COLING 2016 Papers

Identifying events of a specific type is a challenging task as events in texts are described in numerous and diverse ways. Aiming to resolve high complexities of event descriptions, previous work (Huang and Riloff, 2013) proposes multi-faceted event recognition and a bootstrapping method to automatically acquire both event facet phrases and event expressions from unannotated texts. However, to ensure high quality of learned phrases, this method is constrained to only learn phrases that match certain syntactic structures. In this paper, we propose a bilingual structure projection algorithm that explores linguistic divergences between two languages (Chinese and English) and mines new phrases with new syntactic structures, which have been ignored in the previous work. Experiments show that our approach can successfully find novel event phrases and structures, e.g., phrases headed by nouns. Furthermore, the newly mined phrases are capable of recognizing additional event descriptions and increasing the recall of event recognition.

Community Question Answering (cQA) forums have become a popular medium for soliciting direct answers to specific questions of users from experts or other experienced users on a given topic. However, for a given question, users sometimes have to sift through a large number of low-quality or irrelevant answers to find out the answer which satisfies their information need. To alleviate this, the problem of Answer Quality Prediction (AQP) aims to predict the quality of an answer posted in response to a forum question. Current AQP systems either learn models using - a) various hand-crafted features (HCF) or b) Deep Learning (DL) techniques which automatically learn the required feature representations. In this paper, we propose a novel approach for AQP known as - “Deep Feature Fusion Network (DFFN)” which combines the advantages of both hand-crafted features and deep learning based systems. Given a question-answer pair along with its metadata, the DFFN architecture independently - a) learns features from the Deep Neural Network (DNN) and b) computes hand-crafted features using various external resources and then combines them using a fully connected neural network trained to predict the final answer quality. DFFN is end-end differentiable and trained as a single system. We propose two different DFFN architectures which vary mainly in the way they model the input question/answer pair - DFFN-CNN uses a Convolutional Neural Network (CNN) and DFFN-BLNA uses a Bi-directional LSTM with Neural Attention (BLNA). Both these proposed variants of DFFN (DFFN-CNN and DFFN-BLNA) achieve state-of-the-art performance on the standard SemEval-2015 and SemEval-2016 benchmark datasets and outperforms baseline approaches which individually employ either HCF or DL based techniques alone.

In this paper, we propose a new decoding method for phrase-based statistical machine translation which directly uses multiple preordering candidates as a graph structure. Compared with previous phrase-based decoding methods, our method is based on a simple left-to-right dynamic programming in which no decoding-time reordering is performed. As a result, its runtime is very fast and implementing the algorithm becomes easy. Our system does not depend on specific preordering methods as long as they output multiple preordering candidates, and it is trivial to employ existing preordering methods into our system. In our experiments for translating diverse 11 languages into English, the proposed method outperforms conventional phrase-based decoder in terms of translation qualities under comparable or faster decoding time.

In this paper we describe and evaluate methods to perform ensemble prediction in neural machine translation (NMT). We compare two methods of ensemble set induction: sampling parameter initializations for an NMT system, which is a relatively established method in NMT (Sutskever et al., 2014), and NMT systems translating from different source languages into the same target language, i.e., multi-source ensembles, a method recently introduced by Firat et al. (2016). We are motivated by the observation that for different language pairs systems make different types of mistakes. We propose several methods with different degrees of parameterization to combine individual predictions of NMT systems so that they mutually compensate for each other’s mistakes and improve overall performance. We find that the biggest improvements can be obtained from a context-dependent weighting scheme for multi-source ensembles. This result offers stronger support for the linguistic motivation of using multi-source ensembles than previous approaches. Evaluation is carried out for German and French into English translation. The best multi-source ensemble method achieves an improvement of up to 2.2 BLEU points over the strongest single-source ensemble baseline, and a 2 BLEU improvement over a multi-source ensemble baseline.

Evaluation of machine translation (MT) into morphologically rich languages (MRL) has not been well studied despite posing many challenges. In this paper, we explore the use of embeddings obtained from different levels of lexical and morpho-syntactic linguistic analysis and show that they improve MT evaluation into an MRL. Specifically we report on Arabic, a language with complex and rich morphology. Our results show that using a neural-network model with different input representations produces results that clearly outperform the state-of-the-art for MT evaluation into Arabic, by almost over 75% increase in correlation with human judgments on pairwise MT evaluation quality task. More importantly, we demonstrate the usefulness of morpho-syntactic representations to model sentence similarity for MT evaluation and address complex linguistic phenomena of Arabic.

