COLING 2016 论文列表

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.

In order to apply computational linguistic analyses and pass information to downstream applications, transcriptions of speech obtained via automatic speech recognition (ASR) need to be divided into smaller meaningful units, in a task we refer to as ‘speech-unit (SU) delimitation’. We closely recreate the automatic delimitation system described by Lee and Glass (2012), ‘Sentence detection using multiple annotations’, Proceedings of INTERSPEECH, which combines a prosodic model, language model and speech-unit length model in log-linear fashion. Since state-of-the-art natural language processing (NLP) tools have been developed to deal with written text and its characteristic sentence-like units, SU delimitation helps bridge the gap between ASR and NLP, by normalising spoken data into a more canonical format. Previous work has focused on native speaker recordings; we test the system of Lee and Glass (2012) on non-native speaker (or ‘learner’) data, achieving performance above the state-of-the-art. We also consider alternative evaluation metrics which move away from the idea of a single ‘truth’ in SU delimitation, and frame this work in the context of downstream NLP applications.

In this work we tackle the challenge of identifying rhythmic patterns in poetry written in English. Although poetry is a literary form that makes use standard meters usually repeated among different authors, we will see in this paper how performing such analyses is a difficult task in machine learning due to the unexpected deviations from such standard patterns. After breaking down some examples of classical poetry, we apply a number of NLP techniques for the scansion of poetry, training and testing our systems against a human-annotated corpus. With these experiments, our purpose is establish a baseline of automatic scansion of poetry using NLP tools in a straightforward manner and to raise awareness of the difficulties of this task.

Recent work for learning word representations has applied successfully to many NLP applications, such as sentiment analysis and question answering. However, most of these models assume a single vector per word type without considering polysemy and homonymy. In this paper, we present an extension to the CBOW model which not only improves the quality of embeddings but also makes embeddings suitable for polysemy. It differs from most of the related work in that it learns one semantic center embedding and one context bias instead of training multiple embeddings per word type. Different context leads to different bias which is defined as the weighted average embeddings of local context. Experimental results on similarity task and analogy task show that the word representations learned by the proposed method outperform the competitive baselines.

Previous linguistic research on scientific writing has shown that language use in the scientific domain varies considerably in register and style over time. In this paper we investigate the introduction of information theory inspired features to study long term diachronic change on three levels: lexis, part-of-speech and syntax. Our approach is based on distinguishing between sentences from 19th and 20th century scientific abstracts using supervised classification models. To the best of our knowledge, the introduction of information theoretic features to this task is novel. We show that these features outperform more traditional features, such as token or character n-grams, while leading to more compact models. We present a detailed analysis of feature informativeness in order to gain a better understanding of diachronic change on different linguistic levels.

We propose a hierarchical clustering approach designed to group linguistic features for supervised machine learning that is inspired by variationist linguistics. The method makes it possible to abstract away from the individual feature occurrences by grouping features together that behave alike with respect to the target class, thus providing a new, more general perspective on the data. On the one hand, it reduces data sparsity, leading to quantitative performance gains. On the other, it supports the formation and evaluation of hypotheses about individual choices of linguistic structures. We explore the method using features based on verb subcategorization information and evaluate the approach in the context of the Native Language Identification (NLI) task.

In this paper, we aim to investigate the coordination of interlocutors behavior in different emotional segments. Conversational coordination between the interlocutors is the tendency of speakers to predict and adjust each other accordingly on an ongoing conversation. In order to find such a coordination, we investigated 1) lexical similarities between the speakers in each emotional segments, 2) correlation between the interlocutors using psycholinguistic features, such as linguistic styles, psychological process, personal concerns among others, and 3) relation of interlocutors turn-taking behaviors such as competitiveness. To study the degree of coordination in different emotional segments, we conducted our experiments using real dyadic conversations collected from call centers in which agent’s emotional state include empathy and customer’s emotional states include anger and frustration. Our findings suggest that the most coordination occurs between the interlocutors inside anger segments, where as, a little coordination was observed when the agent was empathic, even though an increase in the amount of non-competitive overlaps was observed. We found no significant difference between anger and frustration segment in terms of turn-taking behaviors. However, the length of pause significantly decreases in the preceding segment of anger where as it increases in the preceding segment of frustration.

