paper-with-me

홈 › Papers

Encodings of Source Syntax: Similarities in NMT Representations Across Target Languages

2020-05-17 · WS 2020 7 · Tyler A. Chang, Anna N. Rafferty

We train neural machine translation (NMT) models from English to six target languages, using NMT encoder representations to predict ancestor constituent labels of source language words. We find that NMT encoders learn similar source syntax regardless of NMT target language, relying on explicit morphosyntactic cues to extract syntactic features from source sentences. Furthermore, the NMT encoders outperform RNNs trained directly on several of the constituent label prediction tasks, suggesting that NMT encoder representations can be used effectively for natural language tasks involving syntax. However, both the NMT encoders and the directly-trained RNNs learn substantially different syntactic information from a probabilistic context-free grammar (PCFG) parser. Despite lower overall accuracy scores, the PCFG often performs well on sentences for which the RNN-based models perform poorly, suggesting that RNN architectures are constrained in the types of syntax they can learn.

📄 PDF Abstract BibTeX arXiv:2005.08177

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationNMTTranslation

Similar Papers 제목 키워드 기반

Assessment of Pre-Trained Models Across Languages and Grammars

2023-09-20 · Alberto Muñoz-Ortiz, David Vilares, Carlos Gómez-Rodríguez

We present an approach for assessing how multilingual large language models (LLMs) learn syntax in terms of multi-formalism syntactic structures. We aim to recover constituent and dependency structures by casting parsing…

Dependency Parsing

When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes

2022-04-20 · NAACL 2022 7 · Mycal Tucker, Tiwalayo Eisape, Peng Qian, Roger Levy 외

Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield "false negative" causality results: models may use representations of syntax, but …

Language ModelingLanguage Modelling

When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Recent causal probing literature reveals when language models and syntactic probes use similar representations. Such techniques may yield ``false negative'' causality results: models may use representations of syntax, bu…

Language ModelingLanguage Modelling

IR2Vec: LLVM IR based Scalable Program Embeddings

2019-09-13 · S. VenkataKeerthy, Rohit Aggarwal, Shalini Jain, Maunendra Sankar Desarkar 외

We propose IR2Vec, a Concise and Scalable encoding infrastructure to represent programs as a distributed embedding in continuous space. This distributed embedding is obtained by combining representation learning methods …

Representation Learning

Machine Translation by Projecting Text into the Same Phonetic-Orthographic Space Using a Common Encoding

2023-05-21 · Amit Kumar, Shantipriya Parida, Ajay Pratap, Anil Kumar Singh

The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by be…

Machine TranslationNMTTranslation