scispace - formally typeset
Search or ask a question

Showing papers on "Phrase published in 2015"


Proceedings ArticleDOI
07 Dec 2015
TL;DR: This paper presents Flickr30K Entities, which augments the 158k captions from Flickr30k with 244k coreference chains linking mentions of the same entities in images, as well as 276k manually annotated bounding boxes corresponding to each entity, essential for continued progress in automatic image description and grounded language understanding.
Abstract: The Flickr30k dataset has become a standard benchmark for sentence-based image description. This paper presents Flickr30k Entities, which augments the 158k captions from Flickr30k with 244k coreference chains linking mentions of the same entities in images, as well as 276k manually annotated bounding boxes corresponding to each entity. Such annotation is essential for continued progress in automatic image description and grounded language understanding. We present experiments demonstrating the usefulness of our annotations for text-to-image reference resolution, or the task of localizing textual entity mentions in an image, and for bidirectional image-sentence retrieval. These experiments confirm that we can further improve the accuracy of state-of-the-art retrieval methods by training with explicit region-to-phrase correspondence, but at the same time, they show that accurately inferring this correspondence given an image and a caption remains really challenging.

1,027 citations


Posted Content
TL;DR: C-LSTM is a novel and unified model for sentence representation and text classification that outperforms both CNN and LSTM and can achieve excellent performance on these tasks.
Abstract: Neural network models have been demonstrated to be capable of achieving remarkable performance in sentence and document modeling. Convolutional neural network (CNN) and recurrent neural network (RNN) are two mainstream architectures for such modeling tasks, which adopt totally different ways of understanding natural languages. In this work, we combine the strengths of both architectures and propose a novel and unified model called C-LSTM for sentence representation and text classification. C-LSTM utilizes CNN to extract a sequence of higher-level phrase representations, and are fed into a long short-term memory recurrent neural network (LSTM) to obtain the sentence representation. C-LSTM is able to capture both local features of phrases as well as global and temporal sentence semantics. We evaluate the proposed architecture on sentiment classification and question classification tasks. The experimental results show that the C-LSTM outperforms both CNN and LSTM and can achieve excellent performance on these tasks.

645 citations


Posted Content
TL;DR: This paper presents Flickr30K Entities, which augments the 158k captions from Flickr30k with 244k coreference chains, linking mentions of the same entities across different captions for the same image, and associating them with 276k manually annotated bounding boxes.
Abstract: The Flickr30k dataset has become a standard benchmark for sentence-based image description. This paper presents Flickr30k Entities, which augments the 158k captions from Flickr30k with 244k coreference chains, linking mentions of the same entities across different captions for the same image, and associating them with 276k manually annotated bounding boxes. Such annotations are essential for continued progress in automatic image description and grounded language understanding. They enable us to define a new benchmark for localization of textual entity mentions in an image. We present a strong baseline for this task that combines an image-text embedding, detectors for common objects, a color classifier, and a bias towards selecting larger objects. While our baseline rivals in accuracy more complex state-of-the-art models, we show that its gains cannot be easily parlayed into improvements on such tasks as image-sentence retrieval, thus underlining the limitations of current methods and the need for further research.

356 citations


Book ChapterDOI
TL;DR: In this article, an attention mechanism is used to reconstruct a given phrase by reconstructing the given phrase using an attention loss, which can be either latent or optimized directly for ground-truth spatial localization.
Abstract: Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth spatial localization of phrases, thus it is desirable to learn from data with no or little grounding supervision. We propose a novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly. During training our approach encodes the phrase using a recurrent network language model and then learns to attend to the relevant image region in order to reconstruct the input phrase. At test time, the correct attention, i.e., the grounding, is evaluated. If grounding supervision is available it can be directly applied via a loss over the attention mechanism. We demonstrate the effectiveness of our approach on the Flickr 30k Entities and ReferItGame datasets with different levels of supervision, ranging from no supervision over partial supervision to full supervision. Our supervised variant improves by a large margin over the state-of-the-art on both datasets.

