A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition
نویسندگان
چکیده
We show how to adapt bilingual word embeddings (BWE’s) to bootstrap a crosslingual name-entity recognition (NER) system in a language with no labeled data. We assume a setting where we are given a comparable corpus with NER labels for the source language only; our goal is to build a NER model for the target language. The proposed multi-task model jointly trains bilingual word embeddings while optimizing a NER objective. This creates word embeddings that are both shared between languages and fine-tuned for the NER task. As a proof of concept, we demonstrate this model on English-toChinese transfer using Wikipedia.
منابع مشابه
A resource-light method for cross-lingual semantic textual similarity
Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine translation. Recently proposed methods for predicting cross-lingual semantic similarity of short texts, however, make use of tools and resources (e.g., machine translation systems, syntactic parsers or named ...
متن کاملLearning Sense-specific Word Embeddings By Exploiting Bilingual Resources
Recent work has shown success in learning word embeddings with neural network language models (NNLM). However, the majority of previous NNLMs represent each word with a single embedding, which fails to capture polysemy. In this paper, we address this problem by representing words with multiple and sense-specific embeddings, which are learned from bilingual parallel data. We evaluate our embeddi...
متن کاملConditional Random Fields for Spanish Named Entity Recognition Using Unsupervised Features
Unsupervised features based on word representations such as word embeddings and word collocations have shown to significantly improve supervised NER for English. In this work we investigate whether such unsupervised features can also boost supervised NER in Spanish. To do so, we use word representations and collocations as additional features in a linear chain Conditional Random Field (CRF) cla...
متن کاملAdversarial Training for Unsupervised Bilingual Lexicon Induction
Word embeddings are well known to capture linguistic regularities of the language on which they are trained. Researchers also observe that these regularities can transfer across languages. However, previous endeavors to connect separate monolingual word embeddings typically require cross-lingual signals as supervision, either in the form of parallel corpus or seed lexicon. In this work, we show...
متن کاملBilBOWA: Fast Bilingual Distributed Representations without Word Alignments
We introduce BilBOWA (Bilingual Bag-ofWords without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-alig...
متن کامل