Улучшение точности

We present a new framework for classify- ing common nouns that extends named- entity classification. We used a fixed set of 26 semantic labels, which we called su- persenses. These …...

Many Web news portals have provided clustered news categories for readers to browse many related news articles. However, to the best of our knowledge, they only provide monolingual services. For …...

Although a lot of progress has been made recently in word segmentation and POS tagging for Chinese, the output of cur- rent state-of-the-art systems is too inaccu- rate to allow …...

This paper proposes a dependency parsing method that uses bilingual constraints to improve the accuracy of parsing bilingual texts (bitexts). In our method, a target- side tree fragment that corresponds …...

Temporal resolution systems are tradition- ally tuned to a particular language, re- quiring significant human effort to trans- late them to new languages. We present a language independent semantic parser …...

AbstractAnnotated data is prerequisite for many NLP applications. Acquiring large-scale annotated corpora is a major bottleneck, requiring significant time and resources. Recent work has proposed turning annotation into a game …...

We propose a novel reranking method to extend a deterministic neural dependency parser. Different to conventional k-best reranking, the proposed model integrates search and learning by utilizing a dynamic action …...

Digital personal assistants are becoming both more common and more useful. The major NLP challenge for personal assis- tants is machine understanding: translat- ing natural language user commands into an …...

A corpus of inference rules between a pair of relation phrases is typically generated us- ing the statistical overlap of argument-pairs associated with the relations (e.g., PATTY, CLEAN). We investigate …...

AbstractModeling U.S. Congressional legislation and roll-call votes has received significant attention in previous literature, and while legislators across 50 state governments and D.C. propose over 100,000 bills each year, enacting …...

AbstractWe present a new dataset and models for comprehending paragraphs about processes (e.g., photosynthesis), an important genre of text describing a dynamic world. The new dataset, ProPara, is the first …...

AbstractMultilingual writers and speakers often alternate between two languages in a single discourse. This practice is called “code-switching”. Existing sentiment detection methods are usually trained on sentiment-labeled monolingual text. Manually …...

AbstractPrior works investigating the geometry of pre-trained word embeddings have shown that word embeddings to be distributed in a narrow cone and by centering and projecting using principal component vectors …...

AbstractContext-aware historical text normalisation is a severely under-researched area. To fill the gap we propose a context-aware normalisation approach that relies on the state-of-the-art methods in neural machine translation and …...

AbstractWe propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic …...

AbstractWith the widespread commercialization of smart devices, research on environmental sound classification has gained more and more attention in recent years. In this paper, we set out to make effective …...

AbstractDeriving and modifying graphs from natural language text has become a versatile basis technology for information extraction with applications in many subfields, such as semantic parsing or knowledge graph construction. …...

AbstractAnswer Sentence Selection (AS2) is an efficient approach for the design of open-domain Question Answering (QA) systems. In order to achieve low latency, traditional AS2 models score question-answer pairs individually, …...

There are two types of datasets for data-to- text: one uses raw data obtained in the real world, and the other is constructed artificially for a controlled task. A straightforwardly …...

AbstractThe World Health Organization has emphasised the need of stepping up suicide prevention efforts to meet the United Nation’s Sustainable Development Goal target of 2030 (Goal 3: Good health and …...

AbstractSelf-attention heads are characteristic of Transformer models and have been well studied for interpretability and pruning. In this work, we demonstrate an altogether different utility of attention heads, namely for …...

AbstractThis paper presents a language-independent approach for morphological disambiguation which has been regarded as an extension of POS tagging, jointly predicting complex morphological tags. In the proposed approach, all words, …...

AbstractDo all instances need inference through the big models for a correct prediction? Perhaps not; some instances are easy and can be answered correctly by even small capacity models. This …...

AbstractBantu languages are spoken by communities in more than half of the countries on the African continent by an estimated third of a billion people. Despite this populous and the …...

In recent years, reviews of various products by purchasers have been posted on websites. By browsing these reviews, company representa- tives intend to collect and analyze opinions from the users' …...