346 citations


Journal ArticleDOI
TL;DR: This work proposes models to leverage the phrase pairs from the Paraphrase Database to build parametric paraphrase models that score paraphrase pairs more accurately than the PPDB’s internal scores while simultaneously improving its coverage.
Abstract: The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, due to the heuristic nature of the confidences and its necessarily incomplete coverage. We propose models to leverage the phrase pairs from the PPDB to build parametric paraphrase models that score paraphrase pairs more accurately than the PPDB’s internal scores while simultaneously improving its coverage. They allow for learning phrase embeddings as well as improved word embeddings. Moreover, we introduce two new, manually annotated datasets to evaluate short-phrase paraphrasing models. Using our paraphrase model trained using PPDB, we achieve state-of-the-art results on standard word and bigram similarity tasks and beat strong baselines on our new short phrase paraphrase tasks.

272 citations


Proceedings ArticleDOI
01 Jul 2015
TL;DR: Long ShortTerm Memory (LSTM) recurrent network for twitter sentiment prediction is introduced, with the help of gates and constant error carousels in the memory block structure, to handle interactions between words through a flexible compositional function.
Abstract: In this paper, we introduce Long ShortTerm Memory (LSTM) recurrent network for twitter sentiment prediction. With the help of gates and constant error carousels in the memory block structure, the model could handle interactions between words through a flexible compositional function. Experiments on a public noisy labelled data show that our model outperforms several feature-engineering approaches, with the result comparable to the current best data-driven technique. According to the evaluation on a generated negation phrase test set, the proposed architecture doubles the performance of non-neural model based on bag-of-word features. Furthermore, words with special functions (such as negation and transition) are distinguished and the dissimilarities of words with opposite sentiment are magnified. An interesting case study on negation expression processing shows a promising potential of the architecture dealing with complex sentiment phrases.

248 citations


Proceedings ArticleDOI
01 Sep 2015
TL;DR: A new method is presented that takes both dependency and constituent trees of a sentence into account and significantly outperforms previous methods to identify sentiment of an aspect of an entity.
Abstract: This paper presents a new method to identify sentiment of an aspect of an entity. It is an extension of RNN (Recursive Neural Network) that takes both dependency and constituent trees of a sentence into account. Results of an experiment show that our method significantly outperforms previous methods.

241 citations


Proceedings ArticleDOI
01 Sep 2015
TL;DR: The results show that non-expert annotators can produce high quality QA-SRL data, and also establish baseline performance levels for future work on this task, and introduce simple classifierbased models for predicting which questions to ask and what their answers should be.
Abstract: This paper introduces the task of questionanswer driven semantic role labeling (QA-SRL), where question-answer pairs are used to represent predicate-argument structure. For example, the verb “introduce” in the previous sentence would be labeled with the questions “What is introduced?”, and “What introduces something?”, each paired with the phrase from the sentence that gives the correct answer. Posing the problem this way allows the questions themselves to define the set of possible roles, without the need for predefined frame or thematic role ontologies. It also allows for scalable data collection by annotators with very little training and no linguistic expertise. We gather data in two domains, newswire text and Wikipedia articles, and introduce simple classifierbased models for predicting which questions to ask and what their answers should be. Our results show that non-expert annotators can produce high quality QA-SRL data, and also establish baseline performance levels for future work on this task.

222 citations


Proceedings ArticleDOI
28 Feb 2015
TL;DR: This paper benchmarks recursive neural models against sequential recurrent neural models, enforcing applesto-apples comparison as much as possible, and introduces a method for allowing recurrent models to achieve similar performance: breaking long sentences into clause-like units at punctuation and processing them separately before combining.
Abstract: Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. However there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is appropriate. In this paper, we benchmark recursive neural models against sequential recurrent neural models, enforcing applesto-apples comparison as much as possible. We investigate 4 tasks: (1) sentiment classification at the sentence level and phrase level; (2) matching questions to answerphrases; (3) discourse parsing; (4) semantic relation extraction. Our goal is to understand better when, and why, recursive models can outperform simpler models. We find that recursive models help mainly on tasks (like semantic relation extraction) that require longdistance connection modeling, particularly on very long sequences. We then introduce a method for allowing recurrent models to achieve similar performance: breaking long sentences into clause-like units at punctuation and processing them separately before combining. Our results thus help understand the limitations of both classes of models, and suggest directions for improving recurrent models.