Neural network training has been shown to be advantageous in many natural language processing applications, such as language modelling or machine translation. In this paper, we describe in detail a novel domain adaptation mechanism in neural network training. Instead of learning and adapting the neural network on millions of training sentences – which can be very time-consuming or even infeasible in some cases – we design a domain adaptation gating mechanism which can be used in recurrent neural networks and quickly learn the out-of-domain knowledge directly from the word vector representations with little speed overhead. In our experiments, we use the recurrent neural network language model (LM) as a case study. We show that the neural LM perplexity can be reduced by 7.395 and 12.011 using the proposed domain adaptation mechanism on the Penn Treebank and News data, respectively. Furthermore, we show that using the domain-adapted neural LM to re-rank the statistical machine translation n-best list on the French-to-English language pair can significantly improve translation quality.

Determining the intended sense of words in text – word sense disambiguation (WSD) – is a long-standing problem in natural language processing. Recently, researchers have shown promising results using word vectors extracted from a neural network language model as features in WSD algorithms. However, a simple average or concatenation of word vectors for each word in a text loses the sequential and syntactic information of the text. In this paper, we study WSD with a sequence learning neural net, LSTM, to better capture the sequential and syntactic patterns of the text. To alleviate the lack of training data in all-words WSD, we employ the same LSTM in a semi-supervised label propagation classifier. We demonstrate state-of-the-art results, especially on verbs.

As time passes words can acquire meanings they did not previously have, such as the ‘twitter post’ usage of ‘tweet’. We address how this can be detected from time-stamped raw text. We propose a generative model with senses dependent on times and context words dependent on senses but otherwise eternal, and a Gibbs sampler for estimation. We obtain promising parameter estimates for positive (resp. negative) cases of known sense emergence (resp non-emergence) and adapt the ‘pseudo-word’ technique (Schutze, 1992) to give a novel further evaluation via ‘pseudo-neologisms’. The question of ground-truth is also addressed and a technique proposed to locate an emergence date for evaluation purposes.

Hypernym-hyponym (“is-a”) relations are key components in taxonomies, object hierarchies and knowledge graphs. While there is abundant research on is-a relation extraction in English, it still remains a challenge to identify such relations from Chinese knowledge sources accurately due to the flexibility of language expression. In this paper, we introduce a weakly supervised framework to extract Chinese is-a relations from user generated categories. It employs piecewise linear projection models trained on a Chinese taxonomy and an iterative learning algorithm to update models incrementally. A pattern-based relation selection method is proposed to prevent “semantic drift” in the learning process using bi-criteria optimization. Experimental results illustrate that the proposed approach outperforms state-of-the-art methods.

Most conventional sentence similarity methods only focus on similar parts of two input sentences, and simply ignore the dissimilar parts, which usually give us some clues and semantic meanings about the sentences. In this work, we propose a model to take into account both the similarities and dissimilarities by decomposing and composing lexical semantics over sentences. The model represents each word as a vector, and calculates a semantic matching vector for each word based on all words in the other sentence. Then, each word vector is decomposed into a similar component and a dissimilar component based on the semantic matching vector. After this, a two-channel CNN model is employed to capture features by composing the similar and dissimilar components. Finally, a similarity score is estimated over the composed feature vectors. Experimental results show that our model gets the state-of-the-art performance on the answer sentence selection task, and achieves a comparable result on the paraphrase identification task.

Several recent studies have shown that eye movements during reading provide information about grammatical and syntactic processing, which can assist the induction of NLP models. All these studies have been limited to English, however. This study shows that gaze and part of speech (PoS) correlations largely transfer across English and French. This means that we can replicate previous studies on gaze-based PoS tagging for French, but also that we can use English gaze data to assist the induction of French NLP models.

Light verb constructions (LVC) in Hindi are highly productive. If we can distinguish a case such as nirnay lenaa ‘decision take; decide’ from an ordinary verb-argument combination kaagaz lenaa ‘paper take; take (a) paper’,it has been shown to aid NLP applications such as parsing (Begum et al., 2011) and machine translation (Pal et al., 2011). In this paper, we propose an LVC identification system using language specific features for Hindi which shows an improvement over previous work(Begum et al., 2011). To build our system, we carry out a linguistic analysis of Hindi LVCs using Hindi Treebank annotations and propose two new features that are aimed at capturing the diversity of Hindi LVCs in the corpus. We find that our model performs robustly across a diverse range of LVCs and our results underscore the importance of semantic features, which is in keeping with the findings for English. Our error analysis also demonstrates that our classifier can be used to further refine LVC annotations in the Hindi Treebank and make them more consistent across the board.

