COLING 2016 Papers

Evocation is a directed yet weighted semantic relationship between lexicalized concepts. Although evocation relations are considered potentially useful in several semantic NLP tasks, the prediction of the evocation relation between an arbitrary pair of concepts remains difficult, since evocation relationships cover a broader range of semantic relations rooted in human perception and experience. This paper presents a supervised learning approach to predict the strength (by regression) and to determine the directionality (by classification) of the evocation relation that might hold between a pair of lexicalized concepts. Empirical results that were obtained by investigating useful features are shown, indicating that a combination of the proposed features largely outperformed individual baselines, and also suggesting that semantic relational vectors computed from existing semantic vectors for lexicalized concepts were indeed effective for both the prediction of strength and the determination of directionality.

Human languages have multiple strategies that allow us to discriminate objects in a vast variety of contexts. Colours have been extensively studied from this point of view. In particular, previous research in artificial language evolution has shown how artificial languages may emerge based on specific strategies to distinguish colours. Still, it has not been shown how several strategies of diverse complexity can be autonomously managed by artificial agents . We propose an intrinsic motivation system that allows agents in a population to create a shared artificial language and progressively increase its expressive power. Our results show that with such a system agents successfully regulate their language development, which indicates a relation between population size and consistency in the emergent communicative systems.

Most neural network models for document classification on social media focus on text information to the neglect of other information on these platforms. In this paper, we classify post stance on social media channels and develop UTCNN, a neural network model that incorporates user tastes, topic tastes, and user comments on posts. UTCNN not only works on social media texts, but also analyzes texts in forums and message boards. Experiments performed on Chinese Facebook data and English online debate forum data show that UTCNN achieves a 0.755 macro average f-score for supportive, neutral, and unsupportive stance classes on Facebook data, which is significantly better than models in which either user, topic, or comment information is withheld. This model design greatly mitigates the lack of data for the minor class. In addition, UTCNN yields a 0.842 accuracy on English online debate forum data, which also significantly outperforms results from previous work, showing that UTCNN performs well regardless of language or platform.

Emotions in code-switching text can be expressed in either monolingual or bilingual forms. However, relatively little research has emphasized on code-switching text. In this paper, we propose a Bilingual Attention Network (BAN) model to aggregate the monolingual and bilingual informative words to form vectors from the document representation, and integrate the attention vectors to predict the emotion. The experiments show that the effectiveness of the proposed model. Visualization of the attention layers illustrates that the model selects qualitatively informative words.

Cross-lingual sentiment classification (CLSC) seeks to use resources from a source language in order to detect sentiment and classify text in a target language. Almost all research into CLSC has been carried out at sentence and document level, although this level of granularity is often less useful. This paper explores methods for performing aspect-based cross-lingual sentiment classification (aspect-based CLSC) for under-resourced languages. Given the limited nature of parallel data for many languages, we would like to make the most of this resource for our task. We compare zero-shot learning, bilingual word embeddings, stacked denoising autoencoder representations and machine translation techniques for aspect-based CLSC. Each of these approaches requires differing amounts of parallel data. We show that models based on distributed semantics can achieve comparable results to machine translation on aspect-based CLSC and give an analysis of the errors found for each method.

Sarcasm detection is a key task for many natural language processing tasks. In sentiment analysis, for example, sarcasm can flip the polarity of an “apparently positive” sentence and, hence, negatively affect polarity detection performance. To date, most approaches to sarcasm detection have treated the task primarily as a text categorization problem. Sarcasm, however, can be expressed in very subtle ways and requires a deeper understanding of natural language that standard text categorization techniques cannot grasp. In this work, we develop models based on a pre-trained convolutional neural network for extracting sentiment, emotion and personality features for sarcasm detection. Such features, along with the network’s baseline features, allow the proposed models to outperform the state of the art on benchmark datasets. We also address the often ignored generalizability issue of classifying data that have not been seen by the models at learning phase.

