COLING 2016 论文列表

In this paper, we investigate the annotation projection of semantic units in a practical setting. Previous approaches have focused on using parallel corpora for semantic transfer. We evaluate an alternative approach using loosely parallel corpora that does not require the corpora to be exact translations of each other. We developed a method that transfers semantic annotations from one language to another using sentences aligned by entities, and we extended it to include alignments by entity-like linguistic units. We conducted our experiments on a large scale using the English, Swedish, and French language editions of Wikipedia. Our results show that the annotation projection using entities in combination with loosely parallel corpora provides a viable approach to extending previous attempts. In addition, it allows the generation of proposition banks upon which semantic parsers can be trained.

This paper describes our construction of named-entity recognition (NER) systems in two Western Iranian languages, Sorani Kurdish and Tajik, as a part of a pilot study of “Linguistic Rapid Response” to potential emergency humanitarian relief situations. In the absence of large annotated corpora, parallel corpora, treebanks, bilingual lexica, etc., we found the following to be effective: exploiting distributional regularities in monolingual data, projecting information across closely related languages, and utilizing human linguist judgments. We show promising results on both a four-month exercise in Sorani and a two-day exercise in Tajik, achieved with minimal annotation costs.

This paper investigates the effectiveness of 65 cohesion-based variables that are commonly used in the literature as predictive features to assess text readability. We evaluate the efficiency of these variables across narrative and informative texts intended for an audience of L2 French learners. In our experiments, we use a French corpus that has been both manually and automatically annotated as regards to co-reference and anaphoric chains. The efficiency of the 65 variables for readability is analyzed through a correlational analysis and some modelling experiments.

In this paper we discuss three key points related to error detection (ED) in learners’ English. We focus on content word ED as one of the most challenging tasks in this area, illustrating our claims on adjective–noun (AN) combinations. In particular, we (1) investigate the role of context in accurately capturing semantic anomalies and implement a system based on distributional topic coherence, which achieves state-of-the-art accuracy on a standard test set; (2) thoroughly investigate our system’s performance across individual adjective classes, concluding that a class-dependent approach is beneficial to the task; (3) discuss the data size bottleneck in this area, and highlight the challenges of automatic error generation for content words.

This paper presents a new memory-bounded left-corner parsing model for unsupervised raw-text syntax induction, using unsupervised hierarchical hidden Markov models (UHHMM). We deploy this algorithm to shed light on the extent to which human language learners can discover hierarchical syntax through distributional statistics alone, by modeling two widely-accepted features of human language acquisition and sentence processing that have not been simultaneously modeled by any existing grammar induction algorithm: (1) a left-corner parsing strategy and (2) limited working memory capacity. To model realistic input to human language learners, we evaluate our system on a corpus of child-directed speech rather than typical newswire corpora. Results beat or closely match those of three competing systems.

Topics generated by topic models are typically represented as list of terms. To reduce the cognitive overhead of interpreting these topics for end-users, we propose labelling a topic with a succinct phrase that summarises its theme or idea. Using Wikipedia document titles as label candidates, we compute neural embeddings for documents and words to select the most relevant labels for topics. Comparing to a state-of-the-art topic labelling system, our methodology is simpler, more efficient and finds better topic labels.

On microblogging services, people usually use hashtags to mark microblogs, which have a specific theme or content, making them easier for users to find. Hence, how to automatically recommend hashtags for microblogs has received much attention in recent years. Previous deep neural network-based hashtag recommendation approaches converted the task into a multi-class classification problem. However, most of these methods only took the microblog itself into consideration. Motivated by the intuition that the history of users should impact the recommendation procedure, in this work, we extend end-to-end memory networks to perform this task. We incorporate the histories of users into the external memory and introduce a hierarchical attention mechanism to select more appropriate histories. To train and evaluate the proposed method, we also construct a dataset based on microblogs collected from Twitter. Experimental results demonstrate that the proposed methods can significantly outperform state-of-the-art methods. By incorporating the hierarchical attention mechanism, the relative improvement in the proposed method over the state-of-the-art method is around 67.9% in the F1-score.