We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles that faced by human language learners who need to discover both structure and meaning from noisy and ambiguous data across modalities. We show that our model indeed learns to predict features of the visual context given phonetically transcribed image descriptions, and show that it represents linguistic information in a hierarchy of levels: lower layers in the stack are comparatively more sensitive to form, whereas higher layers are more sensitive to meaning.

In recent years linguistic typologies, which classify the world’s languages according to their functional and structural properties, have been widely used to support multilingual NLP. While the growing importance of typologies in supporting multilingual tasks has been recognised, no systematic survey of existing typological resources and their use in NLP has been published. This paper provides such a survey as well as discussion which we hope will both inform and inspire future work in the area.

Compositional distributional semantic models (CDSMs) have successfully been applied to the task of predicting the meaning of a range of linguistic constructions. Their performance on semi-compositional word formation process of (morphological) derivation, however, has been extremely variable, with no large-scale empirical investigation to date. This paper fills that gap, performing an analysis of CDSM predictions on a large dataset (over 30,000 German derivationally related word pairs). We use linear regression models to analyze CDSM performance and obtain insights into the linguistic factors that influence how predictable the distributional context of a derived word is going to be. We identify various such factors, notably part of speech, argument structure, and semantic regularity.

We present a successful collaboration of word embeddings and co-training to tackle in the most difficult test case of semantic role labeling: predicting out-of-domain and unseen semantic frames. Despite the fact that co-training is a successful traditional semi-supervised method, its application in SRL is very limited especially when a huge amount of labeled data is available. In this work, co-training is used together with word embeddings to improve the performance of a system trained on a large training dataset. We also introduce a semantic role labeling system with a simple learning architecture and effective inference that is easily adaptable to semi-supervised settings with new training data and/or new features. On the out-of-domain testing set of the standard benchmark CoNLL 2009 data our simple approach achieves high performance and improves state-of-the-art results.

This paper describes a unified neural architecture for identifying and classifying multi-typed semantic relations between words in a sentence. We investigate two typical and well-studied tasks: semantic role labeling (SRL) which identifies the relations between predicates and arguments, and relation classification (RC) which focuses on the relation between two entities or nominals. While mostly studied separately in prior work, we show that the two tasks can be effectively connected and modeled using a general architecture. Experiments on CoNLL-2009 benchmark datasets show that our SRL models significantly outperform state-of-the-art approaches. Our RC models also yield competitive performance with the best published records. Furthermore, we show that the two tasks can be trained jointly with multi-task learning, resulting in additive significant improvements for SRL.

Semantic relation classification remains a challenge in natural language processing. In this paper, we introduce a hierarchical recurrent neural network that is capable of extracting information from raw sentences for relation classification. Our model has several distinctive features: (1) Each sentence is divided into three context subsequences according to two annotated nominals, which allows the model to encode each context subsequence independently so as to selectively focus as on the important context information; (2) The hierarchical model consists of two recurrent neural networks (RNNs): the first one learns context representations of the three context subsequences respectively, and the second one computes semantic composition of these three representations and produces a sentence representation for the relationship classification of the two nominals. (3) The attention mechanism is adopted in both RNNs to encourage the model to concentrate on the important information when learning the sentence representations. Experimental results on the SemEval-2010 Task 8 dataset demonstrate that our model is comparable to the state-of-the-art without using any hand-crafted features.

Identification of Multi-Word Expressions (MWEs) lies at the heart of many natural language processing applications. In this research, we deal with a particular type of Hebrew MWEs, Verb-Noun MWEs (VN-MWEs), which combine a verb and a noun with or without other words. Most prior work on MWEs classification focused on linguistic and statistical information. In this paper, we claim that it is essential to utilize semantic information. To this end, we propose a semantically motivated indicator for classifying VN-MWE and define features that are related to various semantic spaces and combine them as features in a supervised classification framework. We empirically demonstrate that our semantic feature set yields better performance than the common linguistic and statistical feature sets and that combining semantic features contributes to the VN-MWEs identification task.