Search Results for author:
Found 32 papers, 16 papers with code
How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task
This work shows that competitive translation results can be obtained in a constrained setting by incorporating the latest advances in memory and compute optimization.
A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs
Negation is one of the most fundamental concepts in human cognition and language, and several natural language inference (NLI) probes have been designed to investigate pretrained language models’ ability to detect and reason with negation.
Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task
We evaluated a range of neural machine translation techniques developed specifically for low-resource scenarios.
Linguistic Annotation of Neo-Latin Mathematical Texts: A Pilot-Study to Improve the Automatic Parsing of the Archimedes Latinus
This paper describes the process of syntactically parsing the Latin translation by Jacopo da San Cassiano of the Greek mathematical work The Spirals of Archimedes.
What is 'Typological Diversity' in NLP?
We recommend future work to include an operationalization of 'typological diversity' that empirically justifies the diversity of language samples.
Sociolinguistically Informed Interpretability: A Case Study on Hinglish Emotion Classification
Emotion classification is a challenging task in NLP due to the inherent idiosyncratic and subjective nature of linguistic expression, especially with code-mixed data.
CreoleVal: Multilingual Multitask Benchmarks for Creoles
Creoles represent an under-explored and marginalized group of languages, with few available resources for NLP research.
A Two-Sided Discussion of Preregistration of NLP Research
Van Miltenburg et al. (2021) suggest NLP research should adopt preregistration to prevent fishing expeditions and to promote publication of negative results.
Language Modelling with Pixels
We pretrain the 86M parameter PIXEL model on the same English data as BERT and evaluate on syntactic and semantic tasks in typologically diverse languages, including various non-Latin scripts.
Ranked #1 on
Named Entity Recognition (NER)
on MasakhaNER
What a Creole Wants, What a Creole Needs
We demonstrate, through conversations with Creole experts and surveys of Creole-speaking communities, how the things needed from language technology can change dramatically from one language to another, even when the languages are considered to be very similar to each other, as with Creoles.
Challenges and Strategies in Cross-Cultural NLP
Various efforts in the Natural Language Processing (NLP) community have been made to accommodate linguistic diversity and serve speakers of many different languages.
Finding Structural Knowledge in Multimodal-BERT
In this work, we investigate the knowledge learned in the embeddings of multimodal-BERT models.
Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning
Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models (Wu and Dredze 2019), but only between related languages.
Parsing with Pretrained Language Models, Multiple Datasets, and Dataset Embeddings
With an increase of dataset availability, the potential for learning from a variety of data sources has increased.
On Language Models for Creoles
Creole languages such as Nigerian Pidgin English and Haitian Creole are under-resourced and largely ignored in the NLP literature.
Itihasa: A large-scale corpus for Sanskrit to English translation
This work introduces Itihasa, a large-scale translation dataset containing 93, 000 pairs of Sanskrit shlokas and their English translations.
Ranked #1 on
Machine Translation
on Itihasa
Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics
Building robust natural language understanding systems will require a clear characterization of whether and how various linguistic meaning representations complement each other.
K\opsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding
We present K{\o}psala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020.
Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding
We present K{\o}psala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020.
Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing - A Tale of Two Parsers Revisited
Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, while graph-based parsers benefit from global optimization but have restricted feature scope.
Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing -- A Tale of Two Parsers Revisited
Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, while graph-based parsers benefit from global optimization but have restricted feature scope.
What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions?
We find that the parser learns different information about AVCs and FMVs if only sequential models (BiLSTMs) are used in the architecture but similar information when a recursive layer is used.
Recursive Subtree Composition in LSTM-Based Dependency Parsing
When ablating the forward LSTM, performance drops less dramatically and composition recovers a substantial part of the gap, indicating that a forward LSTM and composition capture similar information.
82 Treebanks, 34 Models: Universal Dependency Parsing with Multi-Treebank Models
We present the Uppsala system for the CoNLL 2018 Shared Task on universal dependency parsing.
Nightmare at test time: How punctuation prevents parsers from generalizing
Punctuation is a strong indicator of syntactic structure, and parsers trained on text with punctuation often rely heavily on this signal.
Parameter sharing between dependency parsers for related languages
We find that sharing transition classifier parameters always helps, whereas the usefulness of sharing word and/or character LSTM parameters varies.
An Investigation of the Interactions Between Pre-Trained Word Embeddings, Character Models and POS Tags in Dependency Parsing
We provide a comprehensive analysis of the interactions between pre-trained word embeddings, character models and POS tags in a transition-based dependency parser.
Parser Training with Heterogeneous Treebanks
How to make the most of multiple heterogeneous treebanks when training a monolingual dependency parser is an open question.
Arc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle
In this paper, we extend the arc-hybrid system for transition-based parsing with a swap transition that enables reordering of the words and construction of non-projective trees.
From Raw Text to Universal Dependencies - Look, No Tags!
We present the Uppsala submission to the CoNLL 2017 shared task on parsing from raw text to universal dependencies.
CCG Parsing and Multiword Expressions
We show that the baseline model performs significantly better on our gold standard when the data are collapsed before parsing than when the data are collapsed after parsing which indicates that there is a parsing effect.