NBSVM is one of the most popular methods for text classification and has been widely used as baselines for various text representation approaches. It uses Naive Bayes (NB) feature to weight sparse bag-of-n-grams representation. N-gram captures word order in short context and NB feature assigns more weights to those important words. However, NBSVM suffers from sparsity problem and is reported to be exceeded by newly proposed distributed (dense) text representations learned by neural networks. In this paper, we transfer the n-grams and NB weighting to neural models. We train n-gram embeddings and use NB weighting to guide the neural models to focus on important words. In fact, our methods can be viewed as distributed (dense) counterparts of sparse bag-of-n-grams in NBSVM. We discover that n-grams and NB weighting are also effective in distributed representations. As a result, our models achieve new strong baselines on 9 text classification datasets, e.g. on IMDB dataset, we reach performance of 93.5% accuracy, which exceeds previous state-of-the-art results obtained by deep neural models. All source codes are publicly available at https://github.com/zhezhaoa/neural_BOW_toolkit.

Emotion classification from text typically requires some degree of word-emotion association, either gathered from pre-existing emotion lexicons or calculated using some measure of semantic relatedness. Most emotion lexicons contain a fixed number of emotion categories and provide a rather limited coverage. Current measures of computing semantic relatedness, on the other hand, do not adapt well to the specific task of word-emotion association and therefore, yield average results. In this work, we propose an unsupervised method of learning word-emotion association from large text corpora, called Selective Co-occurrences (SECO), by leveraging the property of mutual exclusivity generally exhibited by emotions. Extensive evaluation, using just one seed word per emotion category, indicates the effectiveness of the proposed approach over three emotion lexicons and two state-of-the-art models of word embeddings on three datasets from different domains.

This work investigates whether the development of ideas in writing can be captured by graph properties derived from the text. Focusing on student essays, we represent the essay as a graph, and encode a variety of graph properties including PageRank as features for modeling essay scores related to quality of development. We demonstrate that our approach improves on a state-of-the-art system on the task of holistic scoring of persuasive essays and on the task of scoring narrative essays along the development dimension.

Sentiment polarity lexicons are key resources for sentiment analysis, and researchers have invested a lot of efforts in their manual creation. However, there has been a recent shift towards automatically extracted lexicons, which are orders of magnitude larger and perform much better. These lexicons are typically mined using bootstrapping, starting from very few seed words whose polarity is given, e.g., 50-60 words, and sometimes even just 5-6. Here we demonstrate that much higher-quality lexicons can be built by starting with hundreds of words and phrases as seeds, especially when they are in-domain. Thus, we combine (i) mid-sized high-quality manually crafted lexicons as seeds and (ii) bootstrapping, in order to build large-scale lexicons.

In this paper, we introduce the task of targeted aspect-based sentiment analysis. The goal is to extract fine-grained information with respect to entities mentioned in user comments. This work extends both aspect-based sentiment analysis – that assumes a single entity per document — and targeted sentiment analysis — that assumes a single sentiment towards a target entity. In particular, we identify the sentiment towards each aspect of one or more entities. As a testbed for this task, we introduce the SentiHood dataset, extracted from a question answering (QA) platform where urban neighbourhoods are discussed by users. In this context units of text often mention several aspects of one or more neighbourhoods. This is the first time that a generic social media platform,i.e. QA, is used for fine-grained opinion mining. Text coming from QA platforms are far less constrained compared to text from review specific platforms which current datasets are based on. We develop several strong baselines, relying on logistic regression and state-of-the-art recurrent neural networks

Research in multi-document summarization has focused on newswire corpora since the early beginnings. However, the newswire genre provides genre-specific features such as sentence position which are easy to exploit in summarization systems. Such easy to exploit genre-specific features are available in other genres as well. We therefore present the new hMDS corpus for multi-document summarization, which contains heterogeneous source documents from multiple text genres, as well as summaries with different lengths. For the construction of the corpus, we developed a novel construction approach which is suited to build large and heterogeneous summarization corpora with little effort. The method reverses the usual process of writing summaries for given source documents: it combines already available summaries with appropriate source documents. In a detailed analysis, we show that our new corpus is significantly different from the homogeneous corpora commonly used, and that it is heterogeneous along several dimensions. Our experimental evaluation using well-known state-of-the-art summarization systems shows that our corpus poses new challenges in the field of multi-document summarization. Last but not least, we make our corpus publicly available to the research community at the corpus web page https://github.com/AIPHES/hMDS.

