Обучающие данные

In this paper, a discrimination and robusmess oriented adaptive learning procedure is proposed to deal with the task of syntactic ambiguity resolution. Owing to the problem of insufficient training data …...

We have been developing a spoken language system to recognize and understand spontaneous speech. It is difficult for such systems to achieve good coverage of the lexicon and grammar that …...

This paper describes experiments to establish the performance of a named entity recognition system which builds categorized lists of names from manu- ally annotated training data. Names in text are …...

This paper presents a method that as- sists in maintaining a rule-based named-entity recognition and classifi- cation system. The underlying idea is to use a separate system, constructed with the …...

NLP systems will be more portable among medical domains if acquisition of semantic lexicons can be facilitated. We are pursuing lexical acquisition through the syntactic relationships of words in medical …...

Many recent statistical parsers rely on a preprocess- ing step which uses hand-written, corpus-specific rules to augment the training data with extra infor- mation. For example, head-finding rules are used …...

A serious bottleneck in the development of trainable text summarization systems is the shortage of training data. Constructing such data is a very tedious task, especially because there are in …...

. Researches in speech synthesis and speech analysis are underpinned by the databases they used. The performance of an emotion classifier relies heavily on the qualities of the training and …...

. Fixed multiword expressions are strings of words which to- gether behave like a single word. This research establishes a method for the automatic extraction of such expressions. Our method …...

This paper proposes a method for detect- ing errors in article usage and singular plu- ral usage based on the mass count distinc- tion. First, it learns decision lists from …...

Statistical machine translation is quite ro- bust when it comes to the choice of in- put representation. It only requires con- sistency between training and testing. As a result, there …...

This paper presents the task definition, re- sources, and the single participant system for Task 12: Turkish Lexical Sample Task (TLST), which was organized in the Se- mEval-2007 evaluation exercise. …...

The treatment of ‘spurious’ words of source language is an important problem but often ignored in the discussion on phrase-based SMT. This paper explains why it is impor- tant and …...

In this paper, we describe a system by which the multilingual characteristics of Wikipedia can be utilized to annotate a large corpus of text with Named Entity Recognition (NER) tags …...

We define a probabilistic morphological ana- lyzer using a data-driven approach for Syriac in order to facilitate the creation of an annotated corpus. Syriac is an under-resourced Semitic language for …...

We outline different methods to detect er- rors in automatically-parsed dependency corpora, by comparing so-called depen- dency rules to their representation in the training data and flagging anomalous ones. By …...

Machine Translation (MT) is the task of automatically translating a text from one language to another. In this work we de- scribe a phrase-based Statistical Machine Translation (SMT) system that …...

AbstractThis paper presents and evaluates an original approach to automatically align bitexts at the word level. It relies on a syntactic dependency analysis of the source and target texts and …...

This paper describes how to cluster to- gether the phrases of a phrase-based sta- tistical machine translation (SMT) sys- tem, using information in the phrase table itself. The clustering is …...

Ambiguity of entity mentions and con- cept references is a challenge to mining text beyond surface-level keywords. We describe an effective method of disambi- guating surface forms and resolving them …...

AbstractIn the paper we investigate the impact of data size on a Word Sense Disambiguation task (WSD). We question the assumption that the knowledge acquisition bottleneck, which is known as …...

In many languages the use of compound words is very productive. A common practice to reduce sparsity consists in splitting com- pounds in the training data. When this is done, …...

We describe an approach to coreference resolution that relies on the intuition that easy decisions should be made early, while harder decisions should be left for later when more information …...

The performance of Phrase-Based Statis- tical Machine Translation (PBSMT) sys- tems mostly depends on training data. Many papers have investigated how to cre- ate new resources in order to increase …...

There are some cases where the non- Japanese buyers are unable to find products they want through the Japanese shopping Web sites because they require Japanese queries. We propose to …...

Previous incremental parsers have used monotonic state transitions. However, transitions can be made to revise previous decisions quite naturally, based on further information. We show that a simple adjustment to …...

LDA-frames is an unsupervised approach for identifying semantic frames from semanti- cally unlabeled text corpora, and seems to be a useful competitor for manually created databases of selectional preferences. The …...

Existing semantic parsing research has steadily improved accuracy on a few domains and their corresponding databases. This paper introduces FreeParser, a system that trains on one domain and one set …...

This paper is an overview of the SwatCS system submitted to SemEval-2013 Task 2A: Contextual Polarity Disambiguation. The sen- timent of individual phrases within a tweet are labeled using a …...

AbstractThe spelling competence of school students is best measured on freely written texts, instead of pre-determined, dictated texts. Since the analysis of the error categories in these kinds of texts …...