211 citations


Posted Content
TL;DR: This paper proposed models to leverage the phrase pairs from the PPDB to build parametric paraphrase models that score paraphrase pairs more accurately than the internal scores while simultaneously improving its coverage, achieving state-of-the-art results on standard word and bigram similarity tasks.
Abstract: The Paraphrase Database (PPDB; Ganitkevitch et al., 2013) is an extensive semantic resource, consisting of a list of phrase pairs with (heuristic) confidence estimates. However, it is still unclear how it can best be used, due to the heuristic nature of the confidences and its necessarily incomplete coverage. We propose models to leverage the phrase pairs from the PPDB to build parametric paraphrase models that score paraphrase pairs more accurately than the PPDB's internal scores while simultaneously improving its coverage. They allow for learning phrase embeddings as well as improved word embeddings. Moreover, we introduce two new, manually annotated datasets to evaluate short-phrase paraphrasing models. Using our paraphrase model trained using PPDB, we achieve state-of-the-art results on standard word and bigram similarity tasks and beat strong baselines on our new short phrase paraphrase tasks.

206 citations



Posted Content
TL;DR: The authors show that recursive neural models can outperform simple recurrent neural networks (LSTM and LSTM) on several tasks, such as sentiment classification at the sentence level and phrase level, matching questions to answer-phrases, discourse parsing and semantic relation extraction.
Abstract: Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. But there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is appropriate. In this paper we benchmark {\bf recursive} neural models against sequential {\bf recurrent} neural models (simple recurrent and LSTM models), enforcing apples-to-apples comparison as much as possible. We investigate 4 tasks: (1) sentiment classification at the sentence level and phrase level; (2) matching questions to answer-phrases; (3) discourse parsing; (4) semantic relation extraction (e.g., {\em component-whole} between nouns). Our goal is to understand better when, and why, recursive models can outperform simpler models. We find that recursive models help mainly on tasks (like semantic relation extraction) that require associating headwords across a long distance, particularly on very long sequences. We then introduce a method for allowing recurrent models to achieve similar performance: breaking long sentences into clause-like units at punctuation and processing them separately before combining. Our results thus help understand the limitations of both classes of models, and suggest directions for improving recurrent models.

Proceedings ArticleDOI
07 Jun 2015
TL;DR: This work introduces the problem of visual verification of relation phrases and developed a Visual Knowledge Extraction system called VisKE, which has been used to not only enrich existing textual knowledge bases by improving their recall, but also augment open-domain question-answer reasoning.
Abstract: How can we know whether a statement about our world is valid. For example, given a relationship between a pair of entities e.g., ‘eat(horse, hay)’, how can we know whether this relationship is true or false in general. Gathering such knowledge about entities and their relationships is one of the fundamental challenges in knowledge extraction. Most previous works on knowledge extraction have focused purely on text-driven reasoning for verifying relation phrases. In this work, we introduce the problem of visual verification of relation phrases and developed a Visual Knowledge Extraction system called VisKE. Given a verb-based relation phrase between common nouns, our approach assess its validity by jointly analyzing over text and images and reasoning about the spatial consistency of the relative configurations of the entities and the relation involved. Our approach involves no explicit human supervision thereby enabling large-scale analysis. Using our approach, we have already verified over 12000 relation phrases. Our approach has been used to not only enrich existing textual knowledge bases by improving their recall, but also augment open-domain question-answer reasoning.

