Снижение Ошибок

We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to re- solve ambiguity. HBG incorporates lexical, syn- tactic, semantic, …...

Repair processing plays an important role in spoken language processing systems. This paper proposes a method for correcting Chinese repetition repairs and demonstrates the effects of repair processing in Chinese …...

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag con- texts via a dependency network representa- tion, (ii) broad …...

We discuss two named-entity recognition mod- els which use characters and character � -grams either exclusively or as an important part of their data representation. The first model is a …...

We introduce two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees. The models use syntactic and lexical features. A discourse parsing …...

We present a technique for augmenting annotated training data with hierarchical word clusters that are automatically derived from a large unannotated corpus. Cluster membership is encoded in features that are …...

We examine the utility of speech and lexical fea- tures for predicting student emotions in computer- human spoken tutoring dialogues. We first anno- tate student turns for negative, neutral, positive …...

Most current statistical natural language process- ing models use only local features so as to permit dynamic programming in inference, but this makes them unable to fully account for the …...

This paper presents a novel approach to combining different word alignments. We view word alignment as a pattern classifi- cation problem, where alignment combi- nation is treated as a classifier …...

. We present a preliminary study of several parser adaptation techniques evaluated on the GENIA corpus of MEDLINE abstracts [1,2]. We begin by observing that the Penn Treebank (PTB) is …...

Recent developments in statistical modeling of various linguistic phenomena have shown that additional features give consistent per- formance improvements. Quite often, im- provements are limited by the number of fea- …...

NLP systems for tasks such as question answering and information extraction typ- ically rely on statistical parsers. But the ef- ficacy of such parsers can be surprisingly low, particularly for …...

Transforming syntactic representations in order to improve parsing accuracy has been exploited successfully in statistical parsing systems using constituency-based representations. In this paper, we show that similar transformations can give …...

We describe a word alignment platform which ensures text pre-processing (to- kenization, POS-tagging, lemmatization, chunking, sentence alignment) as re- quired by an accurate word alignment. The platform combines two different …...

Named-entity recognition systems extract entities such as people, organizations, and locations from unstructured text. Rather than extract these mentions in isolation, this paper presents a record extraction sys- tem that …...

This paper demonstrates how unsupervised tech- niques can be used to learn models of deep linguis- tic structure. Determining the semantic roles of a verb’s dependents is an important step …...

We introduce a framework for syntactic parsing with latent variables based on a form of dynamic Sigmoid Belief Networks called Incremental Sigmoid Belief Networks. We demonstrate that a previous feed-forward …...

Traditional noun phrase coreference res- olution systems represent features only of pairs of noun phrases. In this paper, we propose a machine learning method that enables features over sets of …...

An open issue in data-driven dependency parsing is how to handle non-projective dependencies, which seem to be required by linguistically adequate representations, but which pose problems in parsing with respect …...

We study the issue of porting a known NLP method to a language with little existing NLP resources, specifically Hebrew SVM-based chunking. We introduce two SVM-based methods – Model Tampering …...

We propose a cascaded linear model for joint Chinese word segmentation and part- of-speech tagging. With a character-based perceptron as the core, combined with real- valued features such as language …...

VerbNet (VN) is a major large-scale En- glish verb lexicon. Mapping verb instances to their VN classes has been proven use- ful for several NLP tasks. However, verbs are polysemous …...

In this paper we explore robustness and domain adaptation issues for Word Sense Disambiguation (WSD) using Singular Value Decomposition (SVD) and unlabeled data. We focus on the semi-supervised do- main …...

State-of-the-art statistical parsing models applied to free word-order languages tend to underperform compared to, e.g., pars- ing English. Constituency-based mod- els often fail to capture generalizations that cannot be stated …...

Morphological disambiguation proceeds in 2 stages: (1) an analyzer provides all possible analyses for a given token and (2) a stochastic disambiguation module picks the most likely analysis in context. …...

For centuries, the deep connection between languages has brought about major discover- ies about human communication. In this pa- per we investigate how this powerful source of information can be …...

We demonstrate the effectiveness of multilin- gual learning for unsupervised part-of-speech tagging. The key hypothesis of multilin- gual learning is that by combining cues from multiple languages, the structure of …...

Finding negation signals and their scope in text is an important subtask in information ex- traction. In this paper we present a machine learning system that finds the scope of …...

. This paper investigates how to best couple hand-annotated data with information extracted from an external lexical resource to improve POS tagging performance. Focusing on French tagging, we introduce a …...

English pronouns like he and they reliably re- flect the gender and number of the entities to which they refer. Pronoun resolution systems can use this fact to filter noun …...

One of the reasons nonparametric Bayesian inference is attracting attention in computa- tional linguistics is because it provides a prin- cipled way of learning the units of generaliza- tion together …...

We present a Hebrew to English transliter- ation method in the context of a machine translation system. Our method uses ma- chine learning to determine which terms are to be …...

