Cross-lingual alignment transfer: a chicken-and-egg story?
نویسندگان
چکیده
In this paper, we challenge a basic assumption of many cross-lingual transfer techniques: the availability of word aligned parallel corpora, and consider ways to accommodate situations in which such resources do not exist. We show experimentally that, here again, weakly supervised cross-lingual learning techniques can prove useful, once adapted to transfer knowledge across pairs of languages.
منابع مشابه
Cross-Lingual Discriminative Learning of Sequence Models with Posterior Regularization
We present a framework for cross-lingual transfer of sequence information from a resource-rich source language to a resourceimpoverished target language that incorporates soft constraints via posterior regularization. To this end, we use automatically word aligned bitext between the source and target language pair, and learn a discriminative conditional random field model on the target side. Ou...
متن کاملImproved Named Entity Recognition using Machine Translation-based Cross-lingual Information
In this paper, we describe a technique to improve named entity recognition in a resource-poor language (Hindi) by using cross-lingual information. We use an on-line machine translation system and a separate word alignment phase to find the projection of each Hindi word into the translated English sentence. We estimate the cross-lingual features using an English named entity recognizer and the a...
متن کاملStyle Transfer from Non-Parallel Text by Cross-Alignment
This paper focuses on style transfer on the basis of non-parallel text. This is an instance of a broader family of problems including machine translation, decipherment, and sentiment modification. The key technical challenge is to separate the content from desired text characteristics such as sentiment. We leverage refined alignment of latent representations across mono-lingual text corpora wit...
متن کاملCross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding
Entity alignment is the task of finding entities in two knowledge bases (KBs) that represent the same real-world object. When facing KBs in different natural languages, conventional cross-lingual entity alignment methods rely on machine translation to eliminate the language barriers. These approaches often suffer from the uneven quality of translations between languages. While recent embedding-...
متن کاملEstimation of Per Capita Consumption of Chicken Egg and Attitude of Tehrani Families towards Factors Influencing Egg Consumption in 2018
Background: Eggs are of the few naturally occurring foods that meet the needs of human body in a balanced manner. The present study was conducted to determine the rate of egg per capita consumption in Tehran city in 2018. Methods: The present cross-sectional study was conducted on 4.213 heads of families living in 22 regions of Tehran. Selected randomly using multistage cluster sampling meth...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2016