Совместное обучение
Related Papers
A Discriminative Training Procedure for Continuous Translation Models
Continuous-space translation models have recently emerged as extremely powerful ways to boost the performance of existing translation systems. A simple, yet effec- tive way to integrate such models in infer- …...
Deep Multi-Task Learning with Shared Memory for Text Classification
Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task su- pervised objectives, which often suffer …...
Building Open Javanese and Sundanese Corpora for Multilingual Text-to-Speech
We present multi-speaker text-to-speech corpora for Javanese and Sundanese, the second and third largest languages of Indonesia spoken by well over a hundred million people. The key objectives were to …...
Understanding language-elicited EEG data by predicting it from a fine-tuned language model
AbstractElectroencephalography (EEG) recordings of brain activity taken while participants read or listen to language are widely used within the cognitive neuroscience and psycholinguistics communities as a tool to study language …...
Semantic Graphs for Generating Deep Questions
AbstractThis paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information about the input passage. In order …...
Speech Translation and the End-to-End Promise: Taking Stock of Where We Are
AbstractOver its three decade history, speech translation has experienced several shifts in its primary research themes; moving from loosely coupled cascades of speech recognition and machine translation, to exploring questions …...
A Multi-Level Attention Model for Evidence-Based Fact Checking
Evidence-based fact checking aims to verify the truthfulness of a claim against evidence ex- tracted from textual sources. Learning a rep- resentation that effectively captures relations between a claim and …...
BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation
AbstractIn this paper, we focus on the problem of citing sentence generation, which entails generating a short text to capture the salient information in a cited paper and the connection …...
Cross-Register Projection for Headline Part of Speech Tagging
AbstractPart of speech (POS) tagging is a familiar NLP task. State of the art taggers routinely achieve token-level accuracies of over 97% on news body text, evidence that the problem …...
Evaluating a Joint Training Approach for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora on Lower-resource Languages
AbstractCross-lingual word embeddings provide a way for information to be transferred between languages. In this paper we evaluate an extension of a joint training approach to learning cross-lingual embeddings that …...
FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task
AbstractIn this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by …...
Maastricht University’s Multilingual Speech Translation System for IWSLT 2021
AbstractThis paper describes Maastricht University’s participation in the IWSLT 2021 multilingual speech translation track. The task in this track is to build multilingual speech translation systems in supervised and zero-shot …...
RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
AbstractIn various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final …...
Retrieval Augmented Visual Question Answering with Outside Knowledge
AbstractOutside-Knowledge Visual Question Answering (OK-VQA) is a challenging VQA task that requires retrieval of external knowledge to answer questions about images. Recent OK-VQA systems use Dense Passage Retrieval (DPR) to …...
Transforming Sequence Tagging Into A Seq2Seq Task
AbstractPretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one …...
A Survey of Multi-task Learning in Natural Language Processing: Regarding Task Relatedness and Training Methods
AbstractMulti-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences. Nevertheless, it is still …...