Zero-shot relation extraction (ZSRE) aims to predict target relations that cannot be observed during training.
This article combines three different ideas (splitting words into smaller units, using an extra dataset of a related language pair and using monolingual data) for improving the performance of NMT models on language pairs with limited data.
Abstract Meaning Representation (AMR) is a sentence-level meaning representation based on predicate argument structure.
This paper presents a novel method for nested named entity recognition.
Ranked #8 on Nested Named Entity Recognition on ACE 2004
Unsupervised image captioning is a challenging task that aims at generating captions without the supervision of image-sentence pairs, but only with images and sentences drawn from different sources and object labels detected from the images.
This paper presents CovRelex, a scientific paper retrieval system targeting entities and relations via relation extraction on COVID-19 scientific papers.
We propose a simple method for nominal coordination boundary identification.
We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e. g. a few hundred sentence pairs).
In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer.
Ranked #1 on Question Answering on TACRED
Unlike the previous models, our length-controllable abstractive summarization model incorporates a word-level extractive module in the encoder-decoder model instead of length embeddings.
We propose a global entity disambiguation (ED) model based on BERT.
Ranked #1 on Entity Disambiguation on WNED-WIKI
Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science.
Recently, a variety of unsupervised methods have been proposed that map pre-trained word embeddings of different languages into the same space without any parallel data.
To make the model robust against infrequent tokens, we sampled segmentation for each sentence stochastically during training, which resulted in improved performance of text classification.
Recently, relation classification has gained much success by exploiting deep neural networks.
The embeddings of entities in a large knowledge base (e. g., Wikipedia) are highly beneficial for solving various natural language tasks that involve real world knowledge.
This paper discusses the representation of coordinate structures in the Universal Dependencies framework for two head-final languages, Japanese and Korean.
Currently, the biaffine classifier has been attracting attention as a method to introduce an attention mechanism into the modeling of binary relations.
Those two tools cooperate so that the words and multi-word expressions stored in Cradle are directly referred to by ChaKi in conducting corpus annotation, and the words and expressions annotated in ChaKi can be output as a list of lexical entities that are to be stored in Cradle.
One main challenge for incremental transition-based parsers, when future inputs are invisible, is to extract good features from a limited local context.
We present a computer-assisted learning system, Jastudy, which is particularly designed for Chinese-speaking learners of Japanese as a second language (JSL) to learn Japanese functional expressions with suggestion of appropriate example sentences.
This paper addresses the tasks of automatic seed selection for bootstrapping relation extraction, and noise reduction for distantly supervised relation extraction.
This paper proposes an inexpensive way to learn an effective dissimilarity function to be used for $k$-nearest neighbor ($k$-NN) classification.
This paper restores interpretability to such methods by restricting the directions of perturbations toward the existing words in the input embedding space.
We present Segment-level Neural CRF, which combines neural networks with a linear chain CRF for segment-level sequence modeling tasks such as named entity recognition (NER) and syntactic chunking.
In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models.
Humans process language word by word and construct partial linguistic structures on the fly before the end of the sentence is perceived.
In order to assess the performance, we construct model based on an attention mechanism encoder-decoder model in which the source language is input to the encoder as a sequence and the decoder generates the target language as a linearized dependency tree structure.
One reason for this is that in the tagging scheme for such languages, a complete POS tag is formed by combining tags from multiple tag sets defined for each morphosyntactic category.
We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique.
The performance of Japanese predicate argument structure (PAS) analysis has improved in recent years thanks to the joint modeling of interactions between multiple predicates.
Because syntactic structures and spans of multiword expressions (MWEs) are independently annotated in many English syntactic corpora, they are generally inconsistent with respect to one another, which is harmful to the implementation of an aggregate system.
Knowledge base completion (KBC) aims to predict missing information in a knowledge base. In this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC:how to answer queries concerning test entities not observed at training time.
Universal Dependencies (UD) is becoming a standard annotation scheme cross-linguistically, but it is argued that this scheme centering on content words is harder to parse than the conventional one centering on function words.
Learning functional expressions is one of the difficulties for language learners, since functional expressions tend to have multiple meanings and complicated usages in various situations.
When translating formal documents, capturing the sentence structure specific to the sublanguage is extremely necessary to obtain high-quality translations.
This paper presents our ongoing work on compilation of English multi-word expression (MWE) lexicon.
Nevertheless, this method often leads to the following problem: A node derived from an MWE could have multiple heads and the whole dependency structure including MWE might be cyclic.
We present an attempt to port the international syntactic annotation scheme, Universal Dependencies, to the Japanese language in this paper.
We propose a transition-based dependency parser using Recurrent Neural Networks with Long Short-Term Memory (LSTM) units.
This paper discusses the effect of hubness in zero-shot learning, when ridge regression is used to find a mapping between the example space to the label space.
Synthetic word analysis is a potentially important but relatively unexplored problem in Chinese natural language processing.
This work presents an initial investigation on how to distinguish collocations from free combinations.
This paper proposes a discriminative forest reranking algorithm for dependency parsing that can be seen as a form of efficient stacked parsing.
In order to construct an annotated diachronic corpus of Japanese, we propose to create a new dictionary for morphological analysis of Early Middle Japanese (Classical Japanese) based on UniDic, a dictionary for Contemporary Japanese.