The goal of keyphrase extraction is to automatically identify the most salient phrases from documents. The technique has a wide range of applications such as rendering a quick glimpse of a document, or extracting key content for further use. While previous work often assumes keyphrases are a static property of a given documents, in many applications, the appropriate set of keyphrases that should be extracted depends on the set of documents that are being considered together. In particular, good keyphrases should not only accurately describe the content of a document, but also reveal what discriminates it from the other documents. In this paper, we study this problem of extracting discriminative keyphrases. In particularly, we propose to use the hierarchical semantic structure between candidate keyphrases to promote keyphrases that have the right level of specificity to clearly distinguish the target document from others. We show that such knowledge can be used to construct better discriminative keyphrase extraction systems that do not assume a static, fixed set of keyphrases for a document. We show how this helps identify key expertise of authors from their papers, as well as competencies covered by online courses within different domains.

Historical texts are challenging for natural language processing because they differ linguistically from modern texts and because of their lack of orthographical and grammatical standardisation. We use a character-level neural network to build a part-of-speech (POS) tagger that can process historical data directly without requiring a separate spelling normalisation stage. Its performance in a Swedish verb identification and a German POS tagging task is similar to that of a two-stage model. We analyse the performance of this tagger and a more traditional baseline system, discuss some of the remaining problems for tagging historical data and suggest how the flexibility of our neural tagger could be exploited to address diachronic divergences in morphology and syntax in early modern Swedish with the help of data from closely related languages.

We describe and evaluate a character-level tagger for language-independent Named Entity Recognition (NER). Instead of words, a sentence is represented as a sequence of characters. The model consists of stacked bidirectional LSTMs which inputs characters and outputs tag probabilities for each character. These probabilities are then converted to consistent word level named entity tags using a Viterbi decoder. We are able to achieve close to state-of-the-art NER performance in seven languages with the same basic model using only labeled NER data and no hand-engineered features or other external resources like syntactic taggers or Gazetteers.

We investigate using Adaptor Grammars for unsupervised morphological segmentation. Using six development languages, we investigate in detail different grammars, the use of morphological knowledge from outside sources, and the use of a cascaded architecture. Using cross-validation on our development languages, we propose a system which is language-independent. We show that it outperforms two state-of-the-art systems on 5 out of 6 languages.

Misuse of Chinese prepositions is one of common word usage errors in grammatical error diagnosis. In this paper, we adopt the Chinese Gigaword corpus and HSK corpus as L1 and L2 corpora, respectively. We explore gated recurrent neural network model (GRU), and an ensemble of GRU model and maximum entropy language model (GRU-ME) to select the best preposition from 43 candidates for each test sentence. The experimental results show the advantage of the GRU models over simple RNN and n-gram models. We further analyze the effectiveness of linguistic information such as word boundary and part-of-speech tag in this task.

We study the problem of detecting sentences describing adverse drug reactions (ADRs) and frame the problem as binary classification. We investigate different neural network (NN) architectures for ADR classification. In particular, we propose two new neural network models, Convolutional Recurrent Neural Network (CRNN) by concatenating convolutional neural networks with recurrent neural networks, and Convolutional Neural Network with Attention (CNNA) by adding attention weights into convolutional neural networks. We evaluate various NN architectures on a Twitter dataset containing informal language and an Adverse Drug Effects (ADE) dataset constructed by sampling from MEDLINE case reports. Experimental results show that all the NN architectures outperform the traditional maximum entropy classifiers trained from n-grams with different weighting strategies considerably on both datasets. On the Twitter dataset, all the NN architectures perform similarly. But on the ADE dataset, CNN performs better than other more complex CNN variants. Nevertheless, CNNA allows the visualisation of attention weights of words when making classification decisions and hence is more appropriate for the extraction of word subsequences describing ADRs.