Posted Content
TL;DR: In this article, a purely bilinear model is trained to learn a metric between an image representation and phrases that are used to describe the image, and the model is then able to infer phrases from a given image sample.
Abstract: Generating a novel textual description of an image is an interesting problem that connects computer vision and natural language processing. In this paper, we present a simple model that is able to generate descriptive sentences given a sample image. This model has a strong focus on the syntax of the descriptions. We train a purely bilinear model that learns a metric between an image representation (generated from a previously trained Convolutional Neural Network) and phrases that are used to described them. The system is then able to infer phrases from a given image sample. Based on caption syntax statistics, we propose a simple language model that can produce relevant descriptions for a given test image using the phrases inferred. Our approach, which is considerably simpler than state-of-the-art models, achieves comparable results in two popular datasets for the task: Flickr30k and the recently proposed Microsoft COCO.

Proceedings ArticleDOI
05 Jun 2015
TL;DR: This article proposed an abstraction-based multidocument summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases, and employed integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary.
Abstract: We propose an abstraction-based multidocument summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases. Different from existing abstraction-based approaches, our method first constructs a pool of concepts and facts represented by phrases from the input documents. Then new sentences are generated by selecting and merging informative phrases to maximize the salience of phrases and meanwhile satisfy the sentence construction constraints. We employ integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary. Experimental results on the benchmark data set TAC 2011 show that our framework outperforms the state-ofthe-art models under automated pyramid evaluation metric, and achieves reasonably well results on manual linguistic quality evaluation.

Proceedings ArticleDOI
10 Aug 2015
TL;DR: This paper investigates entity recognition (ER) with distant-supervision and proposes a novel relation phrase-based ER framework, called ClusType, that runs data-driven phrase mining to generate entity mention candidates and relation phrases, and enforces the principle that relation phrases should be softly clustered when propagating type information between their argument entities.
Abstract: Entity recognition is an important but challenging research problem. In reality, many text collections are from specific, dynamic, or emerging domains, which poses significant new challenges for entity recognition with increase in name ambiguity and context sparsity, requiring entity detection without domain restriction. In this paper, we investigate entity recognition (ER) with distant-supervision and propose a novel relation phrase-based ER framework, called ClusType, that runs data-driven phrase mining to generate entity mention candidates and relation phrases, and enforces the principle that relation phrases should be softly clustered when propagating type information between their argument entities. Then we predict the type of each entity mention based on the type signatures of its co-occurring relation phrases and the type indicators of its surface name, as computed over the corpus. Specifically, we formulate a joint optimization problem for two tasks, type propagation with relation phrases and multi-view relation phrase clustering. Our experiments on multiple genres---news, Yelp reviews and tweets---demonstrate the effectiveness and robustness of ClusType, with an average of 37% improvement in F1 score over the best compared method.

Journal ArticleDOI
TL;DR: It is argued that earlier claims that intonation is not necessary for correct turn-end projection are misguided, and that research on turn-taking should continue to considerintonation as a source of turn- end cues along with other linguistic and communicative phenomena.

Posted Content
04 Jun 2015
TL;DR: This paper proposed an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases, and employed integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary.
Abstract: We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases. Different from existing abstraction-based approaches, our method first constructs a pool of concepts and facts represented by phrases from the input documents. Then new sentences are generated by selecting and merging informative phrases to maximize the salience of phrases and meanwhile satisfy the sentence construction constraints. We employ integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary. Experimental results on the benchmark data set TAC 2011 show that our framework outperforms the state-of-the-art models under automated pyramid evaluation metric, and achieves reasonably well results on manual linguistic quality evaluation.

Journal ArticleDOI
TL;DR: Experiments show that tweet segmentation quality is significantly improved by learning both global and local contexts compared with using global context alone, and that high accuracy is achieved in named entity recognition by applying segment-based part-of-speech (POS) tagging.
Abstract: Twitter has attracted millions of users to share and disseminate most up-to-date information, resulting in large volumes of data produced everyday However, many applications in Information Retrieval (IR) and Natural Language Processing (NLP) suffer severely from the noisy and short nature of tweets In this paper, we propose a novel framework for tweet segmentation in a batch mode, called HybridSeg By splitting tweets into meaningful segments, the semantic or context information is well preserved and easily extracted by the downstream applications HybridSeg finds the optimal segmentation of a tweet by maximizing the sum of the stickiness scores of its candidate segments The stickiness score considers the probability of a segment being a phrase in English (ie, global context) and the probability of a segment being a phrase within the batch of tweets (ie, local context) For the latter, we propose and evaluate two models to derive local context by considering the linguistic features and term-dependency in a batch of tweets, respectively HybridSeg is also designed to iteratively learn from confident segments as pseudo feedback Experiments on two tweet data sets show that tweet segmentation quality is significantly improved by learning both global and local contexts compared with using global context alone Through analysis and comparison, we show that local linguistic features are more reliable for learning local context compared with term-dependency As an application, we show that high accuracy is achieved in named entity recognition by applying segment-based part-of-speech (POS) tagging

