Chris Dyer · page 2
Papers
- Joshua: An Open Source Toolkit for Parsing-Based Machine Translation (2009 · 163 citations)
Parsing-based statistical MT (Hiero-style hierarchical models and other syntax-driven approaches) had advanced rapidly. - Unsupervised Text Style Transfer using Language Models as Discriminators (2018 · 161 citations)
Unsupervised text style transfer rewrites a sentence so that it carries a different attribute, such as sentiment, cipher orthography or a closely related language, while its content stays the same. - Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold (2017 · 160 citations)
The paper addresses frame-semantic argument identification: finding and labeling the text spans that fill the roles of FrameNet frames. - Discriminative Lexical Semantic Segmentation with Gaps: Running the MWE Gamut (2014 · 159 citations)
The paper addresses the automatic identification of multiword expressions (MWEs) in running English text. It covers the full range of MWE types, from proper names and compounds to phrasal verbs, support-verb constructions and fixed phrases. Earlier work typically targeted one MWE subclass at a time and handled only… - Generation from Abstract Meaning Representation using Tree Transducers (2016 · 152 citations)
The paper generates English from AMR graphs in two steps. A breadth-first spanning tree is taken from the graph, and a weighted tree-to-string transducer turns that tree into a sentence. The transducer rules are extracted from AMR-aligned sentences: each aligned subgraph becomes a rule with argument slots for its… - Machine Learning for Ancient Languages: A Survey (2023 · 124 citations)
This survey maps the published research applying machine learning to texts in ancient languages. It covers any script or writing medium from the first Mesopotamian writing (about 3400 BCE) to the end of the first millennium CE, and it leaves out pre-2000 studies and work that does not use ML. The authors organize the… - Frame-Semantic Role Labeling with Heterogeneous Annotations (2015 · 88 citations)
The paper addresses argument identification in frame-semantic parsing: given a predicate and the FrameNet frame it evokes, the system must find the phrases that fill the frame's roles and label them. - Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale (2022 · 72 citations)
Large Transformer LMs perform strongly without any explicit model of hierarchical syntax. It was unclear whether recursive syntactic composition, which helped small LSTM-based RNNGs, still adds value for Transformers at larger scale. The authors introduce Transformer Grammars (TGs), built on Transformer-XL, which… - Better Document-Level Machine Translation with Bayes' Rule (2020 · 72 citations)
Translating whole documents requires cross-sentence context. For example, Chinese marks tense and number less explicitly than English, so the right English form often depends on other sentences. However, parallel documents for training are scarce. The authors address this by applying Bayes' rule, the classic noisy… - Augmenting English Adjective Senses with Supersenses (2014 · 57 citations)
WordNet groups adjectives into small clusters of near-synonyms but gives them no shared top-level organisation. - Ontology-Aware Token Embeddings for Prepositional Phrase Attachment (2017 · 35 citations)
A type-level embedding gives one vector per word form, so "pool" as a place and "pool" as a game share a vector. - Supersense Tagging for Arabic: the MT-in-the-Middle Attack (2013 · 10 citations)
The paper tackles nominal supersense tagging for Arabic: finding noun chunks and assigning each one of the 25 coarse WordNet noun categories.
This page in Markdown → https://md.research.elamur.ai/free/en/authors/chris-dyer/page/2/