University students in the United States are routinely asked to provide feedback on the quality of the instruction they have received. Such feedback is widely used by university administrators to evaluate teaching ability, despite growing evidence that students assign lower numerical scores to women and people of color, regardless of the actual quality of instruction. In this paper, we analyze students’ written comments on faculty evaluation forms spanning eight years and five STEM disciplines in order to determine whether open-ended comments reflect these same biases. First, we apply sentiment analysis techniques to the corpus of comments to determine the overall affect of each comment. We then use this information, in combination with other features, to explore whether there is bias in how students describe their instructors. We show that while the gender of the evaluated instructor does not seem to affect students’ expressed level of overall satisfaction with their instruction, it does strongly influence the language that they use to describe their instructors and their experience in class.

We present a linguistic analysis of a set of English and Spanish verb+noun combinations (VNCs), and a method to use this information to improve VNC identification. Firstly, a sample of frequent VNCs are analysed in-depth and tagged along lexico-semantic and morphosyntactic dimensions, obtaining satisfactory inter-annotator agreement scores. Then, a VNC identification experiment is undertaken, where the analysed linguistic data is combined with chunking information and syntactic dependencies. A comparison between the results of the experiment and the results obtained by a basic detection method shows that VNC identification can be greatly improved by using linguistic information, as a large number of additional occurrences are detected with high precision.

The modifications that foreign loanwords undergo when adapted into Japanese have been the subject of much study in linguistics. The scholarly interest of the topic can be attributed to the fact that Japanese loanwords undergo a complex series of phonological adaptations, something which has been puzzling scholars for decades. While previous studies of Japanese loanword accommodation have focused on specific phonological phenomena of limited scope, the current study leverages computational methods to provide a more complete description of all the sound changes that occur when adopting English words into Japanese. To investigate this, we have developed a parallel corpus of 250 English transcriptions and their respective Japanese equivalents. These words were then used to develop a wide-coverage finite state transducer based phonological grammar that mimics the behavior of the Japanese adaption process. By developing rules with the goal of accounting completely for a large number of borrowing and analyzing forms mistakenly generated by the system, we discovered an internal inconsistency inside the loanword phonology of the Japanese language, something arguably underestimated by previous studies. The result of the investigation suggests that there are multiple ‘dimensions’ that shape the output form of the current Japanese loanwords. These dimensions include orthography, phonetics, and historical changes.

Linguistic typology provides features that have a potential of uncovering deep phylogenetic relations among the world’s languages. One of the key challenges in using typological features for phylogenetic inference is that horizontal (spatial) transmission obscures vertical (phylogenetic) signals. In this paper, we characterize typological features with respect to the relative strength of vertical and horizontal transmission. To do this, we first construct (1) a spatial neighbor graph of languages and (2) a phylogenetic neighbor graph by collapsing known language families. We then develop an autologistic model that predicts a feature’s distribution from these two graphs. In the experiments, we managed to separate vertically and/or horizontally stable features from unstable ones, and the results are largely consistent with previous findings.

We propose a new method of automatically extracting learner errors from parallel English as a Second Language (ESL) sentences in an effort to regularise annotation formats and reduce inconsistencies. Specifically, given an original and corrected sentence, our method first uses a linguistically enhanced alignment algorithm to determine the most likely mappings between tokens, and secondly employs a rule-based function to decide which alignments should be merged. Our method beats all previous approaches on the tested datasets, achieving state-of-the-art results for automatic error extraction.

Finding authentic examples of grammatical constructions is central in constructionist approaches to linguistics, language processing, and second language learning. In this paper, we address this problem as an information retrieval (IR) task. To facilitate research in this area, we built a benchmark collection by annotating the occurrences of six constructions in a Swedish corpus. Furthermore, we implemented a simple and flexible retrieval system for finding construction occurrences, in which the user specifies a ranking function using lexical-semantic similarities (lexicon-based or distributional). The system was evaluated using standard IR metrics on the new benchmark, and we saw that lexical-semantical rerankers improve significantly over a purely surface-oriented system, but must be carefully tailored for each individual construction.