We present the results of a large-scale, end-to-end human evaluation of various sentiment summarization models. The evaluation shows that users have a strong preference for summarizers that model sentiment over …...

The work presented in this paper explores a supervised method for learning a prob- abilistic model of a lexicon of VerbNet classes. We intend for the probabilis- tic model to …...

The character-based tagging approach is a dominant technique for Chinese word segmentation, and both discrimi- native and generative models can be adopted in that framework. However, generative and discriminative charac- …...

Automatically finding email messages that contain requests for action can provide valu- able assistance to users who otherwise strug- gle to give appropriate attention to the ac- tionable tasks in …...

This work incorporates Selectional Prefer- ences (SP) into a Semantic Role (SR) Clas- sification system. We learn separate selec- tional preferences for noun phrases and prepo- sitional phrases and we …...

Although much work in NLP has focused on simply determining what a document means, we also must know whether or not to believe it. Fact-finding algorithms at- tempt to identify …...

Most supervised language processing sys- tems show a significant drop-off in per- formance when they are tested on text that comes from a domain significantly different from the domain of …...

We present an approach to multilin- gual grammar induction that exploits a phylogeny-structured model of parameter drift. Our method does not require any translated texts or token-level alignments. Instead, the …...

Martins et al. (2008) presented what to the best of our knowledge still ranks as the best overall result on the CONLL- X Shared Task datasets. The paper shows how …...

For millions of people in less resourced re- gions of the world, text messages (SMS) pro- vide the only regular contact with their doc- tor. Classifying messages by medical labels …...

We present a new syntactic parser that works left-to-right and top down, thus maintaining a fully-connected parse tree for a few alternative parse hypotheses. All of the commonly used statistical …...

Natural language systems trained on labeled data from one domain do not perform well on other domains. Most adaptation algorithms proposed in the literature train a new model for the …...

Attempts to profile authors according to their characteristics extracted from textual data, in- cluding native language, have drawn attention in recent years, via various machine learn- ing approaches utilising mostly …...

A central topic in natural language process- ing is the design of lexical and syntactic fea- tures suitable for the target application. In this paper, we study convolution dependency tree …...

Counts from large corpora (like the web) can be powerful syntactic cues. Past work has used web counts to help resolve isolated am- biguities, such as binary noun-verb PP attach- …...

Representation learning is a promising tech- nique for discovering features that allow su- pervised classifiers to generalize from a source domain dataset to arbitrary new domains. We present a novel, …...

We present a distantly supervised system for extracting the temporal bounds of fluents (re- lations which only hold during certain times, such as attends school). Unlike previous pipelined approaches, our …...

Semantic role classification accuracy for most languages other than English is constrained by the small amount of annotated data. In this pa- per, we demonstrate how the frame-to-frame relations described …...

We examine the task of temporal relation clas- sification. Unlike existing approaches to this task, we (1) classify an event-event or event- time pair as one of the 14 temporal …...

We present a method of improving the perfor- mance of dialog act tagging in identifying mi- nority classes by using per-class feature opti- mization and a method of choosing the …...

AbstractDuring the course of first language acquisition, children produce linguistic forms that do not conform to adult grammar. In this paper, we introduce a data set and approach for systematically …...

In this paper we introduce the task of unla- beled, optimal, data set selection. Given a large pool of unlabeled examples, our goal is to select a small subset to …...

Often the bottleneck in document classifica- tion is finding good representations that zoom in on the most important aspects of the doc- uments. Most research uses n-gram repre- sentations, but …...

Inspired by robust generalization and adver- sarial learning we describe a novel approach to learning structured perceptrons for part-of- speech (POS) tagging that is less sensitive to domain shifts. The …...

We present an approach for learning context-dependent semantic parsers to identify and interpret time expressions. We use a Combinatory Categorial Gram- mar to construct compositional meaning representations, while considering contex- …...

Despite the successes of distant supervision approaches to relation extraction in the news do- main, the lack of a comprehensive ontology of medical relations makes it difficult to apply such …...

Structured perceptron becomes popular for various NLP tasks such as tagging and parsing. Practical studies on NLP did not pay much attention to its regularization. In this paper, we study …...

We report an empirical investigation on type-supervised domain adaptation for joint Chinese word segmentation and POS-tagging, making use of domain- specific tag dictionaries and only un- labeled target domain data …...

We propose a transition-based model for joint word segmentation, POS tagging and text normalization. Different from pre- vious methods, the model can be trained on standard text corpora, overcoming the …...

Domestic abuse affects people of every race, class, age, and nation. There is sig- nificant research on the prevalence and ef- fects of domestic abuse; however, such re- search typically …...

Monolingual alignment is the task of pair- ing semantically similar units from two pieces of text. We report a top-performing supervised aligner that operates on short text snippets. We employ …...

