizing three tasks: simile sentence classification, simile component extraction and language modeling.The experimental results show that the neural network based approaches can outperform all rule-based and feature-based baselines.Both simile sentence classification and simile component extraction can benefit from multitask learning.The former can be solved very well, while the latter is more difficult.

Inferring query intent is significant in information retrieval tasks. Query subtopic mining aims to find possible subtopics for a given query to represent potential intents. Subtopic mining is challenging due to the nature of short queries. Learning distributed representations or sequences of words has been developed recently and quickly, making great impacts on many fields. It is still not clear whether distributed representations are effective in alleviating the challenges of query subtopic mining. In this paper, we exploit and compare the main semantic composition of distributed representations for query subtopic mining. Specifically, we focus on two types of distributed representations: paragraph vector which represents word sequences with an arbitrary length directly, and word vector composition. We thoroughly investigate the impacts of semantic composition strategies and the types of data for learning distributed representations. Experiments were conducted on a public dataset offered by the National Institute of Informatics Testbeds and Community for Information Access Research. The empirical results show that distributed semantic representations can achieve outstanding performance for query subtopic mining, compared with traditional semantic representations. More insights are reported as well.

Discourse modes play an important role in writing composition and evaluation.This paper presents a study on the manual and automatic identification of narration, exposition, description, argument and emotion expressing sentences in narrative essays.We annotate a corpus to study the characteristics of discourse modes and describe a neural sequence labeling model for identification.Evaluation results show that discourse modes can be identified automatically with an average F1-score of 0.7.We further demonstrate that discourse modes can be used as features that improve automatic essay scoring (AES).The impacts of discourse modes for AES are also discussed.

We introduce a novel task Anecdote Recognition and Recommendation. An anecdote is a story with a point revealing account of an individual person. Recommending proper anecdotes can be used as evidence to support argumentative writing or as a clue for further reading. We represent an anecdote as a structured tuple — < person, story, implication >. Anecdote recognition runs on archived argumentative essays. We extract narratives containing events of a person as the anecdote story. More importantly, we uncover the anecdote implication, which reveals the meaning and topic of an anecdote. Our approach depends on discourse role identification. Discourse roles such as thesis, main ideas and support help us locate stories and their implications in essays. The experiments show that informative and interpretable anecdotes can be recognized. These anecdotes are used for anecdote recommendation. The anecdote recommender can recommend proper anecdotes in response to given topics. The anecdote implication contributes most for bridging user interested topics and relevant anecdotes.

Parallelism is an important rhetorical device. We propose a machine learning approach for automated sentence parallelism identification in student essays. We build an essay dataset with sentence level parallelism annotated. We derive features by combining generalized word alignment strategies and the alignment measures between word sequences. The experimental results show that sentence parallelism can be effectively identified with a F1 score of 82% at pair-wise level and 72% at parallelism chunk level. Based on this approach, we automatically identify sentence parallelism in more than 2000 student essays and study the correlation between the use of sentence parallelism and the types and quality of essays.

The goal of document representation is to capture certain feature of the document. Many existing document representation methods are based on bag-of-words and ignore semantic relevance between words in the document. There we proposed a semantic smoothed topic model to represent document. It takes semantic similarity into consideration for topic of document. We conducted two experiments utilizing this method for text classification and information retrieval task. The experimental results suggest that our method is useful for capturing the semantic of text to alleviating polysemy and synonyms problem and data sparseness problem.

We present a method of using cohesion to improve discourse element identification for sentences in student essays.New features for each sentence are derived by considering its relations to global and local cohesion, which are created by means of cohesive resources and subtopic coverage.In our experiments, we obtain significant improvements on identifying all discourse elements, especially of +5% F 1 score on thesis and main idea.The analysis shows that global cohesion can better capture thesis statements.