AbstractUsers of Statistical Machine Translation (SMT) sometimes turn to the Web to obtain data to train their systems. One problem with this approach is the potential for “MT contamination”: when …...

AbstractThe training data size is of utmost importance for statistical machine translation (SMT), since it affects the training time, model size, decoding speed, as well as the system’s overall success. …...

AbstractParallel corpus is a valuable resource for cross-language information retrieval and data-driven natural language processing systems, especially for Statistical Machine Translation (SMT). However, most existing parallel corpora to Chinese are …...

NLP methods for automatic information access to rich technological knowledge sources like patents are of great value. One important resource for accessing this knowledge is the tech- nical terminology of …...

A simile is a comparison between two essentially unlike things, such as “Jane swims like a dolphin”. Similes often ex- press a positive or negative sentiment to- ward something, but …...

This paper addresses the problem of mor- phological modeling in statistical speech-to- speech translation for English to Iraqi Ara- bic. An analysis of user data from a real-time MT-based dialog …...

Wikipedia is the largest collection of ency- clopedic data ever written in the history of humanity. Thanks to its coverage and its availability in machine-readable format, it has become a …...

This paper describes a sentiment classifica- tion system designed for SemEval-2015, Task 10, Subtask B. The system employs a con- strained, supervised text categorization ap- proach. Firstly, since thorough preprocess- …...

AbstractWe argue that the field of spoken CALL needs a shared task in order to facilitate comparisons between different groups and methodologies, and describe a concrete example of such a …...

AbstractThis paper introduces a continuous system capable of automatically producing the most adequate speaking style to synthesize a desired target text. This is done thanks to a joint modeling of …...

AbstractGrammar induction is the task of learning syntactic structure in a setting where that structure is hidden. Grammar induction from words alone is interesting because it is similiar to the …...

AbstractSemantic 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 …...

AbstractWe experiment with different ways of training LSTM networks to predict RST discourse trees. The main challenge for RST discourse parsing is the limited amounts of training data. We combat …...

Relation extraction models based on deep learning have been attracting a lot of at- tention recently. Little research is carried out to reduce their need of labeled training data. In …...

AbstractThe fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution. We investigate …...

AbstractSyntactic parsing plays a crucial role in improving the quality of natural language processing tasks. Although there have been several research projects on syntactic parsing in Vietnamese, the parsing quality …...

AbstractThe main motivation for developing contextsensitive lemmatizers is to improve performance on unseen and ambiguous words. Yet previous systems have not carefully evaluated whether the use of context actually helps …...

Transcribing speech is an important part of language documentation, yet speech recognition technology has not been widely harnessed to aid linguists. We explore the use of a neural network architecture …...

AbstractThis paper introduces open-domain event detection, a new event detection paradigm to address issues of prior work on restricted domains and event annotation. The goal is to detect all kinds …...

AbstractThe overall machine translation quality available for professional translators working with the Spanish–Basque pair is rather poor, which is a deterrent for its adoption. This work investigates the plausibility of …...

Recent development of spoken dialog systems has moved away from a command-style input and aims at allowing a natural input style. Obtaining suitable data for training and testing such systems …...

AbstractThe most important obstacles facing multi-document summarization include excessive redundancy in source descriptions and the looming shortage of training data. These obstacles prevent encoder-decoder models from being used directly, but …...

The paper proposes a system that compensates most of the noise in a text in natural language caused by technical imperfection of the input device such as keyboard or scanner …...

AbstractDomain-specific training typically makes NLP systems work better. We show that this extends to cognitive modeling as well by relating the states of a neural phrase-structure parser to electrophysiological measures …...

Text summarization is an important yet chal- lenging task in natural language processing. In this paper, we investigate Pointer Genera- tor Networks for sentence compression. Using Vietnamese as a case …...

AbstractTraining a supervised neural network classifier typically requires many annotated training samples. Collecting and annotating a large number of data points are costly and sometimes even infeasible. Traditional annotation process …...

AbstractLow-resource machine translation suffers from the scarcity of training data and the unavailability of standard evaluation sets. While a number of research efforts target the former, the unavailability of evaluation …...

AbstractThe widespread usage of Twitter during emergencies has provided a new opportunity and timely resource to crisis responders for various disaster management tasks. Geolocation information of pertinent tweets is crucial …...

AbstractThe current aspect extraction methods suffer from boundary errors. In general, these errors lead to a relatively minor difference between the extracted aspects and the ground-truth. However, they hurt the …...

AbstractLarge amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. …...

AbstractIn this work we present the experiments which lead to the creation of our BERT and ELECTRA based German language models, GBERT and GELECTRA. By varying the input training data, …...

AbstractWe introduce the GM-RKB WikiText Error Correction Task for the automatic detection and correction of typographical errors in WikiText annotated pages. The included corpus is based on a snapshot of …...