Journal ArticleDOI
TL;DR: This work proposes efficient unsupervised and task-specific learning objectives that scale the model to large datasets and demonstrates improvements on both language modeling and several phrase semantic similarity tasks with various phrase lengths.
Abstract: Lexical embeddings can serve as useful representations for words for a variety of NLP tasks, but learning embeddings for phrases can be challenging. While separate embeddings are learned for each word, this is infeasible for every phrase. We construct phrase embeddings by learning how to compose word embeddings using features that capture phrase structure and context. We propose efficient unsupervised and task-specific learning objectives that scale our model to large datasets. We demonstrate improvements on both language modeling and several phrase semantic similarity tasks with various phrase lengths. We make the implementation of our model and the datasets available for general use.

Proceedings Article
25 Jul 2015
TL;DR: The Phrase Detectives game as discussed by the authors is an interactive online game-with-a-purpose for creating anaphorically annotated resources that makes use of a highly distributed population of contributors with different levels of expertise.
Abstract: We are witnessing a paradigm shift in human language technology that may well have an impact on the field comparable to the statistical revolution: acquiring large-scale resources by exploiting collective intelligence. An illustration of this approach is Phrase Detectives, an interactive online game-with-a-purpose for creating anaphorically annotated resources that makes use of a highly distributed population of contributors with different levels of expertise. The paper gives an overview of all aspects of Phrase Detectives, from the design of the game and the methods used, to the results obtained so far. It furthermore summarises the lessons that have been learnt in developing the game to help other researchers assess and implement the approach.

Proceedings ArticleDOI
01 Jul 2015
TL;DR: This work presents an account of word and phrase meaning that is perceptually grounded, trainable, compositional, and ‘dialogueplausible’ in that it computes meanings word-by-word.
Abstract: An elementary way of using language is to refer to objects. Often, these objects are physically present in the shared environment and reference is done via mention of perceivable properties of the objects. This is a type of language use that is modelled well neither by logical semantics nor by distributional semantics, the former focusing on inferential relations between expressed propositions, the latter on similarity relations between words or phrases. We present an account of word and phrase meaning that is perceptually grounded, trainable, compositional, and ‘dialogueplausible’ in that it computes meanings word-by-word. We show that the approach performs well (with an accuracy of 65% on a 1-out-of-32 reference resolution task) on direct descriptions and target/landmark descriptions, even when trained with less than 800 training examples and automatically transcribed utterances.

Proceedings ArticleDOI
Qiao Qian1, Bo Tian, Minlie Huang1, Yang Liu2, Xuan Zhu2, Xiaoyan Zhu1 
01 Jul 2015
TL;DR: Two models are proposed, Tag Guided RNN (TGRNN for short) which chooses a composition function according to the part-ofspeech tag of a phrase, and Tag Embedded RNN/RNTN (TE-RNN/ RNTN for long) which learns tag embeddings and then combines tag and word embedDings together.
Abstract: Recursive neural network is one of the most successful deep learning models for natural language processing due to the compositional nature of text. The model recursively composes the vector of a parent phrase from those of child words or phrases, with a key component named composition function. Although a variety of composition functions have been proposed, the syntactic information has not been fully encoded in the composition process. We propose two models, Tag Guided RNN (TGRNN for short) which chooses a composition function according to the part-ofspeech tag of a phrase, and Tag Embedded RNN/RNTN (TE-RNN/RNTN for short) which learns tag embeddings and then combines tag and word embeddings together. In the fine-grained sentiment classification, experiment results show the proposed models obtain remarkable improvement: TG-RNN/TE-RNN obtain remarkable improvement over baselines, TE-RNTN obtains the second best result among all the top performing models, and all the proposed models have much less parameters/complexity than their counterparts.