We present a novel method for open domain named entity extraction by exploiting the collective hidden structures in webpage titles. Our method uncovers the hidden textual structures shared by sets of webpage titles based on generalized URL patterns and a multiple sequence alignment technique. The highlights of our method include: 1) The boundaries of entities can be identified automatically in a collective way without any manually designed pattern, seed or class name. 2) The connections between entities are also discovered naturally based on the hidden structures, which makes it easy to incorporate distant or weak supervision. The experiments show that our method can harvest large scale of open domain entities with high precision. A large ratio of the extracted entities are long-tailed and complex and cover diverse topics. Given the extracted entities and their connections, we further show the effectiveness of our method in a weakly supervised setting. Our method can produce better domain specific entities in both precision and recall compared with the state-of-the-art approaches.

Due to innovative computer technologies of Internet, hypermedia and virtual reality, Intelligent Tutoring System not only can support tutoring for a single learner, but also can manage groups of learners to interact for collaborative learning environment. As collaborative learning becomes more and more popular, the grouping according to learners are also become an important topic. The paper analyzes the characteristic of collaborative learning in Intelligent Tutoring System, and researches grouping strategy in the collaborative learning environment to provide learners to discuss with peers, present and defend ideas, exchange diverse beliefs, and be actively engaged in the learning process. A collaborative learning grouping strategy was proposed to enhance the students' learning efficiency by the combination of genetic algorithm with k-means clustering. According to the experimental analysis, it can be concluded that the proposed grouping strategy can efficiently improve the learning achievement.

Aiming at the disadvantages of the word segmentation method based on string matching, the word segmentation method based on comprehension and the word segmentation method based on statistic, a novel field word segmentation model based on ontology was studied. With ontology technology introduced into Chinese word segmentation, the novel model eliminates ambiguities to a great extent and avoids semantic losing problem which is result from ignoring the context information in traditional Chinese word segmentation method. The experimental results show that the novel method can improve the segmentation precision greatly. And this study is valuable for next semantic retrieval in the future work.

Information retrieval is facing great challenge due to the explosion of the network scales. This makes more researchers focus on the issue of web page classification technology. By applying binary decision tree into Support Vector Machine (SVM), an assorted SVM method, Decision Support Vector Machine (DSVM), based on web information classification was introduced in the paper. And the way was further combined with the clustering method to solve the multicategory classification problem, reduce numbers of the training sample in SVM, and advance the classification speed and accuracy effectively.

Digital Libraries have emerged as an important research and application field, and been facilitated by advances in information technology, such as the World Wide Web. The scale and diversity of documents and information of Digital Libraries are immense, which are often stored with different formats. Therefore research in Digital Libraries has generally focused on transparent access to heterogeneous data sources. For the enormous, heterogeneous, dynamic characteristic of Digital Libraries resource, the integrated retrieval system framework of heterogeneous information in Digital Libraries was designed in the paper with the structure of wrapper and mediator. It includes user interface agent, wrapper agent. Mediator agent, knowledge retrieval agent and knowledge base search agent. The agents communicate each other and cooperate together to carry out integrated retrieval function of heterogeneous information in Digital libraries.

New approach of researching intelligent decision support system (IDSS) emerges following the rapid progress of agent system and network technology. By analyzing the characteristics of an IDSS system and the system structure of the multi-agent system, an improved multi-agent system model has been presented in this paper. Combining with the characteristic of multi-agent system, individual agents are organized by groups, a group based cooperative works model and coloration strategy also discussed; and correlation evidences combination mechanism has been adopted as well to ensure the model running reliably and effectively

By analyzing the complex of the integration of heterogeneous database system and the characteristic of a multi-agent system, this paper proposes an agent based architecture that enables actual cooperation among a set of autonomous and heterogeneous information source. Three types of agent which is based on the speech-act theory have been defined in our proposal, coordinately, a new structure of the heterogeneous database system is also introduced.

This paper introduces the E-Collaboration in E-Business. It stresses that HDBIS (Heterogeneous Database Integration System) plays an important role for supporting E-Collaboration in E-Business. HDBIS provides a crucial technique for integration of heterogeneous information source in E-Business. The paper further displays the E-Collaboration model supported by HDBIS through application of clothing companies, which include three layers: manufacturers, sellers and customers. The system architecture, functions and characteristics of HDBIS are presented. The implementation and model of HDBIS using COM/DCOM and ASP is also introduced.