AbstractWeakly supervised machine reading comprehension (MRC) task is practical and promising for its easily available and massive training data, but inevitablely introduces noise. Existing related methods usually incorporate extra submodels …...

AbstractA key bottleneck for developing dialog models is the lack of adequate training data. Due to privacy issues, dialog data is even scarcer in the health domain. We propose a …...

AbstractThe ubiquitous nature of dialogue systems and their interaction with users generate an enormous amount of data. Can we improve chatbots using this data? A self-feeding chatbot improves itself by …...

AbstractSocial media is a valuable data resource for various natural language processing (NLP) tasks. However, standard NLP tools were often designed with standard texts in mind, and their performance decreases …...

Usually, we train a neural system on a se- quence of mini-batches of labeled instances. Each mini-batch is composed of k samples, and each sample will learn a representation vector. …...

AbstractNLP community is currently investing a lot more research and resources into development of deep learning models than training data. While we have made a lot of progress, it is …...

AbstractPetroni et al. (2019) demonstrated that it is possible to retrieve world facts from a pre-trained language model by expressing them as cloze-style prompts and interpret the model’s prediction accuracy …...

AbstractQA models based on pretrained language models have achieved remarkable performance on various benchmark datasets. However, QA models do not generalize well to unseen data that falls outside the training …...

AbstractMultimodal pre-training models, such as LXMERT, have achieved excellent results in downstream tasks. However, current pre-trained models require large amounts of training data and have huge model sizes, which make …...

AbstractIn this paper, we present coreference resolution experiments with a newly created multilingual corpus CorefUD (Nedoluzhko et al.,2021). We focus on the following languages: Czech, Russian, Polish, German, Spanish, and …...

AbstractWith the recent advances of open-domain story generation, the lack of reliable automatic evaluation metrics becomes an increasingly imperative issue that hinders the fast development of story generation. According to …...

AbstractBuilding open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the …...

AbstractSplit-and-rephrase is a challenging task that promotes the transformation of a given complex input sentence into multiple shorter sentences retaining equivalent meaning. This rewriting approach conceptualizes that shorter sentences benefit …...

AbstractThis paper addresses the automatic translation of conversational content in a business context, for example support chat dialogues. While such use cases share characteristics with other informal machine translation scenarios, …...

AbstractIn this paper, we compare two different approaches to language understanding for a human-robot interaction domain in which a human commander gives navigation instructions to a robot. We contrast a …...

AbstractCurrent language models achieve low perplexity but their resulting generations still suffer from toxic responses, repetitiveness, and contradictions. The standard language modeling setup fails to address these issues. In this …...

AbstractRecent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could …...

AbstractAutomatizing the process of understanding the global narrative structure of long texts and stories is still a major challenge for state-of-the-art natural language understanding systems, particularly because annotated data is …...

AbstractDespite neural language models qualitatively capturing many human linguistic behaviors, recent work has demonstrated that they underestimate the true processing costs of ungrammatical structures. We extend these more fine-grained comparisons …...

AbstractModern neural language models can produce remarkably fluent and grammatical text. So much, in fact, that recent work by Clark et al. (2021) has reported that conventional crowdsourcing can no …...

AbstractWhile neural text-to-speech systems perform remarkably well in high-resource scenarios, they cannot be applied to the majority of the over 6,000 spoken languages in the world due to a lack …...

AbstractThis paper addressed the problem of structured sentiment analysis using a bi-affine semantic dependency parser, large pre-trained language models, and publicly available translation models. For the monolingual setup, we considered: …...

AbstractTranscription is often reported as the bottleneck in endangered language documentation, requiring large efforts from scarce speakers and transcribers. In general, automatic speech recognition (ASR) can be accurate enough to …...

AbstractPrompt-based tuning for pre-trained language models (PLMs) has shown its effectiveness in few-shot learning. Typically, prompt-based tuning wraps the input text into a cloze question. To make predictions, the model …...

AbstractOften both an utterance and its context must be read to understand its intent in a dialog. Herein we propose a task, Self- Contained Utterance Description (SCUD), to describe the …...

Abstract“Recent advances in the field of abstractive summarization leverage pre-trained language models rather than train a model from scratch. However, such models are sluggish to train and accompanied by a …...

AbstractThe objective of the SemEval-2023 Task 1: Visual Word Sense Disambiguation (VWSD) is to identify the image illustrating the indented meaning of a target word and some minimal additional context. …...

AbstractWhile quality estimation (QE) can play an important role in the translation process, its effectiveness relies on the availability and quality of training data. For QE in particular, high-quality labeled …...

AbstractIn the last few years, the natural language processing community has witnessed advances in neural representations of free texts with transformer-based language models (LMs). Given the importance of knowledge available …...