The search space in grammar-based natural language generation tasks can get very large, which is particularly problematic when generating long utterances or paragraphs. Using surface realization with OpenCCG as an example, we show that we can effectively detect partial solutions (edges) which cannot ultimately be part of a complete sentence because of their syntactic category. Formulating the completion of an edge into a sentence as finding a solution path in a large state-transition system, we demonstrate a connection to AI Planning which is concerned with this kind of problem. We design a compilation from OpenCCG into AI Planning allowing the detection of infeasible edges via AI Planning dead-end detection methods (proving the absence of a solution to the compilation). Our experiments show that this can filter out large fractions of infeasible edges in, and thus benefit the performance of, complex realization processes.

In the age of information exploding, multi-document summarization is attracting particular attention for the ability to help people get the main ideas in a short time. Traditional extractive methods simply treat the document set as a group of sentences while ignoring the global semantics of the documents. Meanwhile, neural document model is effective on representing the semantic content of documents in low-dimensional vectors. In this paper, we propose a document-level reconstruction framework named DocRebuild, which reconstructs the documents with summary sentences through a neural document model and selects summary sentences to minimize the reconstruction error. We also apply two strategies, sentence filtering and beamsearch, to improve the performance of our method. Experimental results on the benchmark datasets DUC 2006 and DUC 2007 show that DocRebuild is effective and outperforms the state-of-the-art unsupervised algorithms.

Sentence compression is a way to perform text simplification and is usually handled in a monolingual setting. In this paper, we study ways to extend sentence compression in a bilingual context, where the goal is to obtain parallel compressions of parallel sentences. This can be beneficial for a series of multilingual natural language processing (NLP) tasks. We compare two ways to take bilingual information into account when compressing parallel sentences. Their efficiency is contrasted on a parallel corpus of News articles.

In Natural Language Generation (NLG), one important limitation is the lack of common benchmarks on which to train, evaluate and compare data-to-text generators. In this paper, we make one step in that direction and introduce a method for automatically creating an arbitrary large repertoire of data units that could serve as input for generation. Using both automated metrics and a human evaluation, we show that the data units produced by our method are both diverse and coherent.

We propose an approach to Named Entity Disambiguation that avoids a problem of standard work on the task (likewise affecting fully supervised, weakly supervised, or distantly supervised machine learning techniques): the treatment of name mentions referring to people with no (or very little) coverage in the textual training data is systematically incorrect. We propose to indirectly take into account the property information for the “non-prominent” name bearers, such as nationality and profession (e.g., for a Canadian law professor named Michael Jackson, with no Wikipedia article, it is very hard to obtain reliable textual training data). The target property information for the entities is directly available from name authority files, or inferrable, e.g., from listings of sportspeople etc. Our proposed approach employs topic modeling to exploit textual training data based on entities sharing the relevant properties. In experiments with a pilot implementation of the general approach, we show that the approach does indeed work well for name/referent pairs with limited textual coverage in the training data.

Distant supervision is an efficient approach that automatically generates labeled data for relation extraction (RE). Traditional distantly supervised RE systems rely heavily on handcrafted features, and hence suffer from error propagation. Recently, a neural network architecture has been proposed to automatically extract features for relation classification. However, this approach follows the traditional expressed-at-least-once assumption, and fails to make full use of information across different sentences. Moreover, it ignores the fact that there can be multiple relations holding between the same entity pair. In this paper, we propose a multi-instance multi-label convolutional neural network for distantly supervised RE. It first relaxes the expressed-at-least-once assumption, and employs cross-sentence max-pooling so as to enable information sharing across different sentences. Then it handles overlapping relations by multi-label learning with a neural network classifier. Experimental results show that our approach performs significantly and consistently better than state-of-the-art methods.

Nowadays, neural networks play an important role in the task of relation classification. By designing different neural architectures, researchers have improved the performance to a large extent in comparison with traditional methods. However, existing neural networks for relation classification are usually of shallow architectures (e.g., one-layer convolutional neural networks or recurrent networks). They may fail to explore the potential representation space in different abstraction levels. In this paper, we propose deep recurrent neural networks (DRNNs) for relation classification to tackle this challenge. Further, we propose a data augmentation method by leveraging the directionality of relations. We evaluated our DRNNs on the SemEval-2010 Task 8, and achieve an F1-score of 86.1%, outperforming previous state-of-the-art recorded results.