Proceedings ArticleDOI
28 Jul 2015
TL;DR: This survey aims to categorize SA techniques in general, without focusing on specific level or task, and found that machine learning-based techniques including supervised learning, unsupervisedLearning and semi-supervised learning techniques, Lexicon-based Techniques and hybrid techniques are the most frequent techniques used.
Abstract: Sentiment Analysis (SA) task is to label people's opinions as different categories such as positive and negative from a given piece of text. Another task is to decide whether a given text is subjective, expressing the writer's opinions, or objective, expressing. These tasks were performed at different levels of analysis ranging from the document level, to the sentence and phrase level. Another task is aspect extraction which originated from aspect-based sentiment analysis in phrase level. All these tasks are under the umbrella of SA. In recent years a large number of methods, techniques and enhancements have been proposed for the problem of SA in different tasks at different levels. This survey aims to categorize SA techniques in general, without focusing on specific level or task. And also to review the main research problems in recent articles presented in this field. We found that machine learning-based techniques including supervised learning, unsupervised learning and semi-supervised learning techniques, Lexicon-based techniques and hybrid techniques are the most frequent techniques used. The open problems are that recent techniques are still unable to work well in different domain; sentiment classification based on insufficient labeled data is still a challenging problem; there is lack of SA research in languages other than English; and existing techniques are still unable to deal with complex sentences that requires more than sentiment words and simple parsing.

Proceedings ArticleDOI
01 Jun 2015
TL;DR: A new method is introduced that allows word and phrase vectors to adapt to the notion of composition and learn a VSM that is both tailored to support a chosen semantic composition operation, and whose resulting features have an intuitive interpretation.
Abstract: Vector Space Models (VSMs) of Semantics are useful tools for exploring the semantics of single words, and the composition of words to make phrasal meaning. While many methods can estimate the meaning (i.e. vector) of a phrase, few do so in an interpretable way. We introduce a new method (CNNSE) that allows word and phrase vectors to adapt to the notion of composition. Our method learns a VSM that is both tailored to support a chosen semantic composition operation, and whose resulting features have an intuitive interpretation. Interpretability allows for the exploration of phrasal semantics, which we leverage to analyze performance on a behavioral task.

Journal ArticleDOI
01 Mar 2015-Syntax
TL;DR: In this article, the authors report on the results of five experiments documenting the existence of three distinct grammars of conjunct agreement in Slovenian, found both within and across individuals.
Abstract: In this paper we report on the results of five experiments documenting the existence of three distinct grammars of conjunct agreement in Slovenian, found both within and across individuals: agreement with the highest conjunct, agreement with the closest conjunct, or agreement with the Boolean Phrase itself. We show that this variation is constrained and that some of these mechanisms can be blocked and/or forced depending on the properties of the conjuncts. Finally, we offer the suggestion that the presence of intraindividual variation arises because of ambiguous properties of the primary linguistic data.

15 Sep 2015
TL;DR: The complex adaptive system (N. Ellis & Larsen-Freeman, 2009b) of interactions within AND across form and function is far richer than that emergent from implicit or explicit learning alone.
Abstract: Learning symbols and their arrangement in language involves learning associations across and within modalities. Research on implicit learning and chunking within modalities (e.g. N. C. Ellis, 2002) has identified how language users are sensitive to the frequency of language forms and their sequential probabilities at all levels of granularity from phoneme to phrase. This knowledge allows efficient language processing and underpins acquisition by syntactic bootstrapping. Research on explicit learning (e.g. N. C. Ellis, 2005) has shown how conscious processing promotes the acquisition of novel explicit cross-modal form-meaning associations. These breathe meaning into the processing of language form and they underpin acquisition by semantic bootstrapping. This is particularly important in establishing novel processing routines in L2 acquisition. These representations are also then available as units of implicit learning in subsequent processing. Language systems emerge, both diachronically and ontogenetically, from the statistical abstraction of patterns latent within and across form and function in language usage. The complex adaptive system (N. C. Ellis & Larsen-Freeman, 2009b) of interactions within AND across form and function is far richer than that emergent from implicit or explicit learning alone.