We present LEMMING, a modular log- linear model that jointly models lemmati- zation and tagging and supports the inte- gration of arbitrary global features. It is trainable on corpora annotated …...

AbstractThis paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees. We use integer linear programming to generate equation trees and score …...

. Robust statistical NLP tools, such as pos-taggers and syntax parsers, often use knowledge-poor features, which can easily be applied to any language, but which do not take into account …...

Word segmentation is usually recognized as the first step for many Chinese natural lan- guage processing tasks, yet its impact on these subsequent tasks is relatively under-studied. For example, how …...

AbstractSpeech that contains multimedia content can pose a serious challenge for real-time automatic speech recognition (ASR) for two reasons: (1) The ASR produces meaningless output, hurting the readability of the …...

AbstractIn this paper we present a tagger developed for inflectionally rich languages for which both a training corpus and a lexicon are available. We do not constrain the tagger by …...

Understanding the argumentative structure of a persuasive essay involves addressing two challenging tasks: identifying the components of the essay’s argument and identifying the relations that occur between them. We ex- …...

Neuro-imaging studies on reading differ- ent parts of speech (PoS) report somewhat mixed results, yet some of them indicate different activations with different PoS. This paper addresses the difficulty of …...

Part-of-speech (POS) taggers trained on newswire perform much worse on domains such as subtitles, lyrics, or tweets. In addition, these domains are also heterogeneous, e.g., with respect to registers and …...

We introduce several probabilistic models for learning the lexicon of a semantic parser. Lex- icon learning is the first step of training a se- mantic parser for a new application …...

AbstractOur goal is to combine the rich multi-step inference of symbolic logical reasoning with the generalization capabilities of neural networks. We are particularly interested in complex reasoning about entities and …...

AbstractWe demonstrate that for sentence-level relation extraction it is beneficial to consider other relations in the sentential context while predicting the target relation. Our architecture uses an LSTM-based encoder to …...

AbstractThis article evaluates purported progress over the past years in RST discourse parsing. Several studies report a relative error reduction of 24 to 51% on all metrics that authors attribute …...

AbstractType-level word embeddings use the same set of parameters to represent all instances of a word regardless of its context, ignoring the inherent lexical ambiguity in language. Instead, we embed …...

AbstractSinglish can be interesting to the ACL community both linguistically as a major creole based on English, and computationally for information extraction and sentiment analysis of regional social media. We …...

In this paper, we describe a novel combination of a character-level recurrent neural-network based model and a language model applied to diacritics restoration. In many cases in the past and …...

AbstractPrevious work on the problem of Arabic Dialect Identification typically targeted coarse-grained five dialect classes plus Standard Arabic (6-way classification). This paper presents the first results on a fine-grained dialect …...

AbstractUser-generated text tends to be noisy with many lexical and orthographic inconsistencies, making natural language processing (NLP) tasks more challenging. The challenging nature of noisy text processing is exacerbated for …...

AbstractAutomatically validating a research artefact is one of the frontiers in Artificial Intelligence (AI) that directly brings it close to competing with human intellect and intuition. Although criticised sometimes, the …...

AbstractIn order to automate banking processes (e.g. payments, money transfers, foreign trade), we need to extract banking transactions from different types of mediums such as faxes, e-mails, and scanners. Banking …...

AbstractRecent studies have shown that pre-trained contextual word embeddings, which assign the same word different vectors in different contexts, improve performance in many tasks. But while contextual embeddings can also …...

AbstractThe Air Travel Information Service (ATIS) corpus has been the most common benchmark for evaluating Spoken Language Understanding (SLU) tasks for more than three decades since it was released. Recent …...

AbstractThe official voting records of United States congresspeople are preserved as roll call votes. Prediction of voting behavior of politicians for whom no voting record exists, such as individuals running …...

AbstractUnsupervised document representation learning is an important task providing pre-trained features for NLP applications. Unlike most previous work which learn the embedding based on self-prediction of the surface of text, …...

AbstractA major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or …...

AbstractIn this paper we present a parsing model for projective dependency trees which takes advantage of the existence of complementary dependency annotations which is the case in Arabic, with the …...

AbstractIn this paper we present a character-level sequence-to-sequence lemmatization model, utilizing several subword features in multiple configurations. In addition to generic n-gram embeddings (using FastText), we experiment with concatenative (stems) …...

AbstractPart of speech (POS) tagging is a familiar NLP task. State of the art taggers routinely achieve token-level accuracies of over 97% on news body text, evidence that the problem …...

AbstractQuestion answering over temporal knowledge graphs (KGs) efficiently uses facts contained in a temporal KG, which records entity relations and when they occur in time, to answer natural language questions …...

AbstractModeling the most likely label when an annotation task is perspective-dependent discards relevant sources of variation that come from the annotators themselves. We present three approaches to modeling the controversiality …...