We report three user studies in which the Lexical Simplification needs of non-native English speakers are investigated. Our analyses feature valuable new insight on the relationship between the non-natives’ notion of complexity and various morphological, semantic and lexical word properties. Some of our findings contradict long-standing misconceptions about word simplicity. The data produced in our studies consists of 211,564 annotations made by 1,100 volunteers, which we hope will guide forthcoming research on Text Simplification for non-native speakers of English.

Learning syntactic categories is a fundamental task in language acquisition. Previous studies show that co-occurrence patterns of preceding and following words are essential to group words into categories. However, the neighboring words, or frames, are rarely repeated exactly in the data. This creates data sparsity and hampers learning for frame based models. In this work, we propose a paradigmatic representation of word context which uses probable substitutes instead of frames. Our experiments on child-directed speech show that models based on probable substitutes learn more accurate categories with fewer examples compared to models based on frames.

Cyberbullying statistics are shocking, the number of affected young people is increasing dramatically with the affordability of mobile technology devices combined with a growing number of social networks. This paper proposes a framework to analyse Tweets with the goal to identify cyberharassment in social networks as an important step to protect people from cyberbullying. The proposed framework incorporates latent or hidden variables with supervised learning to determine potential bullying cases resembling short blogging type texts such as Tweets. It uses the LIWC2007 - tool that translates Tweet messages into 67 numeric values, representing 67 word categories. The output vectors are then used as features for four different classifiers implemented in Weka. Tests on all four classifiers delivered encouraging predictive capability of Tweet messages. Overall it was found that the use of numeric psychometric values outperformed the same algorithms using both filtered and unfiltered words as features. The best performing algorithms was Random Forest with an F1-value of 0.947 using psychometric features compared to a value of 0.847 for the same algorithm using words as features.

The Dundee Eyetracking Corpus contains eyetracking data collected while native speakers of English and French read newspaper editorial articles. Similar resources for other languages are still rare, especially for languages in which words are not overtly delimited with spaces. This is a report on a project to build an eyetracking corpus for Japanese. Measurements were collected while 24 native speakers of Japanese read excerpts from the Balanced Corpus of Contemporary Written Japanese Texts were presented with or without segmentation (i.e. with or without space at the boundaries between bunsetsu segmentations) and with two types of methodologies (eyetracking and self-paced reading presentation). Readers’ background information including vocabulary-size estimation and Japanese reading-span score were also collected. As an example of the possible uses for the corpus, we also report analyses investigating the phenomena of anti-locality.

Personal writings have inspired researchers in the fields of linguistics and psychology to study the relationship between language and culture to better understand the psychology of people across different cultures. In this paper, we explore this relation by developing cross-cultural word models to identify words with cultural bias – i.e., words that are used in significantly different ways by speakers from different cultures. Focusing specifically on two cultures: United States and Australia, we identify a set of words with significant usage differences, and further investigate these words through feature analysis and topic modeling, shedding light on the attributes of language that contribute to these differences.

Besides providing the relevant information, amusing users has been an important role of the web. Many web sites provide serendipitous (unexpected but relevant) information to draw user traffic. In this paper, we study the representative scenario of mining an amusing quiz. An existing approach leverages a knowledge base to mine an unexpected property then find quiz questions on such property, based on prototype theory in cognitive science. However, existing deterministic model is vulnerable to noise in the knowledge base. Therefore, we instead propose to leverage probabilistic approach to build a prototype that can overcome noise. Our extensive empirical study shows that our approach not only significantly outperforms baselines by 0.06 in accuracy, and 0.11 in serendipity but also shows higher relevance than the traditional relevance-pursuing baseline using TF-IDF.