Proceedings ArticleDOI
09 Nov 2015
TL;DR: mppSMT as mentioned in this paper is a divide-and-conquer technique for phrase-based SMT to model and translate source code with well-formed structures, but it does not support rule-based methods.
Abstract: Prior research shows that directly applying phrase-based SMT on lexical tokens to migrate Java to C# produces much semantically incorrect code. A key limitation is the use of sequences in phrase-based SMT to model and translate source code with well-formed structures. We propose mppSMT, a divide-and-conquer technique to address that with novel training and migration algorithms using phrase-based SMT in three phases. First, mppSMT treats a program as a sequence of syntactic units and maps/translates such sequences in two languages to one another. Second, with a syntax-directed fashion, it deals with the tokens within syntactic units by encoding them with semantic symbols to represent their data and token types. This encoding via semantic symbols helps better migration of API usages. Third, the lexical tokens corresponding to each sememe are mapped or migrated. The resulting sequences of tokens are merged together to form the final migrated code. Such divide-and-conquer and syntax-direction strategies enable phrase-based SMT to adapt well to syntactical structures in source code, thus, improving migration accuracy. Our empirical evaluation on several real-world systems shows that 84.8 -- 97.9% and 70 -- 83% of the migrated methods are syntactically and semantically correct, respectively. 26.3 -- 51.2% of total migrated methods are exactly matched to the human-written C# code in the oracle. Compared to Java2CSharp, a rule-based migration tool, it achieves higher semantic accuracy from 6.6 -- 57.7% relatively. Importantly, it does not require manual labeling for training data or manual definition of rules.

Journal ArticleDOI
TL;DR: It is argued that the distribution of phrase-level phrase accents in Connemara Irish provides a new type of evidence in favour of the hypothesis that, under ideal conditions, syntactic constituents are mapped onto prosodic constituents in a one-to-one fashion, such that information about the nested relationships between syntactic constituent is preserved through the recursion of prosodic domains.
Abstract: One function of prosodic phrasing is its role in aiding in the recoverability of syntactic structure. In recent years, a growing body of work suggests it is possible to find concrete phonetic and phonological evidence that recursion in syntactic structure is preserved in the prosodic organization of utterances (Ladd 1986, 1988; Kubozono 1989, 1992; Fery and Truckenbrodt 2005; Wagner 2005, 2010; Selkirk 2009, 2011; Ito and Mester 2013; Myrberg 2013). This paper argues that the distribution of phrase-level phrase accents in Connemara Irish provides a new type of evidence in favour of this hypothesis: that, under ideal conditions, syntactic constituents are mapped onto prosodic constituents in a one-to-one fashion, such that information about the nested relationships between syntactic constituents is preserved through the recursion of prosodic domains. Through an empirical investigation of both clausal and nominal constructions, I argue that the distribution of phrasal phrase accents in Connemara Irish can be used as a means of identifying recursive bracketing in prosodic structure.

Proceedings ArticleDOI
01 Jul 2015
TL;DR: C-PHRASE, a distributional semantic model that learns word representations by optimizing context prediction for phrases at all levels in a syntactic tree, outperforms the state-of-theart C-BOW model on a variety of lexical tasks.
Abstract: We introduce C-PHRASE, a distributional semantic model that learns word representations by optimizing context prediction for phrases at all levels in a syntactic tree, from single words to full sentences. C-PHRASE outperforms the state-of-theart C-BOW model on a variety of lexical tasks. Moreover, since C-PHRASE word vectors are induced through a compositional learning objective (modeling the contexts of words combined into phrases), when they are summed, they produce sentence representations that rival those generated by ad-hoc compositional models.