For automatic chatting systems, it is indeed a great challenge to reply the given query considering the conversation history, rather than based on the query only. This paper proposes a deep neural network to address the context-aware response ranking problem by end-to-end learning, so as to help to select conversationally relevant candidate. By combining the multi-column convolutional layer and the recurrent layer, our model is able to model the semantics of the utterance sequence by grasping the semantic clue within the conversation, on the basis of the effective representation for each sentence. Especially, the network utilizes attention pooling to further emphasis the importance of essential words in conversations, thus the representations of contexts tend to be more meaningful and the performance of candidate ranking is notably improved. Meanwhile, due to the adoption of attention pooling, it is possible to visualize the semantic clues. The experimental results on the large amount of conversation data from social media have shown that our approach is promising for quantifying the conversational relevance of responses, and indicated its good potential for building practical IR based chat-bots.

Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently. Most existing approaches treat the given knowledge base as a set of triplets, each of whose representation is then learned separately. However, as a fact, triples are connected and depend on each other. In this paper, we propose a graph aware knowledge embedding method (GAKE), which formulates knowledge base as a directed graph, and learns representations for any vertices or edges by leveraging the graph’s structural information. We introduce three types of graph context for embedding: neighbor context, path context, and edge context, each reflects properties of knowledge from different perspectives. We also design an attention mechanism to learn representative power of different vertices or edges. To validate our method, we conduct several experiments on two tasks. Experimental results suggest that our method outperforms several state-of-art knowledge embedding models.

Compound words with unmarked word boundaries are problematic for many tasks in NLP and computational linguistics, including information extraction, machine translation, and syllabification. This paper introduces a simple, proof-of-concept language modeling approach to automatic compound segmentation, as applied to Finnish. This approach utilizes an off-the-shelf morphological analyzer to split training words into their constituent morphemes. A language model is subsequently trained on ngrams composed of morphemes, morpheme boundaries, and word boundaries. Linguistic constraints are then used to weed out phonotactically ill-formed segmentations, thereby allowing the language model to select the best grammatical segmentation. This approach achieves an accuracy of ~97%.

Current methods for word alignment require considerable amounts of parallel text to deliver accurate results, a requirement which is met only for a small minority of the world’s approximately 7,000 languages. We show that by jointly performing word alignment and annotation transfer in a novel Bayesian model, alignment accuracy can be improved for language pairs where annotations are available for only one of the languages—a finding which could facilitate the study and processing of a vast number of low-resource languages. We also present an evaluation where our method is used to perform single-source and multi-source part-of-speech transfer with 22 translations of the same text in four different languages. This allows us to quantify the considerable variation in accuracy depending on the specific source text(s) used, even with different translations into the same language.

Keystroke dynamics have been extensively used in psycholinguistic and writing research to gain insights into cognitive processing. But do keystroke logs contain actual signal that can be used to learn better natural language processing models? We postulate that keystroke dynamics contain information about syntactic structure that can inform shallow syntactic parsing. To test this hypothesis, we explore labels derived from keystroke logs as auxiliary task in a multi-task bidirectional Long Short-Term Memory (bi-LSTM). Our results show promising results on two shallow syntactic parsing tasks, chunking and CCG supertagging. Our model is simple, has the advantage that data can come from distinct sources, and produces models that are significantly better than models trained on the text annotations alone.

Semantic role labeling (SRL) is the task of identifying and labeling predicate-argument structures in sentences with semantic frame and role labels. A known challenge in SRL is the large number of low-frequency exceptions in training data, which are highly context-specific and difficult to generalize. To overcome this challenge, we propose the use of instance-based learning that performs no explicit generalization, but rather extrapolates predictions from the most similar instances in the training data. We present a variant of k-nearest neighbors (kNN) classification with composite features to identify nearest neighbors for SRL. We show that high-quality predictions can be derived from a very small number of similar instances. In a comparative evaluation we experimentally demonstrate that our instance-based learning approach significantly outperforms current state-of-the-art systems on both in-domain and out-of-domain data, reaching F1-scores of 89,28% and 79.91% respectively.